Improper behavior detection and intervention

Abstract

A system within a traffic vehicle for monitoring inappropriate behavior of adjacent traffic vehicles and initiating intervention includes a plurality of onboard traffic vehicle sensors in communication with a system controller adapted to identify at least one adjacent traffic vehicle, mark the at least one adjacent traffic vehicle with a unique identifier, and transmit the identified at least one adjacent traffic vehicle to the system controller. A driving mode of at least one adjacent traffic vehicle is monitored using a plurality of onboard sensors, the at least one adjacent traffic vehicle is classified, and an intervention action is initiated.

Description

Technical Field

[0001] The present disclosure relates to a system and method for monitoring the behavior of neighboring traffic vehicles and initiating intervention actions based on such behavior. Background Art

[0002] Traffic vehicles are equipped with many sensors that monitor their surroundings and issue warnings when objects are approaching, etc. However, current systems are limited in that they only issue alerts or take action when they detect an imminent risk of collision. Traffic vehicle drivers may be influenced by inappropriate behavior of other traffic vehicles that would not trigger current systems.

[0003] Therefore, while current systems and methods achieve their intended purposes, there is still a need for a new and improved system and method for detecting inappropriate behavior, such as aggressive or stalking behavior, in neighboring vehicles and initiating intervention actions based on the type and severity of the inappropriate behavior and the preferences of the occupants. Summary of the invention

[0004] According to several aspects of the present disclosure, a method for a traffic vehicle to monitor improper behavior of neighboring traffic vehicles and initiate intervention includes: identifying at least one neighboring traffic vehicle by multiple onboard traffic vehicle sensors that communicate with a system controller; marking at least one neighboring traffic vehicle with a unique identifier by the system controller; monitoring the driving mode of at least one neighboring traffic vehicle by multiple onboard sensors that communicate with the system controller; classifying at least one neighboring traffic vehicle by the system controller; and initiating an intervention action by the system controller.

[0005] According to another aspect, the driving mode of monitoring at least one adjacent vehicle by multiple onboard sensors that communicate with the system controller also includes using multiple onboard sensors to monitor: the relative distance of at least one adjacent vehicle; the relative position of at least one adjacent vehicle; the relative speed of at least one adjacent vehicle; and the heading of at least one adjacent vehicle.

[0006] According to another aspect, monitoring the driving pattern of at least one adjacent vehicle by a plurality of onboard sensors in communication with a system controller further comprises: periodically fusing, by the system controller, data from the plurality of onboard sensors; and constructing, by the system controller, a time series of data points.

[0007] According to another aspect, the classification of at least one adjacent traffic vehicle by the system controller also includes: the system controller identifying the behavior pattern of at least one adjacent traffic vehicle; and, by a machine learning algorithm within the system controller, classifying the behavior pattern of at least one adjacent traffic vehicle as one of normal behavior, aggressive behavior, and tracking behavior based on probability.

[0008] According to another aspect, the machine learning algorithm within the system controller classifies the behavior pattern of at least one adjacent traffic vehicle as one of normal behavior, aggressive behavior and tracking behavior based on probability, and also includes: when the behavior pattern of at least one adjacent traffic vehicle is classified as one of aggressive behavior or tracking behavior based on probability, the system controller calculates the severity of the behavior pattern.

[0009] According to another aspect, when the severity of the behavior pattern exceeds a first predetermined threshold, initiating an intervention action by the system controller further comprises: initiating a passive intervention action by the system controller.

[0010] According to another aspect, the passive intervention action initiated by the system controller also includes at least one of the following: notifying occupants in the vehicle via a vehicle human-machine interface (HMI) that communicates with the system controller that at least one adjacent vehicle has been identified by the system controller as having one of aggressive behavior or tracking behavior; acquiring an image of at least one adjacent vehicle and an image of the license plate of at least one adjacent vehicle by multiple onboard sensors; acquiring an image of the driver of the adjacent vehicle by multiple onboard sensors; collecting attributes of at least one adjacent vehicle and attributes of the driver of at least one adjacent vehicle by multiple onboard sensors; locking the door of the vehicle; and closing the window of the vehicle.

[0011] According to another aspect, when the severity of the behavior pattern exceeds a second predetermined threshold, initiating an intervention action by the system controller further includes: initiating an active intervention action by the system controller.

[0012] According to another aspect, the active intervention action initiated by the system controller also includes at least one of the following: the system controller issuing an alert to emergency services via the wireless communication module; the system controller issuing an alert to an emergency contact via the wireless communication module; the system controller providing suggested navigation actions via the HMI; and, the traffic vehicle control module that communicates with the system controller autonomously performing navigation actions.

[0013] According to another aspect, the method further includes: receiving, by the system controller via the HMI, preferences of an occupant in the transportation vehicle related to the first predetermined threshold and the second predetermined threshold; and setting the first predetermined threshold and the second predetermined threshold based on the occupant's preferences.

[0014] According to several aspects of the present disclosure, a system in a traffic vehicle for monitoring improper behavior of neighboring traffic vehicles and initiating intervention includes: a plurality of onboard traffic vehicle sensors in communication with a system controller. The system controller is adapted to identify at least one neighboring traffic vehicle, mark at least one neighboring traffic vehicle with a unique identifier, monitor the driving mode of at least one neighboring traffic vehicle using a plurality of onboard sensors, classify at least one neighboring traffic vehicle, and initiate intervention actions.

[0015] According to another aspect, when a plurality of onboard sensors are used to monitor the driving mode of at least one adjacent vehicle, the system controller is further adapted to use a plurality of onboard sensors to monitor the relative distance of at least one adjacent vehicle, the relative position of at least one adjacent vehicle, the relative speed of at least one adjacent vehicle, and the forward direction of at least one adjacent vehicle.

[0016] According to another aspect, when a plurality of onboard sensors are used to monitor the driving pattern of at least one adjacent traffic vehicle, the system controller is further adapted to periodically fuse data from the plurality of onboard sensors and construct a time series of data points.

[0017] According to another aspect, when classifying at least one adjacent vehicle, the system controller is also suitable for identifying a behavior pattern of at least one adjacent vehicle; and, using a machine learning algorithm within the system controller, classifying the behavior pattern of at least one adjacent vehicle into one of normal behavior, aggressive behavior, and tracking behavior based on probability.

[0018] According to another aspect, when the behavior pattern of at least one neighboring traffic vehicle is classified according to probability and when the behavior pattern of at least one neighboring traffic vehicle is classified according to probability as one of aggressive behavior or tracking behavior, the system controller is further adapted to calculate the severity of the behavior pattern.

[0019] According to another aspect, the system controller is further adapted to initiate a passive intervention action when the severity of the behavior pattern exceeds a first predetermined threshold, wherein the first predetermined threshold is set based on preferences received from an occupant in the transportation vehicle via a transportation vehicle human-machine interface (HMI) that communicates with the system controller.

[0020] According to another aspect, when a passive intervention action is initiated, the system controller is further adapted to perform at least one of the following actions: notifying occupants in the vehicle via a vehicle human-machine interface (HMI) that communicates with the system controller that at least one adjacent vehicle has been identified by the system controller as having one of aggressive behavior or tracking behavior; acquiring an image of at least one adjacent vehicle, an image of a license plate of at least one adjacent vehicle, and an image of a driver of the adjacent vehicle using multiple onboard sensors; collecting attributes of at least one adjacent vehicle and attributes of a driver of at least one adjacent vehicle using multiple onboard sensors; locking the doors of the vehicle; and closing the windows of the vehicle.

[0021] According to another aspect, the system controller is further adapted to initiate an active intervention action when the severity of the behavior pattern exceeds a second predetermined threshold, wherein the second predetermined threshold is set according to a preference received from an occupant in the transportation vehicle via the HMI.

[0022] According to another aspect, when an active intervention action is initiated, the system controller is also suitable for performing at least one of the following actions: issuing an alert to emergency services and emergency contacts via a wireless communication module; providing suggested navigation actions via an HMI; and autonomously performing navigation actions using a vehicle control module that communicates with the system controller.

[0023] Further areas of applicability will become apparent from the description provided herein.It should be understood that the description and specific examples are intended for purposes of illustration only and are not intended to limit the scope of the present disclosure. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The drawings described herein are for illustration purposes only and are not intended to limit the scope of the present disclosure in any way.

[0025] Figure 1 is a schematic diagram of a traffic vehicle having a system for monitoring improper behavior of neighboring traffic vehicles and initiating intervention actions according to an exemplary embodiment;

[0026] Figure 2 is a schematic diagram of a system according to an exemplary embodiment;

[0027] Figure 3 It is shown Figure 1 A schematic diagram of a traffic vehicle shown and a plurality of adjacent traffic vehicles traveling on a road;

[0028] Figure 4 is a flow chart showing an example of monitoring the rear-end collision behavior of adjacent traffic vehicles and initiating intervention actions;

[0029] Figure 5 is a flow chart showing an example of monitoring the tracking behavior of neighboring vehicles and initiating intervention actions; and

[0030] Figure 6 is a flow chart illustrating a method of monitoring improper behavior of at least one neighboring vehicle and initiating intervention action according to an exemplary embodiment.

[0031] The drawings are not necessarily drawn to scale, and some features may be exaggerated or minimized, for example, to show details of a particular component. In some cases, well-known components, systems, materials, or methods are not described in detail to avoid obscuring the present disclosure. Therefore, the specific structural and functional details disclosed herein should not be interpreted as limiting, but merely as a basis for the claims and as a representative basis for teaching those skilled in the art to adopt the present disclosure in different ways. DETAILED DESCRIPTION

[0032] The following description is merely exemplary in nature and is not intended to limit the present disclosure, application or use. In addition, it is not intended to be constrained by any express or implied theory presented in the aforementioned technical field, background technology, content of the invention or the following specific embodiments. It should be understood that throughout the drawings, corresponding reference numerals represent similar or corresponding components and features. As used herein, the term module refers to any hardware, software, firmware, electronic control component, processing logic and / or processor device, individually or in any combination, including but not limited to: application specific integrated circuits (ASICs), electronic circuits, processors (shared, dedicated or groups) and memories that execute one or more software or firmware programs, combinational logic circuits and / or other suitable components that provide the described functions. Although the drawings shown herein depict examples with certain element arrangements, additional intermediate elements, devices, features or components may be present in actual embodiments. It should also be understood that the drawings are merely illustrative and may not be drawn to scale.

[0033] As used herein, the term "vehicle" is not limited to automobiles. Although this article mainly describes the present technology in conjunction with automobiles, the present technology is not limited to automobiles. These concepts can be used in a variety of applications, such as aircraft, ships, other transportation vehicles, and consumer electronic components.

[0034] According to an exemplary embodiment, Figure 1 An electric vehicle 10 according to various embodiments is shown, which has an associated system 11 for monitoring the misbehavior of neighboring vehicles and initiating intervention. Generally speaking, the system 11 works with other systems within the vehicle 10 to display various information and infotainment content for passengers. The vehicle 10 generally includes a chassis 12, a body 14, a front wheel 16, and a rear wheel 18. The body 14 is disposed on the chassis 12 and substantially surrounds the components of the vehicle 10. The body 14 and the chassis 12 can form a frame together. The front wheel 16 and the rear wheel 18 are each rotatably connected to the chassis 12 near the corresponding corners of the body 14.

[0035] In various embodiments, the vehicle 10 is an autonomous vehicle, and the system 11 is incorporated into the autonomous vehicle 10. The autonomous vehicle 10 is, for example, a vehicle 10 that is automatically controlled to transport passengers from one location to another. The vehicle 10 is depicted as a passenger car in the illustrated embodiment, but it should be understood that any other vehicle may also be used, including motorcycles, trucks, sport utility vehicles (SUVs), recreational vehicles (RVs), etc. In an exemplary embodiment, the vehicle 10 is equipped with a so-called level 4 or level 5 automation system. The level 4 system represents "high automation" and refers to the driving mode-specific performance of the autonomous driving system in various aspects of dynamic driving tasks, even if the human driver does not respond appropriately to the intervention request. The level 5 system represents "full automation" and refers to the full-time performance of the autonomous driving system in various aspects of dynamic driving tasks under all road and environmental conditions that the human driver can manage. The novel aspects of the present disclosure are also applicable to non-autonomous vehicles, where the misbehavior detection and intervention capabilities are limited, but can still be implemented. For example, detection may be performed via ultrasonic and camera sensors, however, non-autonomous driving vehicles do not have the ability to take over control of the vehicle 10, so the options for intervention are limited.

[0036] As shown, the vehicle 10 generally includes a propulsion system 20, a transmission system 22, a steering system 24, a braking system 26, a sensor system 28, an actuator system 30, at least one data storage device 32, a vehicle controller 34, and a wireless communication module 36. In an embodiment where the vehicle 10 is an electric vehicle, the transmission system 22 may not be present. In various embodiments, the propulsion system 20 may include an internal combustion engine, an electric motor such as a traction motor, and / or a fuel cell propulsion system. The transmission system 22 is configured to transmit power from the propulsion system 20 to the front wheels 16 and rear wheels 18 of the vehicle according to a selectable speed ratio. According to various embodiments, the transmission system 22 may include a stepped automatic transmission, a continuously variable transmission, or other suitable transmissions. The braking system 26 is configured to provide braking torque to the front wheels 16 and rear wheels 18 of the vehicle. In various embodiments, the braking system 26 may include friction brakes, wire control brakes, regenerative braking systems (e.g., motors), and / or other suitable braking systems. The steering system 24 affects the position of the front wheels 16 and rear wheels 18. Although depicted as including a steering wheel for illustrative purposes, in some embodiments contemplated within the scope of the present disclosure, the steering system 24 may not include a steering wheel.

[0037] The sensor system 28 includes one or more sensing devices 40a-40n, which sense observable conditions of the external environment and / or internal environment of the autonomous driving vehicle 10. The sensing devices 40a-40n may include, but are not limited to, radar, lidar, global positioning system, optical camera, thermal camera, ultrasonic sensor and / or other sensors. The camera may include two or more digital cameras spaced a selected distance from each other, wherein the two or more digital cameras are used to obtain stereo images of the surrounding environment in order to obtain a three-dimensional image or map. Multiple sensing devices 40a-40n are used to determine information about the environment around the vehicle 10. In an exemplary embodiment, the multiple sensing devices 40a-40n include a motor speed sensor, a motor torque sensor, an electric drive motor voltage and / or current sensor, an accelerator pedal position sensor, a coolant temperature sensor, a cooling fan speed sensor and a transmission oil temperature sensor. In another exemplary embodiment, the multiple sensing devices 40a-40n also include sensors for determining information about the surrounding environment of the vehicle 10, such as an ambient air temperature sensor, an atmospheric pressure sensor and / or a camera and / or video camera for observing the environment in front of the vehicle 10. In another exemplary embodiment, at least one of the plurality of sensing devices 40 a - 40 n is capable of measuring distances in the surroundings of the vehicle 10 .

[0038] In a non-limiting example where the plurality of sensing devices 40a-40n include cameras, the plurality of sensing devices 40a-40n use an image processing algorithm configured to process images from the cameras and determine distances between objects to measure distances. In another non-limiting example, the plurality of traffic vehicle sensors 40a-40n include a stereo camera with distance measurement capabilities. In one example, at least one of the plurality of sensing devices 40a-40n is fixed to the interior of the traffic vehicle 10 (e.g., fixed in the roof lining of the traffic vehicle 10) with a view through the windshield of the traffic vehicle 10. In another example, at least one of the plurality of sensing devices 40a-40n is fixed to the exterior of the traffic vehicle 10 (e.g., fixed on the roof of the traffic vehicle 10) with a view of the environment surrounding the traffic vehicle 10. It should be understood that various additional types of sensing devices, such as lidar sensors, ultrasonic ranging sensors, radar sensors, and / or time-of-flight sensors are within the scope of the present disclosure. The actuator system 30 includes one or more actuator devices 42 a - 42 n that control one or more features of the vehicle 10 , such as, but not limited to, the propulsion system 20 , the transmission system 22 , the steering system 24 , and the braking system 26 .

[0039] The traffic vehicle controller 34 includes at least one processor 44 and a computer readable storage device or medium 46. The at least one data processor 44 can be any custom or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor of multiple processors associated with the traffic vehicle controller 34, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, any combination thereof, or any device generally used to execute instructions. The computer readable storage device or medium 46 can include volatile and non-volatile storage devices such as read-only memory (ROM), random access memory (RAM), and keep alive memory (KAM). KAM is a persistent or non-volatile memory that can be used to store various operating variables when the at least one data processor 44 is powered off. The computer readable storage device or medium 46 can be implemented using any of a variety of known storage devices, such as a PROM (programmable read-only memory), an EPROM (erasable programmable read-only memory), an EEPROM (electrically erasable programmable read-only memory), flash memory, or any other electrical, magnetic, optical, or combination storage device capable of storing data (some of which represents executable instructions) used by the controller 34 when controlling the transportation vehicle 10.

[0040] The instructions may include one or more separate programs, each of which includes an ordered list of executable instructions for implementing logical functions. When executed by at least one processor 44, the instructions receive and process signals from the sensor system 28, execute logic, calculations, methods and / or algorithms for automatically controlling components of the transportation vehicle 10, and generate control signals to the actuator system 30 to automatically control components of the transportation vehicle 10 based on the logic, calculations, methods and / or algorithms. Although Figure 1 Only one controller 34 is shown, but embodiments of the vehicle 10 may include any number of controllers 34 that communicate via any suitable communication medium or combination of communication mediums and collaborate to process sensor signals, execute logic, calculations, methods and / or algorithms, and generate control signals that automatically control features of the autonomous vehicle 10.

[0041] In various embodiments, one or more instructions of the traffic vehicle controller 34 are embedded in the trajectory planning system and, when executed by at least one data processor 44, generate trajectory outputs that solve the kinematic and dynamic constraints of the environment. For example, the instructions receive as input processed sensor and map data. These instructions implement a graph-based approach and customized cost functions to handle different road scenarios for cities and highways.

[0042] The wireless communication module 36 is configured to wirelessly transmit information to other remote entities 48, such as, but not limited to, other vehicles ("V2V" communication), infrastructure ("V2I" communication), remote systems, remote servers, cloud computers, and / or personal devices. In an exemplary embodiment, the communication system 36 is a wireless communication system configured to communicate via a wireless local area network (WLAN) using the IEEE 802.11 standard or by using cellular data communications. However, additional or alternative communication methods such as dedicated short-range communication (DSRC) channels are also considered to be within the scope of the present disclosure. A DSRC channel refers to a one-way or two-way short-range to medium-range wireless communication channel designed specifically for automotive use, as well as a set of corresponding protocols and standards.

[0043] The traffic vehicle controller 34 is a non-universal electronic control device having a pre-programmed digital computer or processor, memory or non-transitory computer-readable medium, and a transceiver [or input / output port] for storing data such as control logic, software applications, instructions, computer code, data, look-up tables, etc. Computer-readable media include any type of media that can be accessed by a computer, such as read-only memory (ROM), random access memory (RAM), hard drive, compact disk (CD), digital video disk (DVD), or any other type of memory. "Non-transitory" computer-readable media excludes wired, wireless, optical or other communication links that transmit temporary electrical or other signals. Non-transitory computer-readable media include media that can permanently store data and media that can store data and then be rewritten, such as rewritable optical disks or erasable storage devices. Computer code includes any type of program code, including source code, object code, and executable code.

[0044] refer to Figure 2 , a schematic diagram of the system 11 is shown. The system 11 includes a system controller 34A in communication with a plurality of sensing devices (onboard sensors) 40a-40n. The system controller 34A may be the vehicle controller 34, or the system controller 34A may be a separate controller in communication with the vehicle controller 34. In addition to the plurality of onboard sensors 40a-40n, the system controller 34A also communicates with a human machine interface (HMI) 50, a vehicle control module (VCM) 52, and a wireless communication module 36.

[0045] The system controller 34A is adapted to identify at least one neighboring vehicle 54. A neighboring vehicle 54 is a vehicle within a specified distance 56 of the vehicle 10. The distance 56 that the neighboring vehicle 54 must be at is based on the distance that the plurality of onboard sensors 40a-40n and the majority of such onboard sensors 40a-40n are capable of monitoring the neighboring vehicle 54. Thus, only vehicles that are close enough to be monitored by the plurality of sensing devices 40a-40n and the plurality of types of sensing devices 40a-40n are considered to be neighboring vehicles 54.

[0046] like Figure 2 As shown, the plurality of onboard sensors 40a-40n have detected six adjacent vehicles 54. The system controller 34A is further adapted to tag at least one adjacent vehicle 54 with a unique identifier. Figure 2 As shown, the system controller 34A has marked each of the six adjacent vehicles 54 with a unique identifier. Therefore, the two adjacent vehicles 54 located in the lane adjacent to the vehicle 10 on the left are designated as "L1" and "L2", the two adjacent vehicles 54 traveling in the same lane as the vehicle 10 are designated as "S1" and "S2", and the two adjacent vehicles 54 traveling in the lane adjacent to the vehicle 10 on the right are designated as "R1" and "R2".

[0047] The system controller 34A is also adapted to monitor the driving pattern of at least one adjacent traffic vehicle 54 using a plurality of onboard sensors 40a-40n, classify at least one adjacent traffic vehicle 54, and initiate intervention actions when appropriate. When monitoring the driving pattern of at least one adjacent traffic vehicle 54, the system controller 34A is also adapted to monitor the relative distance (from the traffic vehicle 10) of at least one adjacent traffic vehicle 54, the relative position (left lane, same lane, right lane, etc.) of at least one adjacent traffic vehicle 54, the relative speed of at least one adjacent traffic vehicle 54, and the heading direction of at least one adjacent traffic vehicle 54 using a plurality of onboard sensors 40a-40n. Data is collected periodically for each identified adjacent traffic vehicle 54 (L1, L2, S1, S2, R1, R2) by the plurality of onboard sensors 40a-40n. For example, in an exemplary embodiment, data is collected ten times per second or ten hertz by the plurality of onboard sensors 40a-40n for each identified adjacent traffic vehicle 54. Each time data is collected, the system controller 34A is adapted to fuse the data from the plurality of onboard sensors 40a - 40n for each identified neighboring vehicle 54 and construct a time series of data points given as [timestamp, vehicle_id, relative_dist, relative_pos, relative_speed] for each identified neighboring vehicle 54 .

[0048] When classifying at least one adjacent traffic vehicle 54, the system controller 34A is also suitable for identifying the behavior pattern of at least one adjacent traffic vehicle 54, and using the machine learning algorithm 58 within the system controller 34A to probabilistically classify the behavior pattern of at least one adjacent traffic vehicle 54, the behavior pattern of the at least one adjacent traffic vehicle 54 is one of normal behavior, aggressive behavior and tracking behavior. For each identified adjacent traffic vehicle 54, the system controller 34A analyzes the time series data points to find a recognizable pattern. For example, such a pattern may indicate that the driving behavior of the adjacent traffic vehicle 54 is normal, or the relative distance between the traffic vehicle 10 and the adjacent traffic vehicle 54 is always less than the safe distance for an extended period of time (which indicates aggressive behavior that may be a rear-end collision), or the adjacent traffic vehicle 54 has been following the traffic vehicle 10 for a period of time between different destinations (which indicates possible tracking behavior). Other recognizable signs of improper behavior of adjacent traffic vehicles include, for example, zigzag driving, tailgating, failure to issue a lane change signal, and frequent lane changes.

[0049] Key indicators of stalking behavior include the same vehicle or the same driver frequently appearing near the location of the vehicle 10, even in different areas or at different times. Stalkers often use repetitive patterns when targeting their victims. These patterns may include regularly following the victim's vehicle or repeatedly parking nearby. By observing such patterns, machine learning algorithms can establish a pattern of behavior and classify such a pattern as stalking.

[0050] To create the machine learning algorithm 58, different datasets are collected from vehicles equipped with sensors such as GPS, accelerometers, cameras, radars, and lidars. The data covers a variety of driving scenarios, including urban, highway, and off-road driving. Before the data is fed into the machine learning model, a preprocessing step is required to remove noise, handle missing values, and standardize features. An important step in driving behavior classification is to extract relevant features from the raw data. Various techniques are used to extract meaningful features from sensor readings, including time series analysis, frequency domain analysis, and spatiotemporal patterns. Different types of machine learning algorithms can be used for probabilistic classification of driving behavior patterns, including but not limited to long short-term memory (LSTM), gated recurrent unit (GRU), decision tree, random forest, support vector machine (SVM), neural network (NN), K nearest neighbor (KNN), gradient boosting, and recurrent neural network (RNN). The machine learning algorithm 58 is trained on the labeled dataset and evaluated using various performance metrics such as accuracy, precision, recall, F1-score, and confusion matrix. The hyperparameters of the model are adjusted to obtain the best results. The machine learning algorithm 58 is trained on the training data and learns to map input features to corresponding driving behavior probabilities.

[0051] In an exemplary embodiment, when the behavior pattern of at least one neighboring traffic vehicle 54 is classified as either aggression or tracking according to probability, the system controller 34A is also suitable for calculating the severity of the behavior pattern. For example, in an exemplary embodiment, the severity is calculated as a number between 0 and 5, where 0 is low severity and 5 is the highest severity. For example, the system controller 34A classifies the neighboring traffic vehicle 54 as exhibiting aggressive behavior based on the number of times the neighboring traffic vehicle 54 follows too closely. If multiple onboard sensors 40a-40n observe that the neighboring traffic vehicle 54 follows too closely five times within a time span of twenty minutes, the severity can be calculated as 0 or 1, wherein if multiple onboard sensors 40a-40n observe that the neighboring traffic vehicle 54 follows too closely fifteen times within a time span of twenty minutes, the severity can be calculated as 4 or 5. In another example, the system controller 34A classifies the neighboring traffic vehicle 54 as exhibiting aggressive behavior based on the distance at which the neighboring traffic vehicle 54 follows too closely. If the plurality of onboard sensors 40a-40n observes that the neighboring vehicle 54 is following too closely at a distance of twenty feet from the vehicle 10, the severity may be calculated as 0 or 1, wherein if the plurality of onboard sensors 40a-40n observes that the neighboring vehicle 54 is following too closely at a distance of five feet from the vehicle 10, the severity may be calculated as 4 or 5. In addition, the threshold distance (twenty feet, five feet) may be different when driving in a city or traffic congestion area, where vehicles would otherwise be traveling closer. For example, in a rural environment, the neighboring vehicle would need to be very close to the vehicle 10, two feet from the vehicle 10, before the severity is calculated as 4 or 5. The severity of the attack or stalking behavior may be calculated based on the incidence of the behavior or the magnitude of the behavior.

[0052] In an exemplary embodiment, the system controller 34A is further adapted to initiate a passive intervention action when the severity of the behavior pattern exceeds a first predetermined threshold. The first predetermined threshold is based on a preference setting received from an occupant within the vehicle 10 via the HMI 50. Such preferences may be set in advance by the occupant, or the system controller 34A may prompt the occupant to enter a preference each time an aggressive or stalking behavior of an identified neighboring vehicle 54 is indicated. For example, the first predetermined threshold of severity of aggressive or stalking behavior may be set to 2, wherein a passive intervention is initiated only when an aggressive or stalking behavior is classified with a calculated severity of 2 or higher.

[0053] In an exemplary embodiment, when a passive intervention action is initiated, the system controller 34A is also suitable for performing at least one of the following actions: (1) notifying occupants within the vehicle 10 that the adjacent vehicle 54 has been identified as either aggressive or stalking; (2) using multiple onboard sensors 40a-40n to acquire an image of at least one adjacent vehicle 54, an image of the license plate of at least one adjacent vehicle 54, and an image of the driver of the adjacent vehicle 54; (3) using multiple onboard sensors 40a-40n to collect attributes of at least one adjacent vehicle (color, license plate number, model, manufacturer, car, truck, van, RV) and attributes of the driver (hair color, male, female, race, clothing color); (4) locking the doors of the vehicle 10; and (5) closing the windows of the vehicle 10.

[0054] Passive interventions include actions taken in response to relatively low threat attacks and / or stalking behavior by neighboring vehicles 54. Passive interventions include collecting images and data that may serve as useful evidence if the situation escalates, as well as steps designed to protect occupants of the vehicle 10 when the situation escalates, such as locking doors and closing windows.

[0055] In an exemplary embodiment, the system controller 34A is further adapted to initiate a proactive intervention action when the severity of the behavior pattern exceeds a second predetermined threshold. The second predetermined threshold is based on a preference setting received from an occupant of the vehicle 10 via the HMI 50. Such preferences may be set in advance by the occupant, or the system controller 34A may prompt the occupant to enter a preference each time an indication of aggressive or stalking behavior of an identified neighboring vehicle 54 is given. For example, the second predetermined threshold of severity of aggressive or stalking behavior may be set to 4, wherein proactive intervention is initiated only for behaviors classified as aggressive or stalking with a calculated severity of 4 or above.

[0056] In an exemplary embodiment, when an active intervention action is initiated, the system controller 34A is further adapted to perform at least one of the following actions: (1) alerting emergency services 60 and emergency contacts 62 via the wireless communication module; (2) providing suggested navigation actions to occupants of the vehicle 10 via the HMI 50; and (3) autonomously performing navigation actions using the vehicle control module 52 in communication with the system controller 34A. Active interventions include actions taken in response to a relatively high threat of attack and / or stalking behavior by neighboring vehicles 54. In addition to passive intervention actions, active interventions also include proactively taking steps to seek assistance from emergency contacts 62 and services 60, and proactively taking evasive / defensive maneuvers, either by the occupants as suggested by the system controller 34A, or, if in an autonomous vehicle, autonomously taking evasive / defensive maneuvers via communications between the system controller 34A and the VCM 52.

[0057] refer to Figure 4 , as a non-limiting example, the system controller 34A has identified a neighboring traffic vehicle 54 that exhibits tailgating behavior. Beginning at box 70, the system controller 34A displays information on the HMI 50 to inform the occupants within the traffic vehicle 10 that the neighboring traffic vehicle 54 has been classified as aggressive due to exhibiting tailgating behavior. Moving to box 72, the system controller 34A obtains preferences from the occupant as to what the first predetermined threshold and the second predetermined threshold should be, either by accessing preferences previously entered by the occupant, or by receiving real-time input from the occupant via the HMI 50 in response to a prompt from the system controller 34A. Moving to box 74, the system controller 34A determines whether passive intervention or active intervention is required. If intervention or passive intervention is not required, moving to box 76, the traffic vehicle 10 remains in the same lane and no other action is taken. If the severity exceeds the first predetermined threshold, the passive intervention action at box 76 may also include acquiring an image of the neighboring traffic vehicle 54 and / or the license plate of the neighboring traffic vehicle 54. If active intervention is required, then move to box 78, the system controller 34A determines whether the traffic vehicle 10 is an autonomous traffic vehicle. If the traffic vehicle 10 is an autonomous traffic vehicle, then move to box 80, the traffic vehicle 10 automatically and autonomously navigates to the adjacent lane. If the traffic vehicle 10 is not an autonomous traffic vehicle, then move to box 82, the system controller 34A provides lane change guidance based on the traffic flow in the adjacent lane.

[0058] refer to Figure 5, as a non-limiting example, the system controller 34A has identified a neighboring traffic vehicle 54 that is exhibiting stalking behavior. Beginning at box 90, the system controller 34A checks the status of the door locks and windows of the traffic vehicle 10, and moves to box 92 to display information on the HMI 50 to notify the occupants within the traffic vehicle 10 that the neighboring traffic vehicle 54 has been classified as aggressive due to exhibiting stalking behavior. Moving to box 94, the system controller 34A obtains a preference from the occupant as to what the first predetermined threshold and the second predetermined threshold should be, either by accessing preferences previously entered by the occupant, or by receiving real-time input from the occupant via the HMI 50 in response to a prompt from the system controller 34A. Moving to box 96, the system controller 34A determines whether passive or active intervention is required. If passive intervention is required, moving to box 98, the system controller 34A acquires an image of the neighboring traffic vehicle 54 and / or the driver of the neighboring traffic vehicle, and collects attributes of the neighboring traffic vehicle 54 and / or the driver of the neighboring traffic vehicle 54. If active intervention is required, move to box 100, the system controller 34A initiates passive intervention, wherein the system controller 34A obtains images of the adjacent traffic vehicle 54 and / or the driver of the adjacent traffic vehicle, and collects attributes of the adjacent traffic vehicle 54 and / or the driver of the adjacent traffic vehicle 54, and moves to box 102, the system controller 34A determines whether the traffic vehicle 10 is an autonomous traffic vehicle. If the traffic vehicle 10 is an autonomous traffic vehicle, move to box 104, the traffic vehicle 10 automatically and autonomously navigates to a safe location. If the traffic vehicle 10 is not an autonomous traffic vehicle, move to box 106, the system controller 34A provides navigation instructions to a safe location. In either case, move to box 108, the system controller 34a contacts emergency services via the wireless communication module 36 to report the tracking to the police.

[0059] refer to Figure 6 , the method 200 for monitoring improper behavior of adjacent traffic vehicles and initiating traffic vehicle intervention includes: starting from box 202, multiple airborne traffic vehicle sensors 40a-40n communicating with the system controller 34A identify at least one adjacent traffic vehicle 54; moving to box 204, the system controller 34A uses a unique identifier to mark at least one adjacent traffic vehicle 54; moving to box 206, multiple airborne sensors 40a-40n communicating with the system controller 34A monitor the driving mode of at least one adjacent traffic vehicle 54; moving to box 208, the system controller 34A classifies at least one adjacent traffic vehicle 54; and, moving to box 210, the system controller 34A initiates an intervention action.

[0060] In an exemplary embodiment, monitoring the driving mode of at least one adjacent vehicle 54 by multiple onboard sensors 40a-40n communicating with the system controller 34A at box 206 also includes: monitoring the relative distance of at least one adjacent vehicle 54, the relative position of at least one adjacent vehicle, and the relative speed of at least one adjacent vehicle by multiple onboard sensors 40a-40n.

[0061] In another exemplary embodiment, monitoring the driving pattern of at least one adjacent vehicle 54 by multiple onboard sensors 40a-40n communicating with the system controller 34A at box 206 also includes: moving to box 212, periodically fusing data from the multiple onboard sensors 40a-40n by the system controller 34A; and, moving to box 214, constructing a time series of data points by the system controller 34A.

[0062] In another exemplary embodiment, the classification of at least one adjacent traffic vehicle 54 by the system controller 34A at box 208 also includes: moving to box 216, identifying the behavior pattern of at least one adjacent traffic vehicle 54 by the system controller 34A; and, moving to box 218, classifying the behavior pattern of at least one adjacent traffic vehicle 54 as one of normal behavior, aggressive behavior, and tracking behavior based on probability by the machine learning algorithm 58 within the system controller 34A.

[0063] In another exemplary embodiment, at box 218, the machine learning algorithm 58 in the system controller 34A classifies the behavior pattern of at least one neighboring traffic vehicle 54 as one of normal behavior, aggressive behavior, and tracking behavior based on probability, further comprising: moving to box 220, when the behavior pattern of at least one neighboring traffic vehicle 54 is classified as any one of aggressive behavior or tracking behavior based on probability, moving to box 222, and calculating the severity of the behavior pattern by the system controller 34A. When the behavior pattern of at least one neighboring traffic vehicle 54 is not classified as any one of aggressive behavior or tracking behavior based on probability, moving to box 224, the method 200 ends, and no intervention action is taken.

[0064] In another exemplary embodiment, the method 200 includes moving from box 222 to box 226, so that the system controller 34A receives preferences of an occupant in the transportation vehicle 10 related to the first predetermined threshold and the second predetermined threshold via the HMI 50, and sets the first predetermined threshold and the second predetermined threshold based on the occupant's preferences. Moving to box 228, when the severity of the behavior pattern exceeds the first predetermined threshold, initiating an intervention action by the system controller 34A at box 210 also includes: moving to box 230, initiating a passive intervention action by the system controller 34A.

[0065] In an exemplary embodiment, the passive intervention action initiated by the system controller 34A at box 230 also includes at least one of the following: moving to box 232, notifying the occupants in the transportation vehicle 10 via the transportation vehicle human-machine interface (HMI) 50 that communicates with the system controller 34A that at least one adjacent transportation vehicle 54 has been identified by the system controller 34A as one of aggressive behavior or tracking behavior; moving to box 234, obtaining an image of at least one adjacent transportation vehicle 54 and an image of the license plate of at least one adjacent transportation vehicle 54 by multiple onboard sensors 40a-40n; moving to box 236, obtaining an image of the driver of the adjacent transportation vehicle 54 by multiple onboard sensors 40a-40n; moving to box 238, collecting attributes of at least one adjacent transportation vehicle 54 and attributes of the driver of at least one adjacent transportation vehicle 54 by multiple onboard sensors 40a-40n; moving to box 240, locking the door of the transportation vehicle 10; and, moving to box 242, closing the window of the transportation vehicle 10.

[0066] In yet another exemplary embodiment, moving to block 244, when the severity of the behavior pattern exceeds a second predetermined threshold, initiating an intervention action by the system controller 34A at block 210 further includes moving to block 246, initiating an active intervention action by the system controller 34A.

[0067] In another exemplary embodiment, the active intervention action initiated by the system controller 34A at box 246 also includes at least one of the following: moving to box 248, the system controller 34A issues an alert to the emergency service 60 via the wireless communication module 36; moving to box 250, the system controller 34A issues an alert to the emergency contact 62 via the wireless communication module 36; moving to box 252, the system controller 34A provides a suggested navigation action via the HMI 50; and, moving to box 254, the traffic vehicle control module 52 that communicates with the system controller 34A autonomously performs the navigation action.

[0068] The system and method disclosed herein have the following advantages: monitoring at least one neighboring traffic vehicle and using a machine learning algorithm to classify the behavior of at least one neighboring traffic vehicle into normal behavior, aggressive behavior or tracking behavior based on probability, and initiating intervention actions based on the type of aggressive or tracking behavior, the severity of the inappropriate behavior, and the preferences of the occupants. This enables the occupants in the traffic vehicle to obtain indications of suspicious behavior of the neighboring traffic vehicle as early as possible, and when the behavior of the neighboring traffic vehicle escalates, intervention actions are provided to ensure the safety of the occupants in the traffic vehicle.

[0069] The description of the present disclosure is merely exemplary in nature, and variations that do not depart from the gist of the present disclosure are intended to fall within the scope of the present disclosure. These variations should not be regarded as departing from the spirit and scope of the present disclosure.

Claims

1. A method for a vehicle to monitor improper behavior of a neighboring vehicle and initiate intervention, comprising: identifying at least one adjacent vehicle by a plurality of onboard vehicle sensors in communication with a system controller; marking, by the system controller, the at least one adjacent vehicle with a unique identifier; monitoring a driving pattern of the at least one adjacent vehicle by a plurality of onboard sensors in communication with the system controller; Classifying, by the system controller, the at least one adjacent vehicle; as well as The intervention action is initiated by the system controller.

2. The method according to claim 1, wherein: The monitoring of the driving mode of the at least one adjacent vehicle by a plurality of onboard sensors in communication with the system controller further comprises monitoring, by the plurality of onboard sensors: The relative distance of at least one adjacent vehicle; The relative position of the at least one adjacent vehicle; The relative speed of the at least one adjacent vehicle; and The traveling direction of the at least one adjacent vehicle.

3. The method according to claim 2, wherein: The monitoring of the driving pattern of the at least one adjacent vehicle by a plurality of onboard sensors in communication with the system controller further comprises: periodically fusing, by the system controller, data from the plurality of onboard sensors; and A time series of data points is constructed by the system controller.

4. The method according to claim 3, wherein: The classifying of the at least one adjacent vehicle by the system controller further comprises: identifying, by the system controller, a behavior pattern of the at least one adjacent vehicle; and The machine learning algorithm in the system controller classifies the behavior pattern of the at least one adjacent vehicle into one of normal behavior, aggressive behavior and tracking behavior based on probability.

5. The method according to claim 4, wherein: The machine learning algorithm within the system controller classifies the behavior pattern of the at least one adjacent vehicle as one of normal behavior, aggressive behavior and tracking behavior based on probability, and also includes: when the behavior pattern of the at least one adjacent vehicle is classified as one of aggressive behavior or tracking behavior based on probability, the system controller calculates the severity of the behavior pattern.

6. The method according to claim 5, wherein: When the severity of the behavior pattern exceeds a first predetermined threshold, the initiating an intervention action by the system controller further includes: initiating a passive intervention action by the system controller.

7. The method according to claim 6, wherein: The passive intervention action initiated by the system controller further includes at least one of the following: Notifying an occupant of the transportation vehicle, via a transportation vehicle human machine interface (HMI) in communication with the system controller, that the at least one neighboring transportation vehicle has been identified by the system controller as having been classified as one of an aggressive behavior or a stalking behavior; Acquire an image of the at least one adjacent traffic vehicle and an image of a license plate of the at least one adjacent traffic vehicle by the multiple airborne sensors; Acquiring an image of a driver of the adjacent vehicle by the plurality of onboard sensors; Collecting attributes of the at least one adjacent vehicle and attributes of a driver of the at least one adjacent vehicle by the plurality of onboard sensors; Locking doors of transportation vehicles; or Close the windows of the vehicle.

8. The method according to claim 7, wherein: When the severity of the behavior pattern exceeds a second predetermined threshold, the initiating of an intervention action by the system controller further includes: initiating an active intervention action by the system controller.

9. The method according to claim 8, wherein: The active intervention action initiated by the system controller further includes at least one of the following: issuing an alert by the system controller to emergency services via the wireless communication module; issuing an alert to an emergency contact by the system controller via the wireless communication module; providing suggested navigation actions by the system controller via the HMI; or Navigation actions are performed autonomously by a vehicle control module that communicates with the system controller.

10. The method according to claim 9, further comprising: receiving, by the system controller via the HMI, preferences of an occupant of the transportation vehicle related to the first predetermined threshold and the second predetermined threshold; as well as The first predetermined threshold and the second predetermined threshold are set based on the occupant's preference.

Images