Description:TECHNICAL FIELD
[0001] The disclosure pertains to the domain of freight and fleet management, focusing on advanced technological solutions that combine real-time vehicle tracking with driver monitoring and analytics to enhance efficiency, safety, and sustainability in transportation operations.
BACKGROUND
[0002] Freight and fleet management play an essential role in modern commerce and transportation. The global supply chain relies heavily on the effective coordination and management of freight, ensuring goods are moved from their point of origin to their destination in the most efficient manner. With the burgeoning e-commerce industry and increasing customer demands for expedited shipping, the stakes have never been higher for businesses to streamline their freight and logistics operations.
[0003] Traditionally, fleet management was mainly reactive in nature. Organizations would respond to vehicle breakdowns, accidents, and other emergencies without having any pre-emptive measures in place. Logistics managers largely depended on manual processes and traditional communication methods, such as phone calls and faxes, to coordinate deliveries and address problems. Such reactive approach often led to delays, increased operational costs, and a significant burden on resources. In addition, there were substantial risks associated with fleet operations, including the possibility for accidents due to driver fatigue or distraction.
[0004] Safety concerns have always been paramount in fleet management. With drivers often working long hours on the road, there is a high probability for accidents due to factors such as drowsiness, distraction, or impaired decision-making. Additionally, fleet vehicles navigating through varied terrains and weather conditions require constant monitoring to ensure they stay on their predetermined routes and avoid hazards. Previously, managers had limited oversight of drivers' real-time conditions, relying mostly on periodic check-ins or the occasional complaint from other road users.
[0005] Moreover, fuel efficiency and environmental concerns have also emerged as significant challenges in fleet management. With fluctuating fuel prices and increasing emphasis on sustainable operations, companies are looking for ways to minimize their environmental footprint while maintaining profitability. Maintaining profitability calls for the need to optimize routes, reduce idle times, and ensure that vehicles are maintained to run at their most efficient.
[0006] Introducing technology into freight and fleet management operations was seen as a game-changer. The advent of GPS technology enabled companies to track vehicles in real-time, providing managers with a bird's eye view of their entire fleet. Tracking vehicles helped reduce theft, ensure that drivers stayed on their routes, and improved delivery times by providing alternative routes during traffic or adverse conditions. However, while GPS technology addressed the "where" aspect of fleet management, the GPS technology did little to provide insights into the "how" – i.e., how vehicles were being driven, the state of the driver, and the conditions inside and outside the vehicle.
[0007] Telematics, a fusion of telecommunications and informatics, further revolutionized fleet management. Telematics systems could provide a wealth of data, including vehicle speed, brake usage, fuel consumption, and engine diagnostics. But even with such trove of data, a significant gap remained. While managers could determine where a vehicle was and gather some insights into its operation, they still lacked the ability to monitor the driver's behavior, the primary factor in ensuring safe and efficient fleet operations.
[0008] Additionally, with the rise of smart cities and the increasing integration of the Internet of Things (IoT) in urban infrastructure, there's a pressing need for freight and fleet management systems to seamlessly communicate with other devices and platforms. For instance, real-time data exchange with traffic management systems could provide insights into congestion, accidents, or road closures, allowing for dynamic rerouting and saving precious time and resources.
[0009] Another challenge that fleets operators grapple with is the training and onboarding of drivers. With the high turnover rate in the trucking industry, companies often find themselves spending significant amounts on training new drivers, only for them to leave shortly afterward. The aforesaid scenario emphasizes the need for systems that can not only monitor drivers but also provide real-time feedback, helping them improve their driving habits and aligning them with company safety and efficiency standards.
[0010] In conclusion, while advancements in technology have significantly improved certain aspects of freight and fleet management, several challenges remain. Addressing these challenges requires a holistic approach that combines real-time vehicle tracking with advanced driver monitoring and analytics capabilities.
SUMMARY
[0011] The aim of the present disclosure is to provide a freight and fleet management system and a method for enhancing safety in fleet operations using a freight and fleet management system to reshape the transportation and logistics sector by enhancing the safety, efficiency, and sustainability of fleet operations. The aim of the disclosure is achieved by the freight and fleet management system and the method for enhancing safety in fleet operations using the freight and fleet management system to reshape the transportation and logistics sector by enhancing the safety, efficiency, and sustainability of fleet operations.
[0012] The present disclosure details a freight and fleet management system aimed at enhancing safety during vehicular operations. The freight and fleet management system features a sensing unit with two image sensors: one inside the cabin to capture the image of a vehicle driver and another outside to monitor the road ahead. An onboard control device, connected to both sensors, analyzes the images. The onboard control device evaluates the consciousness of the vehicle driver and identifies the driving pattern of vehicle from the frontal view. Using such insights, a risk score is computed. If the score indicates danger, an audio alert is activated to warn the driver, ensuring timely intervention in risky scenarios. Such approach promotes safer and more efficient fleet operations.
[0013] In an embodiment, the onboard control device transmits an alert notification to a computing device associated to a fleet manager, based on the calculated risk score.
[0014] An embodiment, further comprises a location determination sensor to determine a current location of the vehicle and generate a location signal.
[0015] In an embodiment, the onboard control device acquires the generated location signal and transmit the acquired location signal to the computing device based on the determined consciousness status.
[0016] In an embodiment, the onboard control device computes a driving efficiency score based on the identified driving pattern.
[0017] In an embodiment, the onboard control device correlates the driving efficiency score with a historical driving data to provide insights into the performance of the vehicle driver over the time.
[0018] In an embodiment, the alert notification transmitted to the computing device includes both the calculated risk score and a timestamp based on the determined consciousness status and the identified driving pattern.
[0019] In an embodiment, the onboard control device includes machine learning techniques to continuously improve the accuracy of the consciousness status determination and driving pattern identification.
[0020] In an embodiment, the onboard control device archives detected risk scores and correlates the archived risk scores with external factors, such as weather conditions, time of day, or road type, to refine future risk assessments.
[0021] In an embodiment, the computing device send real-time feedback or instructions to the onboard control device, allowing instant corrective action or guidance to be relayed to the driver.
[0022] In an embodiment, the onboard control device transmits the captured image of the vehicle driver and the captured image of the frontal field of view, to the computing device.
[0023] In an embodiment, the location determination sensor integrates with real-time traffic data to assess the delays or hazards based on a current path and a projected path of the vehicle.
[0024] In an embodiment, the onboard control device uses facial recognition technology to distinguish between the multiple vehicle drivers and adapt the monitoring based on the individual driver profiles.
[0025] The present method enhances fleet safety using a freight and fleet management system. The method employs an in-cabin sensor to capture an image of the vehicle driver and an exterior sensor for capturing an image of the frontal view. An onboard device collects these images, assessing the consciousness of the vehicle driver and the driving pattern of vehicle from them. By combining the consciousness status with the driving pattern, a risk score is formulated. If the score indicates dangers, an audio alert is promptly initiated, ensuring timely interventions for risky driving scenarios.
BRIEF DESCRIPTION OF THE DRAWINGS
[0026] The summary above, as well as the following detailed description of illustrative embodiments, is better understood when read in conjunction with the appended drawings. For the purpose of illustrating the present disclosure, exemplary constructions of the disclosure are shown in the drawings. However, the present disclosure is not limited to specific methods and instrumentalities disclosed herein.
[0027] Embodiments of the present disclosure will now be described, by way of example only, with reference to the following diagrams.
[0028] FIG. 1 illustrates a freight and fleet management system, in accordance with various implementations of the present disclosure; and
[0029] FIG. 2 illustrates a method for enhancing safety in fleet operations using a freight and fleet management system, in accordance with an embodiment of the present disclosure.
DETAILED DESCRIPTION OF EMBODIMENTS
[0030] The following detailed description illustrates embodiments of the present disclosure and ways in which they can be implemented. Although some modes of carrying out the present disclosure have been disclosed, those skilled in the art would recognize that other embodiments for carrying out or practicing the present disclosure are also possible.
[0031] FIG. 1 illustrates a freight and fleet management system 100 (interchangeably referred as system 100), in accordance with an embodiment of the present disclosure. The system 100 comprises a sensing unit 102, an in-cabin image sensor 104, an exterior image sensor 106, an alert mechanism 108, an onboard control device 110 and other known components of a vehicle fleet management system/apparatus.
[0032] In one embodiment of the disclosed freight and fleet management system 100, the sensing unit 102 is provided, wherein the sensing unit 102 comprises an in-cabin image sensor 104 that is configured to capture an image or video stream of a vehicle driver during operation of the vehicle. The in-cabin image sensor 104 is positioned within the cabin of the vehicle to ensure a clear and unobstructed view of the driver.
[0033] In an embodiment, said in-cabin image sensor 104 continuously or intermittently capture images or video stream, enabling real-time monitoring of the behavior and facial features of the vehicle driver. The in-cabin image sensor 104 are specifically oriented in order to minimize glare and reflection from external light sources, ensuring that the captured images are of high quality and clarity. By doing so, accurate data pertaining to the facial expressions, eye movements, and other pertinent indicators of vehicle driver are obtained.
[0034] In an embodiment, the in-cabin image sensor 104 might be further coupled to additional components of the freight and fleet management system 100. Such coupling ensures seamless transmission of the captured images to other subsystems for further processing or analysis. Additionally, the construction and materials used for the in-cabin image sensor 104 are selected to withstand the typical environmental conditions encountered within a vehicle cabin, including temperature fluctuations and vibrations.
[0035] In certain embodiments, the integration of the in-cabin image sensor 104 provides an effective solution for real-time monitoring of the behavior of driver, attention level, tracking activities like road focus, distractions, etc. Such monitoring is critical for ensuring safe driving practices, early detection of driver fatigue, and providing timely interventions in scenarios where drowsiness is detected.
[0036] In another embodiment, the sensing unit 102 comprises an exterior image sensor 106 that is adapted to capture an image or video stream of a frontal field of view of the vehicle in which the system 100 is installed. Designed with precision optics and advanced imaging capabilities, the exterior image sensor 106 is tuned to offer high-resolution imaging, even under variable lighting conditions prevalent on roads.
[0037] In an embodiment, when the vehicle is in operation, the exterior image sensor 106 is passively activated to continuously monitor the environment in front of the vehicle. The continuous monitoring provides real-time visual data, ensuring timely and accurate capture of relevant information such as lane adherence, traffic situations, obstacles, etc. By virtue of specific positioning, the exterior image sensor 106 ensures a wide-angle capture, offering a view that spans across multiple lanes and includes both stationary and moving objects. Such extensive field of view serves as an essential data source for the fleet management system 100, offering insights into the driving environment that surrounds the vehicle.
[0038] In an embodiment, the construction of the exterior image sensor 106 is optimized to be resilient against external environmental factors. Being exposed to the external environment, the exterior image sensor 106 remains unaffected by conditions like rain, dust, or fluctuating temperatures. As a result, protective casings and coatings are applied, ensuring longevity and consistent performance. Additionally, the integration of advanced software algorithms ensures that the captured images are processed in a manner that reduces noise and enhances the clarity of the visual data.
[0039] In an embodiment, the freight and fleet management system 100 comprises the alert mechanism 108 that is specifically configured to produce an audio alert. When certain predetermined conditions are met, as determined by other components of the freight and fleet management system 100, the audio alert is generated. The audio alert serves the crucial function of notifying relevant entities or personnel of specified events or conditions. Coupled to other components of the system 100, the alert mechanism 108 provides instantaneous auditory warnings, which can be critical in scenarios requiring immediate attention or action. The design and integration of the alert mechanism 108 ensures seamless compatibility with the entirety of said freight and fleet management system 100. The precise nature, tone, or duration of the audio alert generated by said alert mechanism 108 can be tailored based on specific needs or preferences, allowing for a range of alerting scenarios. Furthermore, the audio alert produced by the alert mechanism 108 can be calibrated to ensure audibility under a variety of environmental conditions typically encountered by the freight and fleet management system 100.
[0040] In an embodiment, the alert mechanism 108 generates the audio alert directed towards the vehicle driver. The generation of audio alert is initiated upon monitoring of the attention level of vehicle driver. Integral functionalities of the system 100 enable the tracking of activities associated with the vehicle driver. Notably, the ability to ascertain road focus, distractions, and critical drowsiness detection is integrated within the purview of the system 100. Through continuous observation and analysis of the attentional parameters, effective response mechanisms are activated. In scenarios where deviations from optimal road focus are detected, the alert mechanism 108 is initiated. Similarly, any recognized distractions or drowsiness occurrences, as identified by the connected system 100 components, including but not limited to the onboard control device 110, trigger the audio alerts by the alert mechanism 108. Optimally, the onboard control device 110 can trigger an alert (e.g., SMS, email, push notification, voice call, voice mail, social media post etc.) to external computing devices (e.g., smartphone, computer, server etc.), which can be operated by user (e.g., fleet manager, owner, governmental agency etc.). The alert can comprise a current location, record video (from at least one from exterior image sensor 106 and in-cabin image sensor 102). Alternatively, the onboard control device 110 can store the recorded video locally or on external computing devices such as cloud server.
[0041] In an aspect, the onboard control device 110 is electrically connected to both the in-cabin image sensor 102 and the exterior image sensor 106. The onboard control device 110 is specifically configured to receive and process images. Upon deployment, the captured images of the vehicle driver are acquired by the onboard control device 110 from the in-cabin image sensor 102. Simultaneously, images representing the frontal field of view external to the vehicle are also acquired by the onboard control device 110 from the exterior image sensor 106. Through such configuration, a seamless integration of interior and exterior visual data is facilitated by said onboard control device 110, enabling an understanding of the state of vehicle driver and the external driving conditions. The structured interconnection of the onboard control device 110 with the sensing unit 102 ensures an optimized and synchronized acquisition process, laying the foundation for subsequent analysis and decision-making processes within the freight and fleet management system 100.

[0042] In an embodiment, the onboard control device 110 processes and scrutinizes the acquired images of the vehicle driver. Upon acquisition of the images, the onboard control device 110 is structured to undertake a rigorous analysis of the visual data. Through such analysis, the consciousness status of the vehicle driver is determined. Factors indicative of the consciousness status, such as eye movement, facial expressions, and other discernible visual cues, are evaluated by the onboard control device 110. By virtue of programming and advanced algorithms (such as artificial intelligence (AI), etc.), the onboard control device 110 systematically ascertains the alertness or fatigue levels exhibited by the vehicle driver based on the image data provided. The functionality and capabilities of the onboard control device 110 play an essential role in ensuring that the freight and fleet management system 100 operates efficiently and securely by continually monitoring the consciousness status of the vehicle driver, thus acting as an instrumental safeguard in the transportation operations.
[0043] In an embodiment, the onboard control device 110 analyzes the image acquired of the frontal field of view. Through such rigorous examination, various road parameters are discerned with precision. Included among the road parameters are lane adherence practices of the vehicle, prevailing traffic situations, and the identification of obstacles that might be present on the roadway. Such detailed analyses by the onboard control device 110 are instrumental in the determination of the driving pattern of vehicle. By working at the data extracted from the frontal field of view, the onboard control device 110 aids in capturing a picture of the interaction of vehicle with the associated environment, ensuring that any deviations or anomalies in driving patterns, relative to the observed road parameters, are identified promptly. Such functionality of such onboard control device 110 is critical in enhancing the overall safety and efficiency of the fleet management system 100.
[0044] In an embodiment, based on the consciousness status ascertained and the driving pattern identified, a risk score is computed by the onboard control device 110. The risk score, calculated by the onboard control device 110, serves as a quantitative representation of the hazards or inefficiencies that might be encountered during the operation of vehicle. Through the analysis of the attention level of vehicle driver and the driving pattern the onboard control device 110 derives the risk score. By incorporating such functionality, the system 100 ensures that the most relevant data points are utilized, thereby enabling a more precise evaluation of threats or operational inefficiencies. As such, the onboard control device 110 plays an essential role in the proactive management of risks within the freight and fleet management system 100, highlighting the significance in bolstering the safety and efficiency of transportation operations.
[0045] In an embodiment, the onboard control device 110 is configured and structured to take certain precautionary actions upon determination of specific conditions. When the risk score is calculated, the onboard control device 110 is tasked to activate the alert mechanism 108. such action is predicated on the computed risk score surpassing predefined thresholds. Thus, upon receiving data indicative of heightened risk levels associated with the operational status of the vehicle or the attentiveness of the vehicle driver, the onboard control device 110 is automatically provoked to trigger the alert mechanism 110. Such functionality of the onboard control device 110 is instrumental in ensuring that timely warnings are disseminated, facilitating rapid responsive measures. Moreover, the incorporation of such feature within the onboard control device 110 emphasizes the critical role in bolstering safety measures and preemptive risk mitigation within the overarching freight and fleet management system 100. The defined interplay between the calculated risk score and the subsequent activation of the alert mechanism 108 by the onboard control device 110 delineates a proactive approach to operational hazards.
[0046] In an embodiment, the onboard control device 110 may be configured to transmit an alert notification. Upon calculation of the risk score, if a predetermined threshold is exceeded, the alert notification is dispatched by the onboard control device 110. The alert notification is specifically directed to a computing device, which is notably associated with a fleet manager. The association between the computing device and the fleet manager serves as an essential link, ensuring that critical alerts are channeled to responsible parties capable of immediate intervention. The rationale behind such structured alert notification stems from the importance of rapid response in high-risk situations. In scenarios wherein the calculated risk score indicates danger or deviation from accepted operational parameters, the dispatch of the alert notification by the onboard control device 110 becomes instrumental in initiating swift corrective measures or interventions. By virtue of such features, fleet managers are apprised of real-time risks and are empowered to take necessary actions in response to the evolving on-ground situations.
[0047] In an embodiment, the freight and fleet management system 100 may comprise a location determination sensor to determine the current location of the vehicle. Once determined, a location signal is subsequently generated by the location determination sensor. The onboard control device 110, being operatively coupled to the location determination sensor, is designed to receive the generated location signal. The integration of location determination sensor into the freight and fleet management system 100 provides an enhanced capability, allowing for more precise vehicle tracking and monitoring in real-time. The inclusion augments the overall functionality of the freight and fleet management system 100 and offers an up-to-date spatial awareness, crucial for effective fleet management and oversight. The generated location signal, when received by the onboard control device 110, can further be processed or relayed to other system components or external entities as deemed necessary by the operational parameters of said freight and fleet management system 100.
[0048] In one embodiment, the onboard control device 110 may acquire the location signal that represents the current geographical position of the vehicle within the fleet. Furthermore, the onboard control device 110 may also be configured to analyze images to determine the consciousness status of the vehicle driver. Based on the determination of such consciousness status, the acquired location signal is selectively transmitted by the onboard control device 110. The computing device, which may be associated with a fleet management system/fleet manager, receives the transmitted location signal. The transmission ensures that real-time vehicle location information can be accessed and utilized, especially in scenarios where the consciousness status of the vehicle driver indicates concerns or risks. The onboard control device 110 ensures that timely transmission of crucial data occurs, thereby facilitating proactive interventions and real-time decision-making processes by the fleet management system/fleet manager.
[0049] In an embodiment, a driving efficiency score may be computed by the onboard control device 110. Upon acquisition and analysis of the driving pattern by the freight and fleet management system 100, the onboard control device 110 derives a metric, termed as the driving efficiency score that is calculated based on various parameters associated with the identified driving pattern. Factors contributing to the driving efficiency score may encompass parameters like lane adherence, speed consistency, braking patterns, and turning efficiencies, among others. As the system 100 detects and processes these driving behaviors, the resultant data is fed into the onboard control device 110. Machine learning techniques embedded within the onboard control device 110 are then employed to translate the data into the driving efficiency score. The driving efficiency score offers an objective measure of the driving performance, facilitating both real-time feedback and long-term analytics for fleet manager. The computation by the onboard control device 110 ensures a quantitative approach to assess the proficiency and safety of vehicle operations within the freight and fleet management system 100.
[0050] In an embodiment, the onboard control device 110 may be configured to correlate a driving efficiency score with historical driving data. Such correlation by the onboard control device 110 enables the system 100 to generate an analysis of the performance of the vehicle driver over an extended period. By combining the driving efficiency score with the historical driving data, deeper insights into the proficiency, consistency, and areas for improvement of vehicle driver are gleaned. Furthermore, the onboard control device 110 utilizes routines and databases to efficiently compare and analyze the present driving patterns against the archived data. The continuous assessment and correlation performed by the onboard control device 110 ensure that the fleet management system 100 remains updated on the evolving proficiency levels of the vehicle driver, thereby facilitating informed decisions regarding training and feedback. The system 100, through the onboard control device 110, thus offers a dynamic and robust mechanism to monitor, evaluate, and enhance the driving standards over time, ensuring the sustained quality of fleet operations. The below mentioned exemplary table. 1 depicts the performance insight of multiple vehicle drivers, based on the driving efficiency score and the historical driving data.
Sr. No Driver Driving Pattern Driving Efficiency Score Historical Driving Data (Previous Scores) Performance Insight
1 John Doe Aggressive 56/100 59, 60, 58 Decline in efficiency; aggressive driving pattern observed often
2 Jane Smith Cautious 89/100 87, 86, 88 Consistent high efficiency; maintains cautious driving
3 Richard Roe Erratic 67/100 70, 72, 68 Mild decline in efficiency; some erratic patterns observed
4 Emily Johnson Moderate 80/100 79, 80, 81 Stable efficiency; mostly moderate driving pattern
5 Michael Williams Overly cautious 75/100 78, 77, 76 Slight decline; overly cautious driving can impact efficiency

Table. 1
[0051] In an embodiment, the onboard control device 110 may be configured to transmit the alert notification to the computing device. The alert notification comprises calculated risk score and a timestamp, indicative of the specific moment the parameters (the determined consciousness status and the identified driving pattern) were recorded. The alert notification, as transmitted by the onboard control device 110 to the computing device, encompasses both the calculated risk score and the corresponding timestamp. The incorporation of the timestamp ensures a chronological context for the data, aiding in a precise understanding of when risks were detected within the operation of vehicle. Consequently, a timely analysis of safety hazards is facilitated. The combination of the risk score with specific timestamp provides fleet managers with the ability to discern the urgency and context of any vehicular or driver-related issues, ensuring a proactive response in maintaining safety standards and operational efficiency.
[0052] In an embodiment, the onboard control device 110 may comprise an advanced computational mechanism, integrated within said onboard control device 110, incorporates machine learning techniques. As data is acquired and processed, the aforesaid machine learning techniques (such as AI, etc.) are employed to refine and enhance the determinative processes of the system 100. Over time and with the accumulation of substantial data sets, the precision of the consciousness status determination of the vehicle driver is observed to be enhanced. Concurrently, the accuracy with which the driving pattern of the vehicle is identified also undergoes refinement. By utilizing the machine learning techniques, the onboard control device 110 may adaptively learn from the continuously acquired data. The continual learning process ensures that the efficiency of system 100 in identifying risks and irregularities in driving behavior is augmented over time. Thus, as more data is processed by the onboard control device 110, the reliability and accuracy of the consciousness status determination and driving pattern identification are incrementally improved, resulting in a progressively optimized performance of the freight and fleet management system 100.
[0053] In an embodiment, the onboard control device 110 may be configured with storage capabilities that allow for the archiving of detected risk scores. The archived risk scores, once stored within the onboard control device 110, are correlated with various external factors. Notably, factors such as prevailing weather conditions, the specific time of day, and the categorized type of road are considered by the onboard control device 110 during the correlation process. Such integrative process ensures that an understanding of the driving environment is incorporated into the risk analysis. Consequently, by correlating the archived risk scores with these external factors, the onboard control device 110 is enabled to refine and enhance subsequent risk assessments. The continuous refinement facilitated by the correlation ensures that the risk determination process remains adaptive and is continually optimized based on past and present data, leading to more accurate and timely risk evaluations by the onboard control device 110 in future fleet management operations.
[0054] In an embodiment, real-time feedback or instructions may be transmitted to the onboard control device 110 by the computing device. Upon receipt of the transmissions, corrective actions or guidance are enabled to be instantaneously relayed to the vehicle driver. By virtue of such configuration, immediate interventions and directions can be facilitated, enhancing the overall safety and operational efficiency of the fleet. Furthermore, any discrepancies or anomalies detected in the driving patterns or vehicle parameters are addressed promptly, ensuring the mitigation of risks. The direct communication between the computing device and said onboard control device 110 is designed to provide a seamless and uninterrupted exchange of crucial data, contributing to a proactive and responsive fleet management system 100. Through such mechanisms, the ability of the system 100 to adapt and respond to varying driving conditions and scenarios is considerably bolstered. The integration of the aforesaid feature underscores the commitment to optimizing fleet operations and prioritizing the well-being and safety of the vehicle drivers.
[0055] In an embodiment, the captured image of the vehicle driver and the captured image of the frontal field of view may be transmitted by the onboard control device 110. Such transmission is directed towards the computing device, ensuring that the computing device receives the relevant image data for further processing or analysis. Such transmission from the onboard control device 110 is facilitated in real-time or near-real-time, depending on system specifications and requirements. The integration and functionality of such onboard control device 110 are crucial for maintaining efficient communication between the sensing unit 102 and the associated computing device, ensuring timely and accurate data relay for the optimal functioning of the freight and fleet management system 100.
[0056] In an embodiment, the location determination sensor may be operatively integrated with real-time traffic data sources. As a result of such integration, delays or hazards on both a current path and a projected path of a vehicle can be assessed. When considering the paths, the real-time traffic data is processed in tandem with the location information derived from said location determination sensor. Subsequently, the assessed delays or hazards related to the movement of vehicle are conveyed to the onboard control device 110. In response, the onboard control device 110 can compute optimal alternative routes or necessary adjustments in the itinerary of vehicle to mitigate or altogether avoid identified impediments. Through such integration, the system 100 equips fleet operators with an enhanced ability to navigate the intricacies of real-time road conditions, thereby ensuring timely deliveries and reducing unforeseen operational challenges. The aforesaid embodiment, depicting real-time data, serves to enhance the overall efficiency and reliability of the freight and fleet management system 100.
[0057] In an embodiment, the onboard control device 110 may utilize facial recognition technology. Through the aforesaid technology, multiple vehicle drivers are distinguished by the onboard control device 110. Upon recognition of the facial features of a particular driver, the monitoring parameters are adapted and adjusted. Multiple driver profiles are stored within a memory component of the onboard control device 110. Each of the profiles contains specific monitoring preferences and thresholds tailored for that specific driver. When a driver enters the vehicle and is detected by the system 100, the facial features of the driver are captured and compared with the stored profiles in the memory component. Once a match is identified, the onboard control device 110 adjusts the monitoring parameters to align with the preferences and thresholds associated with the recognized profile of driver. Such a mechanism ensures that the freight and fleet management system 100 offers a personalized monitoring experience, catering to the specific requirements of each registered driver. The adaptability provided by the onboard control device 110, using facial recognition, enhances the efficiency and accuracy of the monitoring process.
[0058] The freight and fleet management system 100 offers an advancement in promoting road safety and fleet efficiency. Through the deployment of the sensing unit 102, which encompasses an in-cabin image sensor 104 for driver monitoring and an exterior image sensor 106 for real-time road condition analysis, the system 100 achieves oversight of both the internal and external driving environment. The onboard control device 110, equipped with routines, seamlessly processes the data to gauge the consciousness status of driver and analyze prevalent driving patterns. Notably, the system 100 computes a risk score, derived from the amalgamation of driver alertness and driving behavior, highlights the disclosure. Should the risk score cross a predetermined threshold, indicating danger, the alert mechanism 108 is promptly activated. Thus, the technical efficiency of the system 100 is two-fold: firstly, the system 100 offers real-time intervention during hazardous driving scenarios by issuing timely alerts, and secondly, the system 100 forms a foundation for a more proactive fleet management approach, wherein driver behavior and road conditions are continuously monitored and assessed, ensuring a safer, more efficient, and responsive fleet operation.
[0059] FIG. 2 illustrates a method 200 for enhancing safety in fleet operations using a freight and fleet management system, in accordance with an embodiment of the present disclosure. At step 202, an in-cabin image sensor is placed within the vehicle's cabin. The in-cabin image sensor is tasked with continuously capturing clear images or video stream of the vehicle driver, focusing especially on their facial features. At step 204, an exterior image sensor is mounted on a suitable part of the vehicle, commonly near the front. The exterior image sensor is designed to capture images that present a frontal view of the road and its surroundings. At step 206, the onboard control device connects to a sensing unit 102. The onboard control device fetches and stores both the image of the vehicle driver from the in-cabin sensor and the frontal view image from the exterior sensor. At step 208, using advanced image processing techniques, the onboard control device analyzes the in-cabin image. The objective is to ascertain the consciousness status of the driver, identifying signs of fatigue or distraction. At step 210, the image from the exterior sensor is analyzed to observe the vehicle's driving pattern. Factors considered include lane discipline, proximity to other vehicles, and adherence to traffic signals. At step 212, based on the consciousness status of the driver and the observed driving pattern, a risk score is determined. The risk score quantifies the danger level at any given moment. At step 214, if the calculated risk score crosses a predefined threshold, indicating a heightened risk, an alert mechanism is triggered. The alert mechanism generates an audio alert within the vehicle, prompting the driver to take corrective actions.
[0060] In an aspect, AI technique may be selected from any or a combination of machine learning mechanisms such as decision tree learning, Bayesian network, deep learning, random forest, supervised vector machines, reinforcement learning, prediction models, Statistical Algorithms, Classification, Logistic Regression, Support Vector Machines, Linear Discriminant Analysis, K-Nearest Neighbours, Decision Trees, Random Forests, Regression, Linear Regression, Support Vector Regression, Logistic Regression, Ridge Regression, Partial Least-Squares Regression, Non-Linear Regression, Clustering, Hierarchical Clustering – Agglomerative, Hierarchical Clustering – Divisive, K-Means Clustering, K-Nearest Neighbours Clustering, EM (Expectation Maximization) Clustering, Principal Components Analysis Clustering (PCA), Dimensionality Reduction, Non-Negative Matrix Factorization (NMF), Kernel PCA, Linear Discriminant Analysis (LDA), Generalized Discriminant Analysis (kernel trick again), Ensemble Algorithms, Deep Learning, Reinforcement Learning, AutoML (Bonus) and the like can be employed to learn sensor/hardware components.
[0061] The foregoing description of the specific embodiments will so fully reveal the general nature of the embodiments herein that others can, by applying current knowledge, readily modify and/or adapt for various applications such specific embodiments without departing from the generic concept, and, therefore, such adaptations and modifications should and are intended to be comprehended within the meaning and range of equivalents of the disclosed embodiments. It is to be understood that the phraseology or terminology employed herein is for the purpose of description and not of limitation. Therefore, while the embodiments herein have been described in terms of preferred embodiments, those skilled in the art will recognize that the embodiments herein can be practiced with modification within the spirit and scope of the embodiments as described herein.
[0062] It should be apparent to those skilled in the art that many more modifications besides those already described are possible without departing from the inventive concepts herein. The inventive subject matter, therefore, is not to be restricted except in the spirit of the appended claims. Moreover, in interpreting both the specification and the claims, all terms should be interpreted in the broadest possible manner consistent with the context. In particular, the terms “comprises” and “comprising” should be interpreted as referring to elements, components, or steps in a non-exclusive manner, indicating that the referenced elements, components, or steps may be present, or utilized, or combined with other elements, components, or steps that are not expressly referenced.

What is claimed is:
1. A freight and fleet management system, comprising:
a sensing unit that comprises:
an in-cabin image sensor configured to capture an image of a vehicle driver; and
an exterior image sensor positioned to capture an image of a frontal field of view;
an alert mechanism to generate an audio alert for the vehicle driver;
an onboard control device coupled to the in-cabin image sensor and the exterior image sensor, wherein the onboard control device is arranged to:
acquire the captured image of the vehicle driver and the captured image of the frontal field of view, from the sensing unit;
analyses the acquired image of the vehicle driver to determine a consciousness status of the vehicle driver;
identify a driving pattern of the vehicle by analysing the acquired image of the frontal field of view;
calculate a risk score based on the determined consciousness status and the identified driving pattern; and
activate the alert mechanism based on the calculated risk score.
2. The freight and fleet management system of claim 1, wherein the onboard control device transmits an alert notification to a computing device associated to a fleet manager, based on the calculated risk score.
3. The freight and fleet management system of claim 1, further comprises a location determination sensor to determine a current location of the vehicle and generate a location signal.
4. The freight and fleet management system of claim 3, wherein the onboard control device acquires the generated location signal and transmit the acquired location signal to the computing device based on the determined consciousness status.
5. The freight and fleet management system of claim 1, wherein the onboard control device computes a driving efficiency score based on the identified driving pattern.
6. The freight and fleet management system of claim 5, wherein the onboard control device correlates the driving efficiency score with a historical driving data to provide insights into the performance of the vehicle driver over the time.
7. The freight and fleet management system of claim 1, wherein the alert notification transmitted to the computing device includes both the calculated risk score and a timestamp based on the determined consciousness status and the identified driving pattern.
8. The freight and fleet management system of claim 1, wherein the onboard control device includes machine learning techniques to continuously improve the accuracy of the consciousness status determination and driving pattern identification.
9. The freight and fleet management system of claim 1, wherein the onboard control device archives detected risk scores and correlates the archived risk scores with external factors, such as weather conditions, time of day, or road type, to refine future risk assessments.
10. A method for enhancing safety in fleet operations using a freight and fleet management system, the method comprising the steps of:
deploying an in-cabin image sensor to capture an image of a vehicle driver;
positioning an exterior image sensor to capture an image of a frontal field of view;
acquiring, by an onboard control device, the captured image of the vehicle driver and the captured image of the frontal field of view from a sensing unit;
analysing the acquired image of the vehicle driver to determine a consciousness status of said vehicle driver;
identifying a driving pattern of the vehicle by analysing the acquired image of the frontal field of view;
calculating a risk score based on the determined consciousness status and the identified driving pattern; and
activating an alert mechanism to generate an audio alert based on the calculated risk score.

The present disclosure pertains to a freight and fleet management system designed for enhanced road safety through real-time monitoring. The system incorporates a sensing unit equipped with dual image sensors: an in-cabin sensor capturing imagery of the driver and an exterior sensor monitoring the frontal field of view. An onboard control device, connected to these sensors, meticulously processes the gathered images. By scrutinizing the image of driver, the consciousness status of the driver is determined. Simultaneously, the system discerns the driving pattern of vehicle from the frontal view. Integrating the analysis, a risk score is derived. Upon identifying hazards, as signified by the risk score, an audio alert is swiftly activated for the driver. Such an approach ensures immediate interventions during precarious driving scenarios, substantially enhancing safety in fleet operations.
Fig. 1 , Claims:What is claimed is:
1. A freight and fleet management system, comprising:
a sensing unit that comprises:
an in-cabin image sensor configured to capture an image of a vehicle driver; and
an exterior image sensor positioned to capture an image of a frontal field of view;
an alert mechanism to generate an audio alert for the vehicle driver;
an onboard control device coupled to the in-cabin image sensor and the exterior image sensor, wherein the onboard control device is arranged to:
acquire the captured image of the vehicle driver and the captured image of the frontal field of view, from the sensing unit;
analyses the acquired image of the vehicle driver to determine a consciousness status of the vehicle driver;
identify a driving pattern of the vehicle by analysing the acquired image of the frontal field of view;
calculate a risk score based on the determined consciousness status and the identified driving pattern; and
activate the alert mechanism based on the calculated risk score.
2. The freight and fleet management system of claim 1, wherein the onboard control device transmits an alert notification to a computing device associated to a fleet manager, based on the calculated risk score.
3. The freight and fleet management system of claim 1, further comprises a location determination sensor to determine a current location of the vehicle and generate a location signal.
4. The freight and fleet management system of claim 3, wherein the onboard control device acquires the generated location signal and transmit the acquired location signal to the computing device based on the determined consciousness status.
5. The freight and fleet management system of claim 1, wherein the onboard control device computes a driving efficiency score based on the identified driving pattern.
6. The freight and fleet management system of claim 5, wherein the onboard control device correlates the driving efficiency score with a historical driving data to provide insights into the performance of the vehicle driver over the time.
7. The freight and fleet management system of claim 1, wherein the alert notification transmitted to the computing device includes both the calculated risk score and a timestamp based on the determined consciousness status and the identified driving pattern.
8. The freight and fleet management system of claim 1, wherein the onboard control device includes machine learning techniques to continuously improve the accuracy of the consciousness status determination and driving pattern identification.
9. The freight and fleet management system of claim 1, wherein the onboard control device archives detected risk scores and correlates the archived risk scores with external factors, such as weather conditions, time of day, or road type, to refine future risk assessments.
10. A method for enhancing safety in fleet operations using a freight and fleet management system, the method comprising the steps of:
deploying an in-cabin image sensor to capture an image of a vehicle driver;
positioning an exterior image sensor to capture an image of a frontal field of view;
acquiring, by an onboard control device, the captured image of the vehicle driver and the captured image of the frontal field of view from a sensing unit;
analysing the acquired image of the vehicle driver to determine a consciousness status of said vehicle driver;
identifying a driving pattern of the vehicle by analysing the acquired image of the frontal field of view;
calculating a risk score based on the determined consciousness status and the identified driving pattern; and
activating an alert mechanism to generate an audio alert based on the calculated risk score.