Description:FIELD OF THE INVENTION
[0001] The present application relates to the domain of a vehicle, more specifically the present application is related to a method and system for determining sub-path in a navigational path for a vehicle.

BACKGROUND
[0002] In the present era, Global Positioning System (GPS) has become a popular and extensively used navigation system used by the user for navigating vehicle while moving from one location to another. More specifically, in the GPS system the user inputs the destination name or address via an interface (such as an LCD screen) on the navigation system. Accordingly, the navigation system quickly maps out the preferred route along with estimated time and provides instructions verbally or displays the instructions on a map on the interface, or both. As the user begins driving the vehicle, the navigation system may provide turn-by-turn directions, visually and verbally instructing the user on which road to stay on, which exit to take, where to make a turn, and the like, thereby assisting the user to more efficiently arrive at the desired destination.

[0003] GPS based navigation system provides real-time navigation with traffic data and suggests the preferred route based on road conditions, traffic data, and other parameters. Further, to find a navigation sub-path, you can simply adjust the route by selecting a different starting point, destination, or waypoints along the route. Furthermore, the GPS based navigation system may provide alternative routes that you can choose from. Moreover, during navigation, the GPS based navigation system may also suggest alternative routes if traffic conditions change or if a faster route becomes available.

[0004] One of the problems available with the roads is bad conditions of the roads such as pothole on the roads, irregular speed breakers on the roads, accumulation of water or dust on the road, or the like. The aforesaid problems are universal problems which are faced by almost all the countries and the same is recurring problem creating inevitable damage to the road surfaces from traffic, construction, and the environment. The aforesaid problems can reduce the quality of roads and make them more dangerous to drive on. The presence of potholes or other obstacles can lead to lower property values in the area. The same is dangerous for the user as well as the vehicle. The presence of potholes or other obstacles can cause damage to vehicles such as bent rims, cracked wheels, flat tires, increase in maintenance cost, broken suspension components, and other damage to the vehicle 's undercarriage. The presence of potholes or other obstacles can increase the risk of accidents and make roads more dangerous. The GPS based navigation systems available in the art fails to identify the potholes on the roads.

[0005] In some of the situations because of the accidents on the road, the rescuers often need to manually place the road when coming to deal with the accident, however, because of the same traffic congestion is easy to cause, and inevitable troubles are caused for vehicles and pedestrians passing through the site within an accident influence range. The same may increase the rescuing time and will also delay the fellow user.

[0006] In light of the above, the problems available with the GPS based navigation systems available in the art is that the same does not consider the road conditions, speed breaker, potholes presence, roadblock, or the like obstacles. Further, the GPS based navigation systems available in the art does not generate a navigation path within the preferred route that can help the user manoeuvre the vehicle by missing the potholes, roadblocks, or the like and at the same time ensuring safety and avoid damage to the vehicle.

[0007] In light of the aforesaid problems available in the art there is a need to develop a navigation system to overcome the deficiency available in the art. Further, there is also a need for a system and method for determining sub-path in a navigational path for the vehicle.

[0008] The above information as disclosed in this background section is only for enhancement of understanding of the background of the disclosure and therefore it may contain information that does not form the prior art that is already known in this country to a person of ordinary skill in the art.

SUMMARY
[0009] It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

[00010] In one of the embodiments of the present application, a method for determining a sub-path in a navigational path for a vehicle comprising: receiving, by an application server, a plurality of parameters from one or more sensors of the vehicle. Establishing, by the application server, a correlation between the plurality of parameters using a joint distribution derived amongst the plurality of parameters using a D-vine copula. Identifying, by the application server, a plurality of candidate sub-path s for navigation within the navigation path based on the correlation. Selecting, by the application server, a sub-path from the plurality of candidate sub-paths using one or more machine learning techniques. Providing, by the application server, the selected sub-path to a user for navigating the vehicle.

[00011] In one of the embodiments of the present application, an enhanced view of the selected sub-path to the user for navigating the vehicle.

[00012] In one of the embodiments of the present application, providing navigation details of the selected sub-path to at least one controller of the vehicle. Further, the at least one controller of the vehicle is configured to control operation of at least turning indicators, tale lamp, hazard lamp, headlight of the vehicle.

[00013] In one of the embodiments of the present application, the machine learning techniques comprises at least one of reinforcement learning, deep learning, Bayesian optimization, graph-based learning, decision trees, support vector machines, or combination thereof.

[00014] In one of the embodiments of the present application, the plurality of parameters which are determined using the one or more sensors of the vehicle are length of the vehicle, ground clearance of the vehicle, length of the selected sub-path, traffic on the selected sub-path and on the navigational path, road conditions of the selected sub-path and the navigational path, elevation of the selected sub-path and the navigational path, congestion on the selected sub-path and on the navigational path, speed limitation of the selected sub-path and the navigational path and driving preferences of the user or combination thereof.

[00015] In one of the embodiments of the present application, the road conditions of the selected sub-path and the navigational path is determined using number of potholes, dimension of the potholes, depth of the potholes, number of speeds breaker, dimension of the speed breaker, length of the speed breakers, water or dust on the road or combination thereof.

[00016] In one of the embodiments of the present application, classifying, by the electronic device, the plurality of candidate sub-paths for navigation within the navigation path.

[00017] In one of the embodiments of the present application, labelling, by the electronic device, the plurality of candidate sub-paths for navigation within the navigation path.

[00018] In one of the embodiments of the present application, segmenting, by the electronic device, the plurality of candidate sub-paths for navigation within the navigation path.

[00019] In one of the embodiments of the present application, segmenting, by the electronic device, the selected sub-path using one or more machine learning techniques.

[00020] In one of the embodiments of the present application, the one or more sensors of the vehicle are Camera, Radar, Light Detection and Ranging (LiDAR), Ultrasonic sensors, Advanced Driver Assistance System (ADAS), Global Positioning System (GPS), Image sensor, or the combination thereof.

[00021] In one of the embodiments of the present application, estimating a conditional probability distribution, based on the joint distribution of each of the plurality of parameters, received from the one or more sensors of the vehicle.

[00022] In one of the embodiments of the present application, the reinforcement learning model is configured to learns to select the sub-path using a reward signal and a penalty signal based on feedback data received from the one or more sensors of the vehicle while navigating the selected sub-path.

[00023] In one of the embodiments of the present application, the reinforcement learning model takes the joint distribution generated by the D-vine copula as an input. Further, the reinforcement learning model is configured to estimate the probability of the plurality of parameters.

[00024] In one of the embodiments of the present application, the reward signal can be defined based on cost or reward functions. Further, the cost or reward functions is one of Distance-based cost function, Time-based reward function, Safety-based reward function, Fuel-efficiency based cost function, User-preference based cost or reward function.

[00025] In one of the embodiments of the present application, displaying, the selected sub-path to the user on a displaying module of the vehicle. Further, the displaying module of the vehicle is an instrumentation cluster, speedometer, multimedia system.

[00026] In one of the embodiments of the present application, displaying, the selected sub-path to the user on an electronic device of the user.

[00027] In one of the embodiments of the present application, the vehicle is an electric vehicle (EV), Internal Combustion (IC) engine-driven vehicle, a hybrid electric vehicle (HEV), an Autonomous Vehicle (AV). In one of the embodiments of the present application, the vehicle can be a two wheeled vehicle, a three wheeled vehicle, a four wheeled vehicle or the like.

[00028] In one of the embodiments of the present application, a system for determining at least one sub-path in a navigational path for a vehicle is disclosed. The system comprising a processor and a memory communicatively coupled to the processor. The memory stores processor instructions which on execution causes the processor to receive a plurality of parameters from one or more sensors of the vehicle. Further, establishing a correlation between the plurality of parameters using a joint distribution derived amongst the plurality of parameters using a D-vine copula. Furthermore, identifying a plurality of candidate sub paths for navigation within the navigation path based on the correlation. Moreover, selecting the at least one sub-path from the plurality of candidate sub paths using one or more machine learning techniques and providing the selected sub-path to a user for navigating the vehicle.

BRIEF DESCRIPTION OF FIGURES:
[00029] The accompanying drawings, which are incorporated herein and constitute part of this specification, illustrate preferred embodiments of the invention, and together with the general description given above and the detailed description given below, serve to explain features of the invention.

[00030] Figure 1 illustrates a system environment in which various embodiments of the method and the system may be implemented.

[00031] Figure 2 illustrates a system which is used to detect at least one sub-path in a navigational path for a vehicle.

[00032] Figure 3 illustrates a method which is used to detect at least one sub-path in a navigational path for a vehicle.

DETAILED DESCRIPTION
[00033] Exemplary embodiments detailing features of a battery pack in accordance with the present subject matter will be described hereunder with reference to the accompanying drawings. Various aspects of different embodiments of the present invention will become discernible from the following description set out hereunder. Rather, the following description provides a convenient illustration for implementing exemplary embodiments of the present subject matter. Further, it is to be understood that the phraseology and terminology used herein is for the purpose of description and should not be regarded as limiting. Additionally, all numerical terms, such as, but not limited to, “first”, “second”, “third”, “primary”, “secondary”, “main” or any other ordinary and/or numerical terms, should also be taken only as identifiers, to assist the reader's understanding of the various elements, embodiments, variations and/or modifications of the present disclosure, and may not create any limitations, particularly as to the order, or preference, of any element, embodiment, variation and/or modification relative to, or over, another element, embodiment, variation and/or modification.

[00034] The following detailed description refers to the accompanying drawings. Wherever possible, the same reference numbers are used in the drawings and the following description to refer to the same or similar elements. While embodiments may be described, modifications, adaptations, and other implementations are possible. For example, substitutions, additions, or modifications may be made to the elements illustrated in the drawings, and the methods described herein may be modified by substituting, reordering, or adding stages to the disclosed methods. Accordingly, the following detailed description does not limit the claimed subject matter. Instead, the proper scope of the claimed subject matter is defined by the appended claims. It should be noted that the description and figures merely illustrate principles of the present subject matter. Various arrangements may be devised that, although not explicitly described or shown herein, encompass the principles of the present subject matter. Moreover, all statements herein reciting principles, aspects, and examples of the present subject matter, as well as specific examples thereof, are intended to encompass equivalents thereof.

[00035] Further, various embodiments disclosed herein are to be taken in the illustrative and explanatory sense and should in no way be construed as limiting of the present disclosure. All joinder references (e.g., attached, affixed, coupled, disposed, etc.) are only used to aid the reader's understanding of the present disclosure, and may not create limitations, particularly as to the position, orientation, or use of the systems and/or methods disclosed herein. Therefore, joinder references, if any, are to be construed broadly. Moreover, such joinder references do not necessarily infer those two elements are directly connected to each other.

[00036] It will also be appreciated that one or more of the elements depicted in the drawings/figures can also be implemented in a more separated or integrated manner, or even removed or rendered as inoperable in certain cases, as is useful in accordance with a particular application. Additionally, any signal hatches in the drawings/figures should be considered only as exemplary, and not limiting, unless otherwise specifically specified.

[00037] The problems of potholes or other obstacles on the roads are generally common to all the countries and the process to maintain the roads is quite exhaustive and costly. The problem of pothole is a recurring problem which is creating inevitable damage to the surface of roads from traffic, construction, and the environment. The present invention is disclosing a system and method for determining at least one sub-path in a navigational path for a vehicle 104. The present invention is using various system such as but not limited to Advanced Driver Assistance System (ADAS) for example determining the curvature or gradient of a section of the road ahead in order to determine a suitable speed for traversing the section, and may then, for example, control the braking subsystems of the vehicle 104 in order to implement the determined speed.

[00038] The vehicle 104 may be an electric vehicle 104 (EV), Internal Combustion (IC) engine-driven vehicle 104, a hybrid electric vehicle 104 (HEV), an autonomous vehicle 104 or the like. In one of the embodiments of the present application, the vehicle can be a two wheeled vehicle, a three wheeled vehicle, a four wheeled vehicle or the like.

[00039] FIG. 1 is a block diagram that illustrates a system environment 100 in which various embodiments of the method and the system may be implemented.

[00040] The system environment 100 may include a server 108, a communication network 106, an application server 102, and a vehicle 104. The server 108 may be communicatively coupled to the vehicle 104, and the application server 102 via the communication network 106. In an embodiment, the server 108, the application server 102, and the vehicle 104 may communicate with each other via the communication network 106 application server 102.

[00041] The application server 102 may refer to a computing device used by a user. The application server 102 may be comprised of one or more processors and one or more memories. The one or more memories may include computer readable code that may be executable by the one or more processors to perform predetermined operations. Further, the application server 102 may be configured to present a user-interface to the user to provide the user input. Examples of the application server 102 may include, but are not limited to, a personal computer, a laptop, a personal digital assistant (PDA), a mobile device, a tablet, or any other computing device.

[00042] The application server 102 may be configured to receive user may receive inputs from the one or more sensors of the vehicle 104 to communicate with a server 108 using a secure protocol. In an embodiment, the communication may comprise exchange of messages using one or more secure protocol data packets for execution of one or more transactions. The application server 102 may be configured to authenticate the vehicle 104 based on the received credentials to create the authenticated session. The application server 102 may be configured to monitor one or more actions performed by the one or more sensors of the vehicle 104 during the authenticated session.

[00043] Figure 2 illustrates a system 200 which is used to detect at least one sub-path in a navigational path for the vehicle 104, in accordance with some embodiments of the present application. The system 200 comprises a processor 202, a memory 204, a transceiver 206, an input/output unit 208, a pre-processing unit 210, an object detection and classification unit 212, and a path planning unit 218. The processor 202 may be communicatively coupled to the memory 204, the transceiver 206, the input/output unit 208, the pre-processing unit 210, the object detection and classification unit 212, and the path planning unit 218. The navigational path of the vehicle 104, is the path identified by a navigation unit of the user or the vehicle 104, for directing vehicle 104 to move from one identified location to another identified location.

[00044] The processor 202 comprises suitable logic, circuitry, interfaces, and/or code that may be configured to execute a set of instructions stored in the memory 204. The processor 202 may be implemented based on a number of processor technologies known in the art. Examples of the processor 202 include, but not limited to, an X86-based processor, a Reduced Instruction Set Computing (RISC) processor, an Application-Specific integrated Circuit (ASIC) processor, a. Complex Instruction Set Computing (CISC) processor, and/or other processor.

[00045] The memory 204 comprises suitable logic, circuitry, interfaces, and/or code that may be configured to store the set of instructions, which may be executed by the processor 202. In an embodiment, the memory 204 may be configured to store one or more programs, routines, or scripts that may be executed in coordination with the processor 202. The memory 204 may be implemented based on a Random Access Memory (RAM), a Read-Only Memory (ROM), a Hard Disk Drive (HDD), a storage server, and/or a Secure Digital (SD) card.

[00046] The transceiver 206 comprises of suitable logic, circuitry, interfaces, and/or code that may be configured to transmit the secure protocol data packet comprising the encrypted linked data to the communication network 106. The transceiver 206 may be further configured to transmit the secret key and the encrypted linked data to the server 108. The transceiver 206 may be further configured to receive a public key from the server 108. The transceiver 206 is connected with the one or more sensors of the vehicle 104.

[00047] The Input/ Output (I/O) unit 208 comprises suitable logic, circuitry, interfaces, and/or code that may be configured to receive an input or transmit an output. The input/output unit 208 comprises of various input and output devices that are configured to communicate with the processor 202. Examples of the input devices include, but are not limited to, a key board, a mouse, a joystick, a touch screen, a. microphone, and/or a docking station, multimedia device of the vehicle 104. Examples of the output devices include, but are not limited to, a display screen and/or a speaker, electronic device, multimedia device of the vehicle 104.

[00048] The Pre-Processing Unit 210 or a comprises suitable logic, circuitry, interfaces, and/or code that may be configured to receive inputs from the one or more sensors of the vehicle 104 using the secure protocol. The pre-processing unit 210 may be configured to authenticate the location of the vehicle 104 based on the received input from one or more sensors of the vehicle 104. The pre-processing unit 210 also comprises suitable logic, circuitry, interfaces, and/or code that may be configured to pre-process inputs received from the one or more sensors of the vehicle 104 to filter noise and other disturbances from the input data.

[00049] The Object Detection and Classification Unit 212 comprises suitable logic, circuitry, interfaces, and/or code that may be configured to identify the objects in the navigation path of the vehicle 104 using the pre-processed data. Further, after identifying the objects using the pre-processed data, the object detection and classification unit 212 will classify the identified objects in the navigation path of the vehicle 104.

[00050] The Path Planning unit 216 comprises suitable logic, circuitry, interfaces, and/or code that may be configured to generate at least one sub-path after identifying plurality of candidate sub paths. In an embodiment, the one or more plurality of candidate sub paths may be identified based on the comparison of the data received from the object detection and classification unit 212 and one or more actions being performed by the path planning unit 216 with a plurality of historical actions and a plurality of sub-paths information saved with the server108.

[00051] Figure 3 illustrates a method 300 which is used to detect at least one sub-path in a navigational path for the vehicle 104, in accordance with some embodiments of the present application. More specifically, the method comprising steps of receiving, at step 302 using an application server 102, a plurality of parameters from one or more sensors of the vehicle 104. Further, establishing 304 a correlation between the plurality of parameters using a joint distribution method derived amongst the plurality of parameters using a D-vine copula by the application server 102. Furthermore, identifying 306 a plurality of candidate sub-paths for navigation within the navigation path based on the correlation by the application server 102. Moreover, selecting 308 the at least one sub-path from the plurality of candidate sub paths using one or more machine learning techniques and providing 310 the selected sub-path to a user for navigating the vehicle 104 using, by the application server 102.

[00052] The system is also capable of providing enhanced view of the selected sub-path to the user for navigating the vehicle 104 using the application server 102. Further, the system will also provide navigation details of the selected sub-path to at least one controller of the vehicle 104. Furthermore, the at least one controller of the vehicle 104 is configured to control operation of at least turning indicators, tale lamp, hazard lamp, headlight of the vehicle 104.

[00053] In one of the embodiments of the present application, the system will display the selected at least one sub-path on at least a displaying module of the vehicle 104 or an electronic device of the user. Further, an enhanced view of the selected at least one sub-path is displayed by performing a zooming operation on the at least one displaying module of the vehicle 104 or the electronic device of the user.

[00054] The machine learning techniques comprises at least one of reinforcement learning, deep learning, Bayesian optimization, graph-based learning, decision trees, support vector machines, or combination thereof.

[00055] The plurality of parameters which are considered for determining at least one sub-path in a navigational path for the vehicle 104 are length of the vehicle 104, ground clearance of the vehicle 104, length of the selected sub-path, traffic on the selected sub-path and on the navigational path, road conditions of the selected sub-path and of the navigational path, elevation of the selected sub-path and of the navigational path, traffic congestion on the selected sub-path and on the navigational path, speed limitation of the selected sub-path and of the navigational path; and driving preferences of the user, or the combination thereof.

[00056] The road conditions of the selected sub-path and the navigational path is determined using number of potholes, dimension of the potholes, depth of the potholes, number of speeds breaker, dimension of the speed breaker, length of the speed breakers, water or dust on the road or combination thereof. Further, the system will classify the plurality of candidate sub paths for navigation within the navigation path using the inputs received from the conditions of the selected sub-path and the navigational path. Furthermore, the system will label and segment the plurality of candidate sub paths for navigation within the navigation path based on the classified data received from the conditions of the selected sub-path and the navigational path.

[00057] The one or more sensors of the vehicle 104 are Camera, Infra-Red (IR) Camera, Radio Detection and Ranging (RADAR), Light Detection and Ranging (LiDAR), Ultrasonic sensors, Advanced Driver Assistance System (ADAS), Global Positioning System (GPS), Image sensor, Inertial measurement units (IMUs), Wheel speed sensors, or the combination thereof. The one or more sensors will enable the user to see the navigational path ahead of the vehicle 104 having potholes or other obstacles on the roads.

[00058] The system also estimates a conditional probability distribution, based on the joint distribution method of each of the plurality of parameters, received from the one or more sensors of the vehicle 104.

[00059] The reinforcement learning model is configured to learns to select the at least one sub-path using a reward signal and a penalty signal based on feedback data received from the one or more sensors of the vehicle 104 while navigating the vehicle 104.

[00060] The reinforcement learning model takes the joint distribution generated by the D-vine copula as an input. Further, the reinforcement learning model is configured to accurately select the at least one sub-path within the navigation path.

[00061] The reward signal can be defined based on cost or reward functions. Further, the cost or reward functions is one of Distance-based cost function, Time-based reward function, Safety-based reward function, Fuel-efficiency based cost function, User-preference based cost or reward function.

[00062] A system for determining at least one sub-path in a navigational path for a vehicle 104, the system comprising a processor and a memory communicatively coupled to the processor. The memory stores processor instructions, which, on execution, causes the processor to receive a plurality of parameters from one or more sensors of the vehicle 104. Further, establishing a correlation between the plurality of parameters using a joint distribution derived amongst the plurality of parameters using a D-vine copula. Furthermore, identifying a plurality of candidate sub paths for navigation within the navigation path based on the correlation. Moreover, selecting the at least one sub-path from the plurality of candidate sub paths using one or more machine learning techniques and providing the selected sub-path to a user for navigating the vehicle 104.

[00063] In one of the embodiments of the present application, the system further comprising displaying, the selected at least one sub-path on at least a displaying module of the vehicle 104 or an electronic device of the user. Further, an enhanced view of the selected at least one sub-path is displayed by performing a zooming operation on the at least one displaying module of the vehicle 104 or the electronic device of the user.

[00064] In one of the embodiments of the present application, the navigation details of the selected at least one sub-path to at least one controller of the vehicle 104. Further, the at least one controller of the vehicle 104 is configured to control operation of at least turning indicators, tail lamp, hazard lamp, headlight of the vehicle 104.

[00065] A D-vine copula model can be used to estimate the relationship between plurality of parameters received from the one or more sensors of a vehicle 104 and can be used in estimating the at least one sub-path in a navigational path for the vehicle 104. However, the D-vine copula models are statistical models and are used for modelling dependencies between multiple variables, and they do not provide a direct solution for finding the new sub-path. The D-vine copula model can only help in understanding how different parameters such as traffic, road conditions, and other factors are related and can be used to make predictions or generate simulations based on these relationships. Further, to actually estimate the sub-path in a navigational path for the vehicle 104 other methods such as optimization algorithms or machine learning models will be used in congestion with the D-vine copula model.

[00066] There are several machine learning models which are used to find a new sub-path, depending on the specific requirements of the problem. One approach is to use a Reinforcement Learning (RL) model. The RL model can learn to navigate the vehicle 104 through an environment by maximizing a reward signal. In the context of finding the at least one sub-path, the RL model could learn to navigate through different road conditions, traffic patterns, and other factors to find the shortest or fastest or safest sub-path towards the destination of the user.

[00067] The plurality of parameters which are determined using the one or more sensors of the vehicle 104 are length of the vehicle 104, ground clearance of the vehicle 104, length of the selected sub-path, traffic on the selected sub-path and on the navigational path, road conditions of the selected sub-path and the navigational path, elevation of the selected sub-path and the navigational path, congestion on the selected sub-path and on the navigational path, speed limitation of the selected sub-path and the navigational path and driving preferences of the user, or the like. Further, the input from the one or more sensors is also used to determine the environment around the vehicle 104.

[00068] Another approach which is used in the present application is a graph-based model, where the road network is represented as a graph, and the machine learning model can find the shortest path or fastest sub-path or safest sub-path through the graph based on different criteria such as time, distance, traffic, or the like. Examples of such models include Dijkstra's algorithm, A* algorithm, and variants of graph neural networks.

[00069] Finding the at least one sub-path is a complex problem that depends on many factors, and no single model can guarantee the optimal solution in all cases. It is often necessary to combine different techniques and models, as well as real-time data and user feedback, to find the best sub-path.

[00070] A combination of the Reinforcement Learning (RL) model and a graph-based model could be used to find the shortest or fastest or safest sub-path through a road network, while taking into account the real-time traffic conditions and road closures.

[00071] The RL model could learn to navigate through the environment by maximizing a reward signal based on the current state of the road network, while the graph-based model could provide a baseline path and take into account factors such as road conditions, elevation changes, and speed limits.

[00072] Further, other models such as but not limited to decision trees or support vector machines could be used to help identify the best sub-path based on specific criteria or constraints. The combination of these different models can provide a more comprehensive solution and improve the accuracy and efficiency of finding the at least one sub-path in the navigational path for the vehicle 104.

[00073] The parameters that are used for finding the sub-path in the navigational path for the vehicle 104 are Distance, Traffic conditions, Road conditions, Elevation changes, Speed limits, Road closures, Driver preferences, type of vehicle 104, length of vehicle 104, ground clearance of vehicle 104, traffic congestion, or the like. For example, for finding the at least one sub-path in the navigational path for the vehicle 104, the system may check the length of the sub-paths, which may be important for minimizing travel time or fuel consumption. The system may check the amount of traffic on different segments of the sub-paths, which can affect travel time and route efficiency. The system may check the condition of the road surface on the sub-paths, which can affect the speed at which the vehicle 104 can travel and the safety of the sub-paths. The system may check the changes in elevation along the sub-path, which can affect the speed and fuel efficiency of the vehicle 104. The system may check the posted speed limits along the sub-paths, which can affect the safety of the route and the likelihood of getting a ticket for speeding. The system may check the information on any closures or detours along the sub-paths, which can affect the optimal sub-paths. The system may check the user-defined preferences, such as avoiding highways, toll roads, or certain areas, which can affect the optimal sub-path. The system may check the information pertaining to the vehicle 104 which user is driving, information of vehicle 104 such as length of the vehicle 104, type of the vehicle 104, ground clearance of the vehicle 104, or the like. The system may check the traffic congestion on different segments of the sub-path, which can affect travel time and route efficiency.

[00074] The aforesaid parameters can be used to define a cost or reward function that a machine learning model can optimize, or to filter or rank alternative routes generated by an algorithm. In practice, the choice of parameters and their importance may vary depending on the context and user requirements. A cost or reward function can be used to evaluate different sub-paths and select the at least one sub-path that optimizes the objective of the problem.

[00075] Examples of cost and reward functions for finding a sub-path within a path are Distance-based cost function, Time-based reward function, Safety-based reward function, Fuel-efficiency based cost function and User-preference based cost or reward function.

[00076] In the Distance-based cost function, cost is equivalent to the distance travelled which could be used to minimize the total distance travelled between the start and end points of the sub-path. In the time-based reward function, reward is equivalent to 1/time travelled, which could be used to maximize the speed of travel through the sub-path, taking into account traffic conditions, speed limits, and other factors. In the safety-based reward function, reward is equivalent to “1 – risk factor” where risk factor could be calculated as a combination of factors such as road conditions, traffic, and accident rates. Further, safety-based reward function could be used to maximize the safety of the route, taking into account the likelihood of accidents or other hazards. In the fuel-efficiency based cost function, cost is equivalent to the fuel consumed, which could be used to minimize the fuel consumption of the vehicle 104 along the sub-path, taking into account factors such as road conditions, elevation changes, and speed limits. In the user-preference based cost or reward function Cost or Reward is equivalent to the user-defined weights on each parameter, which could be used to incorporate user-defined preferences into the selection of the sub-path, allowing the user to weigh the importance of different parameters based on their specific requirements.

[00077] A combined cost or reward function for finding a sub-path within a navigation path of the vehicle 104 could take into account multiple parameters and their relative importance. Here is an example of a possible combined function:

Cost/ Reward = W1 * Distance + W2 * Travel_time + W3 * Safety + W4 * Fuel_consumption + w5 * User_preference

Where:
• W1, W2, W3, W4, W5 are weights assigned to each parameter, reflecting their relative importance to the problem at hand. These weights can be user-defined or determined through optimization techniques;
• Distance is the length of the sub-path;
• Travel_time is the time taken to travel the sub-path, taking into account traffic conditions, speed limits, and other factors;
• Safety is a measure of the risk of accidents or hazards along the sub-path, taking into account road conditions, traffic, and other factors;
• Fuel_consumption is the amount of fuel consumed to travel the sub-path, taking into account road conditions, elevation changes, and speed limits; and
• User_preference is a measure of the user-defined preferences for specific routes or criteria.

[00078] This function can be used to evaluate alternative sub-paths and select the at least one optimal sub-path that will optimizes the overall objective, such as minimizing travel time, fuel consumption, or risk, or maximizing user satisfaction or safety. The specific weights and parameters used in the function can be adjusted based on the specific requirements of the problem and the context in which the sub-path is being found.

[00079] To identify the presence of potholes or other obstacles on the road and create at least one sub-path that avoids them while also considering vehicle 104-related parameters, the system will use a combination of data sources, sensors, and machine learning models. More specifically, the system will collect data from various sources, such as road maps, traffic data, weather reports, and images of roads. This can provide information on the location of roads, traffic conditions, weather, and road surface conditions. Further, the system can identify potholes or other obstacles using various technologies such as but not limited to satellite imagery, GIS mapping, and ground-based laser scanning. This can help to identify areas where potholes or other obstacles are present and track their location and size. The sensors that can detect road surface conditions, such as accelerometers, gyroscopes, or vibration sensors are already present in most of the vehicle 104 or the same can be easily implemented in the vehicle 104. These sensors can provide information on the roughness or unevenness of the road, which can be an indicator of the presence of potholes or other obstacles.

[00080] The Machine learning models can be used to analyse the data from the above sources and identify patterns and trends in the data. For example, the system could train a model to identify potholes or other obstacles based on the vibration or acceleration data collected by the one or more sensors of the vehicle 104. The system can also train a model to predict the likelihood of the potholes or other obstacles on a particular road segment based on factors such as weather, traffic, or road surface conditions.

[00081] Utilizing the data from the one or more sensors of the vehicle 104 and the machine learning models, the system can identify at least one sub-path in the navigational path for the vehicle 104 that can avoids potholes, irregular speed breakers, traffic congestion or the like from the navigational path for the vehicle 104 while also considering vehicle 104 related parameters. For example, the system could use the model to identify road segments with a high likelihood of potholes or other obstacles and plan a route that avoids those segments. The system could also consider vehicle 104 related parameters such as the suspension, tire pressure, and ground clearance of the vehicle 104 when planning the at least one sub-path, to ensure that the vehicle 104 can safely navigate through the sub-path.

[00082] The system could provide real-time updates to the user based on the data and machine learning models. For example, the system could alert the user to the presence of potholes or other obstacles and suggest at least one sub-path, routes that avoid potholes, tolls, based on the data collected by the one or more sensors of the vehicle 104 and the analysis performed by the machine learning models.

[00083] The aforesaid approach combines multiple sources of data and machine learning models to identify potholes or other obstacles and accordingly will identify at least one sub-path that avoids them while also considering vehicle 104 related parameters.

[00084] To identify potholes and to plan at least one sub-path that avoids them while considering vehicle 104 related parameters, the system can use a combination of machine learning models, depending on the data available and the specific requirements of the problem.

[00085] Classification model of the machine learning models could be used to identify potholes or other obstacles and to plan at least one sub-path. The classification model can be trained on labelled data to distinguish between road segments with potholes or other obstacles and those without the same. For example, the system could collect data from one or more sensors of the vehicle 104 that detect road surface conditions, such as accelerometers or vibration sensors, and label the data as "pothole" “irregular speed breakers” or "no pothole" or the like based on ground truth observations. Accordingly, the system could use this labelled data to train a classification model, such as a convolutional neural network, to identify potholes or other obstacles based on the sensors data. The output of this model can be used to plan at least one sub-path in the navigational path for the vehicle 104 that avoids road segments with potholes while considering vehicle 104 related parameters.

[00086] Regression model of the machine learning models could be used to identify potholes or other obstacles and to plan at least one sub-path. The regression model can be used to predict the likelihood of potholes or other obstacles on a given road segment based on factors such as traffic, weather, road surface conditions, or the like. For example, the system could collect historical data on road surface conditions, weather, traffic, and other relevant parameters, and use this data to train a regression model, such as a random forest or support vector regression, to predict the likelihood of potholes or other obstacles on a given road segment. The output of this model can be used to plan at least one sub-path in the navigational path for the vehicle 104 that avoids road segments with potholes while considering vehicle 104 related parameters.

[00087] Reinforcement learning model of the machine learning models could be used to identify potholes or other obstacles and to plan at least one sub-path. The reinforcement learning model can be used to learn an optimal policy for navigating a road network while avoiding potholes and considering vehicle 104-related parameters. For example, the system could use a deep reinforcement learning algorithm, such as a Deep Q-Network (DQN), to learn a policy for navigating a road network based on sensors data from the vehicle 104 and feedback on the effectiveness of the sub-path. The reinforcement learning model could be based on the safety of the sub-path, the time taken to reach the destination, and other relevant factors. The output of this model can be used to plan at least one sub-path in the navigational path for the vehicle 104 that avoids road segments with potholes or other obstacles.

[00088] Light Detection and Ranging (LiDAR), Radio Detection and Ranging (RADAR) sensors, Ultrasonic sensors, Image sensors, Night vision camera, Camera, or the like can be used to generate a detailed map of the road and its surroundings. The mentioned sensors can then be used to plan a sub-path that avoids potholes and other obstacles. LiDAR system use lasers to measure the distance to objects, while LiDAR sensors use radio waves. The mentioned sensors can provide information on the distance, angle, and velocity of objects in the environment, making them useful for generating a detailed map of the road and its surroundings.

[00089] In addition to LiDAR and LiDAR, other sensors that can be used to generate a sub-path include cameras which can be used to detect visual cues in the environment, such as lane markings and traffic signs, and to identify other vehicles and pedestrians. Global Positioning System (GPS), which can be used to determine the location of the vehicle 104 and to provide information on the road network and traffic conditions. Inertial measurement units (IMUs), which can be used to measure the acceleration, velocity, and orientation of the vehicle 104 and to provide information on the motion of the vehicle 104. Wheel speed sensors which can be used to measure the speed and direction of the wheels, which can be used to determine the motion of the vehicle 104. Proximity sensors, the proximity sensor present in the rear and front part of the vehicle 104 determines if some pedestrian or other vehicle 104 is present in the proximity of the vehicle 104. If there is any pedestrian or vehicle 104 present in the predefined range. Advanced Driver Assistance System (ADAS) which can utilize one or more sensors of the vehicle 104 to perceive the world around it, and then either provides information to the user or takes automatic action based on what it perceives.

[00090] In one of the embodiments of the present application, the one or more sensors comprising an Infra-Red (IR) camera. The IR camera is placed in the vicinity of the headlamp with a field of view as same as the headlamp. This night assist feature can be enabled through the display cluster. This system gives a real time live view of the path ahead, hence enabling the user to see the navigational path ahead. Further, the same will also determine potholes or other obstacles in the roadway while driving at higher speeds at night in the roadway with continuous opposing traffic with high beam ON.

[00091] In one of the embodiments of the present application, a display cluster or the instrumentation cluster placed on the front of the vehicle 104, used to display various parameters of the vehicle 104. A processing unit used to process the data sent by the one or more sensors of the vehicle 104 and display the captured view of the path ahead on the display cluster of the vehicle 104.

[00092] In one of the embodiments of the present invention, a lift indicator is placed over the vehicle 104 to inform pedestrian that the user is willing to give a lift. The lift indicator can be illuminated via lightning means such as LCD or LED or the like when the user is willing to give a lift. The aforesaid indicator may have a dedicated switch in the vehicle 104.

[00093] In one of the embodiments of the present invention, a “U” turn indicator is placed over the vehicle 104 to inform the fellow vehicle 104 that the user is going to take a “U” turn. Further, the “U” turn indicator can be illuminated via lightning means such as LCD or LED or the like. The aforesaid indicator may have a dedicated switch in the vehicle 104.

[00094] In one of the embodiments of the present invention, a single indicator is performing operation for a lift indicator as well as a “U” turn indicator.

[00095] The vehicle 104 comprising of a primary driver, a processing unit which is used to assist the user while driving in the night where the processing unit receives the data from the one or more sensors of the vehicle 104, processes the data and the displays the captured view of the road ahead, on the display cluster. The one or more sensors is used to capture the navigational path ahead of the vehicle 104 to identify potholes or other obstacles in the roadway. Since the one or more sensors can capture images even in the absence of light and camera is not affected by the flashing of the high beam of the opposite traffic, the images captured are very clear. The display cluster is used to display the navigational path ahead having to identify potholes or other obstacles.

[00096] The vehicle 104 with a primary driver and it associated parts comprising of one or more sensors which are used to capture the view of the navigational path ahead of the vehicle 104, a display cluster used to display the view of the path ahead of the vehicle 104 to the user, a processing unit to process the data received from the one or more sensors of the vehicle 104 and then display the captured view on the display unit. The inputs which are capture from the one or more sensors of the vehicle 104 will be sent to the processing unit. The processing unit process the data received from the one or more sensors of the vehicle 104 and then sends the processed data to the display unit where the captured view is displayed in real time.

[00097] In one of the embodiments of the present application, the camera will be connected to the instrumentation cluster of the vehicle 104. When the vehicle 104 will be in parking mode, the camera will be switched ON and the instrumentation cluster screen will split and show the rear and front view of the vehicle 104 according to the parking mode the vehicle 104 is in. Further, when the user receives the audio alert about some object being in proximity, if the user wants, the user can watch it on the cluster with the help of camera. The camera can also be switched ON when it receives a command from the user.

[00098] By combining information from the aforesaid one or more sensors, it is possible to generate a detailed map of the road and its surroundings and to identify the plurality of candidate sub paths for navigation within the navigation path based on the correlation a sub-path that avoids potholes and other obstacles while considering vehicle 104-related parameters. For example, LiDAR and RADAR sensors along with Ultrasonic sensors, Image sensors, IR camera, proximity sensor, can be used to detect potholes and other obstacles, while GPS and wheel speed sensors can be used to determine the location and speed of the vehicle 104. Cameras and IMUs can be used to detect other vehicles and pedestrians and to provide information on the motion of the vehicle 104. The output of this sensor fusion can then be used to plan at least one optimal sub-path that avoids obstacles and considers the capabilities of the vehicle 104.

[00099] An example of how the sensors mentioned above can be used in a system to plan at least one sub-path that avoids potholes and other obstacles, LiDAR and RADAR sensors along with Ultrasonic sensors, Image sensors scan the surrounding environment and generate a 3D map of the road and its surroundings. The data from the same sensors is combined with camera data to detect and classify objects in the environment, such as other vehicles, pedestrians, road signs or the like. The GPS. IMUs and wheel speed sensors provide information on the vehicle’s 104 location and speed, which is used to localize the vehicle 104 within the map. At least one controller of the vehicle 104 will analyse the sensor data and generates a plurality of candidate sub paths that avoids potholes and other obstacles while considering vehicle 104-related parameters, such as the vehicle’s 104 size and turning radius. Further, the plurality of candidate sub paths is sent to the at least one controller of the vehicle 104, which identify the at least one sub-path and adjusts the vehicle’s 104 trajectory to follow the sub-path. The at least one controller of the vehicle 104 is also configured to control operation of at least turning indicators, tale lamp, hazard lamp, headlight of the vehicle 104 which will convey information of the vehicle 104 to the adjacent vehicles. Furthermore, the current process is repeated in real-time to adapt the sub-path to changing road conditions, traffic, and other parameters. Accordingly, the system is able to plan at least one sub-path in the navigational path for the vehicle 104 that avoids road segments with potholes and other obstacles.

[000100] The aforesaid example is just a high-level overview, and the specifics of the implementation will depend on the system requirements and the specific sensors and algorithms used. However, this example illustrates how a combination of one or more sensors such as but not limited to LiDAR and RADAR sensors along with Ultrasonic sensors, Image sensors, cameras, IMUs, GPS, and wheel speed sensors can be used to generate a sub-path that avoids potholes and other obstacles while considering vehicle 104-related parameters.

[000101] Machine learning can be used to optimize the sub-path planning process in real-time by learning from the one or more sensors data and adjusting the sub-path based on the learned models.

[000102] Reinforcement learning model of the machine learning can be used to learn an optimal sub-path by training an agent to interact with the environment and receive feedback in the form of rewards or penalties. The agent can learn to avoid potholes or other obstacles by maximizing the reward signal and adjusting the sub-path in real-time based on the learned models.

[000103] Deep learning model of the machine learning can be used to learn a mapping between the one or more sensors data and the optimal sub-path. For example, a convolutional neural network (CNN) can be trained to classify obstacles in the environment, and a recurrent neural network (RNN) can be used to generate at least one sub-path that avoids those obstacles. The network can be updated in real-time based on the one or more sensors data to generate at least one optimal sub-path while considering vehicle 104-related parameters.

[000104] Bayesian optimization of the machine learning can be used to optimize the sub-path planning process by modelling the uncertainty in the one or more sensors data and adjusting the sub-path based on the learned models. This can be particularly useful when the one or more sensors data is noisy or incomplete, as it allows the system to make decisions based on the most likely models.

[000105] In one of the embodiments of the present application, for identifying at least one sub-path in a navigational path for the vehicle 104 in a real-time using Artificial Intelligence (AI) machine learning models and sensor inputs. The system takes in sensor inputs from one or more sensors of the vehicle 104, including LiDAR and RADAR sensors along with Ultrasonic sensors, Image sensors, cameras, IMUs, GPS, and wheel speed sensors. These sensors provide the system with information about the vehicle’s 104 environment, including the location of obstacles, road conditions, and the vehicle’s 104 position and speed. The sensor data is combined and fused to create a more comprehensive view of the vehicle’s 104 environment. This step helps to reduce noise and improve the accuracy of the one or more sensors data. The system uses AI machine learning models to detect and classify objects in the vehicle’s 104 environment, such as other vehicles, pedestrians, and road signs. This step provides the system with a more detailed understanding of the vehicle’s 104 environment and helps it to identify potential obstacles. The system uses AI machine learning models to plan at least one optimal sub-path based on the one or more sensors data and vehicle 104-related parameters, such as the vehicle’s 104 size and turning radius. The system considers the information from the previous steps to identify at least one sub-path that avoids obstacles and provides a smooth and safe ride. The sub-path generated by the AI machine learning models is fed to the at least one control system of the vehicle 104, which adjusts the vehicle’s 104 trajectory to follow the sub-path. The system repeats the above steps in real-time to adapt the sub-path to changing road conditions, traffic, and other parameters. Other sensors that can be used in this context include ultrasonic sensors, which can be used to detect nearby obstacles, and inertial measurement units (IMUs), which can be used to measure the vehicle’s 104 acceleration and orientation.

[000106] D-vine copula is a statistical method that can be used to model the joint distribution of multiple random variables, which can help in sub-path planning based on the above one or more sensors data. Further, D-vine copula can be used to model the joint distribution of sensor data, such as LiDAR and RADAR data, to capture their interdependence and generate a more accurate representation of the vehicle’s 104 environment. The D-vine copula can also be used to model the conditional probability distribution of a given parameter, such as road surface condition, given the other parameters, such as vehicle 104 speed, GPS location, and weather conditions. This can help in generating at least one optimal sub-path that takes into account the road surface conditions and adjusts the path accordingly.

[000107] In combination with other machine learning models, D-vine copula can be used to optimize the sub-path planning based on the one or more sensors data in real-time. For example, the joint distribution model generated by the D-vine copula can be used as an input to the path planning model, which can optimize the sub-path based on the probability of different road conditions, traffic patterns, and other parameters. Overall, the use of D-vine copula in sub-path planning can help to improve the accuracy and reliability of the system and provide a more comprehensive view of the vehicle’s 104 environment, leading to safer and more efficient driving.

[000108] D-vine copula can be used with reinforcement learning to optimize the at least one sub-path planning for a vehicle 104 in real-time. The joint distribution model generated by the D-vine copula can be used as an input to the reinforcement learning algorithm.

[000109] In reinforcement learning, the agent (in this case, the vehicle 104) learns to take actions (i.e., the at least one sub-path) based on the environment (i.e., one or more sensors data) to maximize a cumulative reward signal. The reward signal can be defined based on the cost and reward functions as discussed earlier, such as minimizing travel time and fuel consumption while avoiding potholes.

[000110] The reinforcement learning algorithm can take the joint distribution model generated by the D-vine copula as an input and use it to estimate the probability of different road conditions and other environmental factors. Based on this probability estimate, the reinforcement learning algorithm can learn to take actions (i.e., at least one sub-path) that are more likely to lead to a positive reward signal.

[000111] The D-vine copula can also be used to model the dependencies between different environmental factors and their effect on the reward signal, which can help the reinforcement learning algorithm to make more informed decisions.

[000112] Further, the combination of D-vine copula and reinforcement learning can help to optimize the sub-path planning in real-time, leading to safer and more efficient driving.

[000113] The method to identify the optimal sub-path within a path in real-time using AI machine learning models, sensor inputs, and D-vine copula can be described using following steps. More specifically, in the first step the system will collect the data from the one or more sensors of the vehicle 104 such as Lidar and Radar data, GPS location, vehicle 104 speed, and weather conditions. After that the data acquired from the one or more sensors will be pre-processed by filtering, normalizing, and smoothing the data to remove noise and anomalies. The D-vine copula to estimate the joint distribution of the sensor data, capturing the dependencies and interdependence between the variables. The estimated joint distribution is used to estimate the conditional probability distribution of road conditions, traffic data, and other parameters given by the one or more sensor data. The machine learning models, such as reinforcement learning, is used to generate candidate sub-paths based on the estimated probability distribution. Further, evaluating the candidate sub-paths based on the cost and reward functions, such as minimizing travel time, fuel consumption, and avoiding potholes or number of speed breaker, or the like. Selecting the at least one sub-path with the highest expected reward, taking into account the estimated probability distribution and the cost and reward functions. Updating the joint distribution with the one or more sensor data and use it to estimate the probability distribution for the next time step. Furthermore, repeating the aforesaid steps in real-time to continuously generate and update the optimal sub-path. Also displaying the same to user to navigate the vehicle 104 on the selected at least one sub-path. In one of the embodiments of the present application, enhance view of the selected at least one sub-path will be shown to the user on an instrumentation cluster of the vehicle 104 or on the one or more electronic devices of the user.

[000114] The above method uses D-vine copula to estimate the joint distribution of the sensor data, which helps to capture the dependencies between the variables and generate more accurate estimates of the probability distribution. The combination of machine learning models and the estimated probability distribution can be used to generate and update the optimal sub-path in real-time.

[000115] There are several advantages of using the present invention where D-vine copula and reinforcement learning are used for determining at least one sub-path in a navigational path for the vehicle 104. More specifically, D-vine copula can capture complex dependencies and interdependence between variables. Further, in sub-path planning as disclosed in the present application the D-vine copula can capture the relationships between different environmental factors, such as road conditions, traffic data, and weather conditions, and use these relationships to estimate the probability distribution more accurately. Further, using the D-vine copula as disclosed in the present application, the system can handle high-dimensional data, which is important for sub-path planning, where multiple environmental factors need to be considered.

[000116] The D-vine copula as used in the present system is non-parametric in nature, which means that it does not require a specific functional form to model the joint distribution. This allows for greater flexibility in modelling the distribution and can capture complex relationships between variables. Further, using the present invention, the reinforcement learning can learn from experience and adjust the sub-path based on the observed rewards and penalties. This can lead to better sub-path planning over time. Furthermore, in the present invention both D-vine copula and reinforcement learning are computationally efficient and can be applied to large datasets, making them suitable for real-time sub-path planning. Moreover, D-vine copula as disclosed in the present application is robust to outliers and noise in the data, which is important for sub-path planning where sensor data can be noisy. Overall, combining D-vine copula and reinforcement learning as disclosed in the present invention can lead to more accurate and efficient sub-path planning, which can improve safety for vehicle 104 as well as for the user and reduce travel time.

[000117] In one of the embodiments of the present application, the instrumentation cluster is touch based. The instrumentation cluster splits into two parts when the system will identify the at least one sub-path and show the frames sent by camera. In one of the embodiments of the present application, the user can also manually give the command to split the instrumentation cluster when the user want to see the identified sub-path. In one of the embodiments of the present application, a speaker will be connected to the instrumentation cluster of the vehicle 104.

[000118] In view of the above, the steps as discussed above are not routine, conventional, or well understood in the art, as the claimed steps enable the following solutions to the existing problems in conventional technologies.

[000119] The above-described embodiments, and particularly any “preferred” embodiments, are possible examples of implementations and merely set forth for a clear understanding of the principles of the invention. It will be apparent to those skilled in the art that changes in form, connection, and detail may be made therein without departing from the spirit and scope of the invention.

[000120] Non-limiting and non-exhaustive embodiments of the invention are described with reference to the following figures, wherein like reference numerals refer to like parts throughout the various views unless otherwise specified. It should be appreciated that the following figures may not be drawn to scale.

[000121] The foregoing disclosure is not intended to limit the present disclosure to the precise forms or particular fields of use disclosed. As such, it is contemplated that various alternate embodiments and/or modifications to the present disclosure, whether explicitly described or implied herein, are possible in light of the disclosure. Having thus described embodiments of the present disclosure, a person of ordinary skill in the art will recognize that changes may be made in form and detail without departing from the scope of the present disclosure. Therefore, it is intended that the present invention not to be limited to the particular embodiment disclosed, but that the present invention will include all embodiments falling within the scope of the appended claims.

[000122] In the foregoing specification, the disclosure has been described with reference to specific embodiments. However, as one skilled in the art will appreciate, various embodiments disclosed herein can be modified or otherwise implemented in various other ways without departing from scope of the disclosure. Accordingly, this description is to be considered as illustrative and is for the purpose of teaching those skilled in the art the manner of making and using various embodiments of the disclosure. It is to be understood that the forms of disclosure herein shown and described are to be taken as representative embodiments. Equivalent elements, materials, processes or steps may be substituted for those representatively illustrated and described herein. Moreover, certain features of the disclosure may be utilized independently of the use of other features, all as would be apparent to one skilled in the art after having the benefit of this description of the disclosure. Expressions such as “including”, “comprising”, “incorporating”, “consisting of”, “have”, “is” used to describe and claim the present disclosure are intended to be construed in a non-exclusive manner, namely allowing for items, components or elements not explicitly described also to be present. Reference to the singular is also to be construed to relate to the plural.
, Claims:We Claim:

1. A method for determining at least one sub-path in a navigational path for a vehicle (104), the method comprising:
receiving (302), by an application server (102), a plurality of parameters from one or more sensors of the vehicle (104);
establishing (304), by the application server (102), a correlation between the plurality of parameters using a joint distribution derived amongst the plurality of parameters using a D-vine copula;
identifying (306), by the application server (102), a plurality of candidate sub paths for navigation within the navigation path based on the correlation;
selecting (308), by the application server (102), the at least one sub-path from the plurality of candidate sub paths using one or more machine learning techniques; and
providing (310), by the application server (102), the selected at least one sub-path to a user for navigating the vehicle (104).

2. The method as claimed in claim 1, wherein the providing (310) includes displaying, the selected at least one sub-path on at least a displaying module of the vehicle (104) or an electronic device of the user, wherein an enhanced view of the selected at least one sub-path is displayed by performing a zooming operation on the at least one displaying module of the vehicle (104) or the electronic device of the user.

3. The method as claimed in claim 2, wherein providing (310) navigation details of the selected at least one sub-path to at least one controller of the vehicle (104) wherein the at least one controller of the vehicle (104) is configured to control operation of at least turning indicators, tail lamp, hazard lamp, headlight of the vehicle (104).

4. The method as claimed in claim 1, wherein the machine learning techniques comprises at least one of reinforcement learning model, deep learning, Bayesian optimization, graph-based learning, decision trees, support vector machines, or combination thereof.

5. The method as claimed in claim 1, wherein the plurality of parameters comprising:
a length of the vehicle (104);
a ground clearance of the vehicle (104);
a length of the selected sub-path;
traffic data on the selected sub-path and on the navigational path;
road conditions of the selected sub-path and of the navigational path;
elevation of the selected sub-path and of the navigational path;
speed limitation of the selected sub-path and of the navigational path; and
driving preferences of the user, or combination thereof.

6. The method as claimed in claim 5, wherein the road conditions of the selected sub-path and the navigational path is determined using a number of potholes, a dimension of the potholes, a depth of the potholes, a number of speeds breaker, a dimension of the speed breaker, a length of the speed breakers, water or dust accumulation on the road or combination thereof.

7. The method as claimed in claim 1, further comprising classifying, by the application server (102), the plurality of candidate sub paths for navigation within the navigation path labelling, by the application server (102),
wherein the plurality of candidate sub paths for navigation within the navigation path segmenting, by the application server (102), the plurality of candidate sub paths for navigation within the navigation path.

8. The method as claimed in claim 1, wherein the one or more sensors of the vehicle (104) are Camera, Infra-Red (IR) Camera, Radio Detection and Ranging (RADAR), Light Detection and Ranging (LiDAR), Ultrasonic sensors, Advanced Driver Assistance System (ADAS), Global Positioning System (GPS), Image sensor, Inertial measurement units (IMUs), Wheel speed sensors, or the combination thereof.

9. The method as claimed in claim 1, wherein the method further comprises estimating a conditional probability distribution, based on the joint distribution of each of the plurality of parameters, received from the one or more sensors of the vehicle (104).

10. The method as claimed in claim 4, wherein the reinforcement learning model is configured to select the sub-path using a reward signal and a penalty signal based on feedback data received from the one or more sensors of the vehicle (104) while navigating the selected at least one sub-path.

11. The method as claimed in claim 4, wherein the reinforcement learning model takes the joint distribution generated by the D-vine copula as an input, wherein the reinforcement learning model is configured to accurately select the at least one sub-path within the navigation path.

12. The method as claimed in claim 10, wherein the reward signal can be defined based on cost or reward functions, wherein the cost or reward functions is one of Distance-based cost function, Time-based reward function, Safety-based reward function, Fuel-efficiency based cost function, User-preference based cost or reward function.

13. A system for determining at least one sub-path in a navigational path for a vehicle (104), the system comprising:
a processor (202); and
a memory (204) communicatively coupled to the processor (202), wherein the memory (204) stores processor instructions, which, on execution, causes the processor to:
receive a plurality of parameters from one or more sensors of the vehicle (104);
establish a correlation between the plurality of parameters using a joint distribution derived amongst the plurality of parameters using a D-vine copula using a pre-processing unit (210);
identify a plurality of candidate sub paths for navigation within the navigation path based on the correlation using an object detection and classification unit (212);
select the at least one sub-path from the plurality of candidate sub paths using one or more machine learning techniques using a path-planning unit (214); and
provide the selected sub-path to a user for navigating the vehicle (104).

14. The system as claimed in claim 13 wherein the system further comprising displaying, the selected at least one sub-path on at least a input/output Unit (208) of the vehicle (104) or an electronic device of the user; wherein an enhanced view of the selected at least one sub-path is displayed by performing a zooming operation on the at least one displaying module of the vehicle (104) or the electronic device of the user.

15. The system as claimed in claim 13, wherein providing navigation details of the selected at least one sub-path to at least one controller of the vehicle (104), wherein the at least one controller of the vehicle (104) is configured to control operation of at least turning indicators, tail lamp, hazard lamp, headlight of the vehicle (104).

16. The system as claimed in claim 13, wherein the plurality of parameters comprising:
a length of the vehicle (104);
a ground clearance of the vehicle (104);
a length of the selected sub-path;
traffic data on the selected sub-path and on the navigational path;
road conditions of the selected sub-path and of the navigational path;
elevation of the selected sub-path and of the navigational path;
speed limitation of the selected sub-path and of the navigational path; and
driving preferences of the user, or combination thereof.

17. The system as claimed in claim 16, wherein the road conditions of the selected sub-path and the navigational path is determined using a number of potholes, a dimension of the potholes, a depth of the potholes, a number of speeds breaker, a dimension of the speed breaker, a length of the speed breakers, water or dust accumulation on the road or combination thereof.

18. The system as claimed in claim 14, wherein the one or more sensors of the vehicle (104) are Camera, Infra-Red (IR) Camera, Radio Detection and Ranging (RADAR), Light Detection and Ranging (LiDAR), Ultrasonic sensors, Advanced Driver Assistance System (ADAS), Global Positioning System (GPS), Image sensor, Inertial measurement units (IMUs), Wheel speed sensors, or the combination thereof.

19. The system as claimed in claim 13, wherein the vehicle (104) is an electric vehicle (104) (EV), Internal Combustion (IC) engine-driven vehicle (104), a hybrid electric vehicle (104) (HEV), an Autonomous Vehicle (104) (AV).

20. A vehicle (104) comprising a system as claimed in claims 13 to 19 for determining at least one sub-path in a navigational path for the vehicle (104).