Description:Complete Specification:
The following specification describes and ascertains the nature of this invention and the manner in which it is to be performed

Field of the invention

The present invention relates to a processor to assign a driver of a vehicle at least one skill-category and a method thereof.

Background of the invention
[0001] Besides the regulations, technology readiness and business-case attractiveness, the customer preference with respect to cab drivers in cab providing services may be influenced by the following namely, severe environment conditions like rain, snow, dusty, road conditions like hilly tracks, off-roads, traffic conditions like intense peaks, much slower or faster time frames, occupant's situations with physically disabled passengers, Pregnant women, infants on board, aged people etc.

[0002] Further, autonomous driving represents a huge opportunity to transform mobility. Road safety would increase, and drivers would have more time to relax in vehicles rather than focus on the road. In Future, for the Robo-taxis and Robo-Shuttles will be on-demand taxi services using autonomous vehicles without human drivers. Hence Effective profiling of professional Auto-Driver codes for various scenarios will need to be supplied.

[0003] Preferring the best cab-driver or for that matter, an auto-driver profile for the customer may be made available wherein auto-driver/driver codes and profiles may be adoptable for each situation/factor discussed above. The present invention relates building multiple driver-profiles that are reflective of the Driver’s behavior to a scenario such as driver reflexes, driver Maneuvering Skills etc. The driver’s skill in different weather / climate / traffic, the driver’s time to complete a trip and compliance to rules and regulations etc. may also be indicated through driver profiles.

[0004] Brief description of the accompanying drawings
[0005] An embodiment of the invention is described with reference to the following accompanying drawings:
[0006] Figure 1 depicts a processor to assign a driver of a vehicle at least one skill-category.
[0007] Figure 2 depicts a flowchart for a method to assign a driver of a vehicle at least one skill-category.

[0008] Detailed description of the drawings:

[0009] The present invention will now be described by way of example, with reference to accompanying drawings. Throughout all the figures, same or corresponding elements may generally be indicated by same reference numerals. These depicted embodiments are to be understood as illustrative of the invention and not as limiting in any way. It should also be understood that the figures are not necessarily to scale and that the embodiments are sometimes illustrated by graphic symbols, phantom lines, diagrammatic representations, and fragmentary views. In predetermined instances, details which are not necessary for an understanding of the present invention, or which render other details difficult to perceive may have been omitted.

[0010] Referring to Figure 1, disclosed is a processor (1) to assign a driver of a vehicle (2) at least one skill category (6). In accordance with an embodiment of the present invention, the processor (1) maybe provided with necessary signal detection, acquisition, and processing circuits. The processor (1) may be a component of a greater device/system or the processor (1) on its own may comprise input interface, output interfaces having pins or ports, the memory element (not shown) such as Random Access Memory (RAM) and/or Read Only Memory (ROM), Analog-to-Digital Converter (ADC) and a Digital-to-Analog Convertor (DAC), clocks, timers. Said processor (1) is capable of implementing machine learning model. The processor (1) may as an independent component or as a part of a greater system comprising communication units such as transceivers to communicate through wireless or wired means such as Global System for Mobile Communications (GSM), 3G, 4G, 5G, Wi-Fi, Bluetooth, Ethernet, serial networks, and the like. The processor (1) is implementable in the form of System-in-Package (SiP) or System-on-Chip (SOC) or any other known types. The processor (1) is in communication with plurality of sensors, said sensors communicating with the processor (1) through a communication bus or any other known in-vehicle communication system.

[0011] The output from the processor (1) may be displayed on a display or sent through the bus which can be read by other devices. Further, the processor (1) may also be deployed as an Application programming interface (API) in cloud which takes the selected parameters as input through a telematic device connected in the vehicle and provides the at least one skill category (6) to the driver .

[0012] Alternatively, the processor (1) may be deployed as an edge use case operating from a control unit in the vehicle instead of from cloud which based on skills of a known driver maneuvering a vehicle (2) with known vehicle and road parameters, provides a driver skillset.

[0013] The processor (1) is configured to receive a set of vehicle parameters (3)from a steering system of the vehicle, said vehicle maneuvered by the driver for a time t. According to the present invention, the vehicle parameters may be received through a steering system of the vehicle. These vehicle parameters may include steering wheel positions and steering torques requested while maneuvering the vehicle. These vehicle parameters may be received through plurality of external sensors and internal sensors of the vehicle. These sensors (external/internal) may be in direct or wireless connection with the processor (1) . Said sensors maybe used for object detection, path prediction, environment scanning, collision assessment, passenger and/or load position assessment. For instance, these plurality of external sensors may be to radar, lidar, optical sensors, ultrasonic sensors, active and passive infrared sensors, radio frequency (RF) sensors, camera sensors, etc. The internal sensors may include various vehicle system sensors including brake sensors, a throttle sensor, a suspension sensor, tire pressure sensors, vehicle inertial sensor(s), a wheel speed sensor, a vehicle (2) speed sensor, a seat belt sensor, temperature sensors, accelerometers, a steering angle sensor, etc.

[0014] The above sensors(internal/external) may be used individually or in conjunction with each other. The vehicle inertial sensor(s), the vehicle speed sensor, and the steering wheel angle sensor, vibration sensor may be used in coordination to generate a signal or signals indicative of vehicle path data or vehicle trajectory data, such as traveling on or approaching a curved road. The inertial sensor(s) may allow the processor (1) to determine vehicle parameters such as yaw of the vehicle, roll rate and pitch rate of the vehicle, center of gravity of the vehicle. sensors, etc.

[0015] The processor (1) receives a set of road parameters (4)from a global position system (GPS) and the steering system of the vehicle for the time t. The road parameters may be obtained by global position system (GPS) integrated within the vehicle. This road information may include vehicle location data , weather data, and vehicle operational data from other vehicles in the vicinity of the host vehicle. Further, road parameters may also be obtained from a steering rack actuator unit of the steering system.

[0016] Said processor (1) comprises an assignment means (5) to assign the driver the at least one skill category (6) based on said received set of vehicle parameters (3)and road parameters. The at least one skill category (6) may comprise any one of an experienced driver, a reflex skill, a terrain-expert, a bad driver and a safe driver. It is to be understood that the skill categories can be customized and categorized further into various categories. The list of such categories is non exhaustive therefore the at least one skill category (6) is not to be construed as limiting the scope of the invention.

[0017] Said assignment means (5) is trained to assign the driver the at least skill-category based on a known-set of vehicle parameters (3) and a known-set of road parameters. Said assignment means (5) is trained to assign the driver the at least one skill category (6) by using an ensemble learning technique. Said known set of vehicle and road parameters (3, 4) are received from at least one known vehicle maneuvered by at least one known-driver. The at least one known driver is assigned at least one known skill-category.

[0018] The assignment means (5) may be a Machine learning (ML) trained using different models of known vehicles driven by known drivers having known skill categories. The ML model may be a Machine learning model based on Extra tree classifier. Extra-Trees is a known ensemble machine learning approach. Ensemble methods are techniques that aim at improving the accuracy of results in models by combining multiple models instead of using a single model. The combined models increase the accuracy of the results significantly. Under the extra tree classification numerous decision trees are trained and the results from the group of decision trees are aggregated to output a prediction.

[0019] An implementation of the present invention is described further. A set of known-drivers may be pre-labeled as an experienced driver, a reflex skill, a terrain-expert, a safe driver and a bad-driver. The vehicle is then maneuvered by the known drivers along a known route. Therefore, a classification model is built based on the vehicle and road parameters (3, 4) and the effect of said vehicle and road parameters (3, 4) on the known driver of the vehicle.

[0020] In an example, these selected vehicle parameters while vehicle is being maneuvered, may be steering torque, steepness of a turn, speed of the vehicle when the vehicle is turning and jerks /vibrations. Similarly, selected road parameters may be road bumps, wet road, sharp turn etc. It is to be understood that the above vehicle and road parameters (3, 4) are only exemplary and not to be construed as limiting the scope of this invention.

[0021] The significant vehicle parameters and road parameters maybe selected by using various feature selection techniques where selected variable (parameter) has a correlation to the driver’s behavior. It is to be noted that any vehicle/road parameter correlated to the driver’s behavior may be selected and this is not to be taken as limiting the scope of the present disclosure. Once the assignment means (5) in trained, for every new driver driving a vehicle (2), a skill category may be assigned using the trained classification model.

[0022] Depicted in Figure 2 is a flow chart for the method to assign a driver of a vehicle (2) at least one skill category (6). The method may be implemented by the processor (1) described in figure 1. The method (100) comprises several step. The first step (101) is receiving by a processor (1) , a set of vehicle parameters (3)from a steering system of the vehicle, said vehicle maneuvered by the driver for a time t. This is followed by step (102) of receiving, by a processor (1) , a set of road parameters (4)from a global position system (GPS) and the steering system of the vehicle for the time t. The characteristic step (103) is assigning, by an assignment means (5) , at least one skill category (6) to the driver based on said received set of vehicle parameters (3)and road parameters. The assignment means (5) is trained to assign the driver at least skill-category based on a known-set of vehicle parameters (3)and a known-set of road parameters, said known set of vehicle and road parameters (3, 4)received from at least one known vehicle maneuvered by at least one known-driver. Said assignment means (5) is trained to assign the driver the at least one skill category (6) by using a on an ensemble learning technique.
, Claims:We Claim:
1. A processor (1) to assign a driver of a vehicle (2) at least one skill category (6), the processor (1) configured to:
-receive a set of vehicle parameters (3) from a steering system of the vehicle, said vehicle maneuvered by the driver for a time t,
-receive a set of road parameters (4) from a global position system (GPS) and the steering system of the vehicle for the time t,
characterized in that, said processor (1) comprises :
-an assignment means (5) to assign the driver the at least one skill category (6) based on said received set of vehicle parameters (3)and road parameters.

2. The processor (1) as claimed in Claim 1, wherein, said assignment means (5) is trained to assign the driver the at least skill-category based on a known-set of vehicle parameters (3)and a known-set of road parameters,
said known set of vehicle and road parameters (3, 4) received from at least one known vehicle maneuvered by at least one known-driver.

3. The processor (1) as claimed in Claim 2, wherein, the at least one known driver is assigned at least one known skill-category.

4. The processor (1) as claimed in claim 1, wherein said assignment means (5) is trained to assign the driver the at least one skill category (6) by using an ensemble learning technique.

5. A method (100) to assign a driver of a vehicle (2) at least one skill category (6) by a the processor (1) , the method comprising the steps of:
-receiving by a processor (1) , a set of vehicle parameters (3)from a steering system of the vehicle, said vehicle maneuvered by the driver for a time t (101),
-receiving, by a processor (1) , a set of road parameters (4)from a global position system (GPS) and the steering system of the vehicle for the time t (102),
characterized in that method:
- assigning, by an assignment means (5) , at least one skill category (6) to the driver based on said received set of vehicle parameters (3)and road parameters (103).