Radar and camera fusion based wireless communication misbehavior detection

Abstract

A method of detecting malicious wireless V2X communications includes retrieving perception data from a perception system on a host vehicle, determining information of nearby objects from the perception data, receiving a first basic safety message (BSM) from a first V2X source, and determining whether a vehicle location indicated in the first BSM corresponds to a location visible to the host vehicle. In the event that the vehicle location indicated in the first BSM does not correspond to the location visible to the host vehicle, the method further includes receiving a second V2X communication from a second V2X source and determining whether the second V2X communication indicates a vehicle at the vehicle location indicated in the first BSM. In the event that the second V2X communication does not indicate a vehicle at the vehicle location indicated in the first BSM, the first BSM data is flagged as malicious.

Description

Technical Field

[0001] This disclosure relates to determining the validity of vehicle-to-everything (V2X) wireless communication messages received by a vehicle. Background Technology

[0002] V2X communication alerts drivers to vehicles equipped with similar technology in their vicinity. Information shared via V2X can provide warnings of potential hazards and allow drivers to take steps to avoid collisions. However, malicious V2X messages may also be transmitted to interfere with the benefits of V2X communication and cause traffic congestion or collisions.

[0003] Therefore, although current systems used for V2X communication have achieved their intended purpose, a new and improved system and approach are still needed to deal with malicious V2X messages. Summary of the Invention

[0004] According to several aspects, a method for detecting malicious wireless V2X communication includes: retrieving sensing data from a sensing system on a vehicle; and determining information about nearby objects based on the sensing data. The method further includes receiving a first basic security message (BSM) from a first V2X source and determining whether a vehicle location indicated in the first BSM corresponds to a location visible to the sensing system. If the vehicle location indicated in the first BSM does not correspond to a location visible to the sensing system, the method includes receiving second V2X communication from a second V2X source different from the first V2X source and determining whether the second V2X communication indicates that the vehicle is at the vehicle location indicated in the first BSM. If the second V2X communication does not indicate that the vehicle is at the vehicle location indicated in the first BSM, the method includes marking the first BSM data as malicious.

[0005] In another aspect of this disclosure, the first BSM includes the time, location, speed, and direction of travel of nearby vehicles.

[0006] In another aspect of this disclosure, the information about nearby objects determined based on the perception data includes estimates of their distance, speed, and direction of travel relative to the vehicle's own position.

[0007] In another aspect of this disclosure, the method further includes performing a secondary check on the first BSM.

[0008] In another aspect of this disclosure, the secondary inspection includes a check on the reasonableness of the vehicle speed.

[0009] In another aspect of this disclosure, the secondary checks include message consistency checks.

[0010] In another aspect of this disclosure, the second V2X source is a roadside unit.

[0011] In another aspect of this disclosure, a sensor self-test is performed before receiving second V2X communication from a second V2X source.

[0012] In another aspect of this disclosure, the method also includes refining the sensor parameters of the sensors in the sensing system.

[0013] Further applications will become apparent from the description provided herein. It should be understood that the descriptions and specific examples are for illustrative purposes only and are not intended to limit the scope of this disclosure. Attached Figure Description

[0014] The accompanying drawings described herein are for illustrative purposes only and are not intended to limit the scope of this disclosure in any way.

[0015] Figure 1 This is a schematic block diagram of a vehicle according to an exemplary embodiment;

[0016] Figure 2 and Figure 3 This is a diagram illustrating a hypothetical scenario where the vehicle itself is near other vehicles, according to an exemplary embodiment.

[0017] Figure 4 This is a flowchart of an algorithm for detecting inappropriate behavior in V2X according to an exemplary embodiment;

[0018] Figure 5 It is shown Figure 4 A detailed diagram of the sensor fusion components in the flowchart; and

[0019] Figure 6 The results of a proof-of-concept experiment are presented, which compares the detection of inappropriate behavior using the proposed sensor fusion algorithm and the camera-only algorithm. Detailed Implementation

[0020] The following detailed description is exemplary in nature only and is not intended to limit this application or use. Furthermore, it is not intended to be limited by the explicit or implicit theories presented in the foregoing technical field, background, summary of the invention, or the following detailed description. As used herein, the term "module" means individual hardware, software, firmware, electronic control components, processing logic and / or processor devices or combinations thereof, including but not limited to: application-specific integrated circuits (ASICs), electronic circuits, processors (shared processors, dedicated processors, or processor groups) and memory executing one or more software or firmware programs, combinational logic circuits, and / or other suitable components providing the said functionality.

[0021] Embodiments of this disclosure can be described herein in terms of functional and / or logical block components and various processing steps. It should be understood that such block components can be implemented by hardware, software, and / or firmware components configured to perform specified functions. For example, embodiments of this disclosure can employ various integrated circuit components, such as memory elements, digital signal processing elements, logic elements, lookup tables, etc., which can perform various functions under the control of one or more microprocessors or other control devices. Furthermore, those skilled in the art will understand that embodiments of this disclosure can be practiced in conjunction with multiple systems, and the systems described herein are merely exemplary embodiments of this disclosure.

[0022] For the sake of brevity, techniques related to signal processing, data fusion, signal transmission, control, and other functional aspects of the system (and its various operating components) may not be described in detail herein. Furthermore, the connecting lines shown in the various figures included herein are intended to represent example functional relationships and / or physical connections between various elements. It should be noted that alternative or additional functional relationships or physical connections may exist in the embodiments of this disclosure.

[0023] Many vehicles are equipped with sensors such as radar, cameras, ultrasonic sensors, and lidar to detect objects around the vehicle and notify the driver of their presence or take measures (e.g., automatic braking) to avoid a collision. Vehicle-to-vehicle (V2V) wireless communication can improve vehicle safety by allowing a vehicle to exchange real-time information on speed, position, and direction with other nearby vehicles. As used herein, the term "own vehicle" refers to the primary connected vehicle and / or automated vehicle whose behavior is of primary concern in the operational scenario.

[0024] Even when other objects obstruct the driver's view, V2V allows the vehicle itself and another connected vehicle to communicate electronically within a range of approximately 300 meters, thereby enhancing safety. This "look-around" capability can be a crucial safety feature in various common driving scenarios. Examples of scenarios where V2V can enhance safety include, but are not limited to: when the vehicle and another vehicle are approaching each other at a blind curve or tactile paving intersection: viewing a large truck in front of the vehicle to determine if it is safe to pass, providing information about a car suddenly braking in traffic congestion ahead, identifying vehicles emerging from a lane or parking space, and alerting the driver of the vehicle ahead that the vehicle has come to a complete stop and is turning left. With timely notification, the driver of the vehicle can adjust their speed and / or direction of travel to reduce the likelihood of a collision.

[0025] As used in this article, the term vehicle-to-everything (V2X) wireless communication includes various forms of wireless communication with one's own vehicle, including V2V, vehicle-to-infrastructure (V2I), vehicle-to-pedestrian (V2P), etc.

[0026] like Figure 1 As shown, a vehicle 10, which can be considered as a self-contained vehicle, typically includes a chassis 12, a body 14, front wheels, and rear wheels 17. The body 14 is mounted on the chassis 12 and substantially covers all components of the vehicle 10. The body 14 and the chassis 12 may together form a frame. Each wheel 17 is rotatably connected to the chassis 12 near a corresponding corner of the body 14.

[0027] Vehicle 10 is described as a passenger car in the illustrated embodiment, but it should be understood that other vehicles, including motorcycles, trucks, sports utility vehicles (SUVs), recreational vehicles (RVs), boats, aircraft, etc., may also be used.

[0028] As shown, vehicle 10 typically 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, at least one controller 34, and a communication system 36. In various embodiments, the propulsion system 20 may include an electric motor, such as a traction electric motor, and / or a fuel cell propulsion system. Vehicle 10 also includes a battery (or battery pack) 21 electrically connected to the propulsion system 20. Therefore, the battery 21 is configured to store electrical energy and supply electrical energy to the propulsion system 20. Furthermore, the propulsion system 20 may include an internal combustion engine. The transmission system 22 is configured to transmit power from the propulsion system 20 to the wheels 17 according to a selectable speed ratio. According to various embodiments, the transmission system 22 may include a stepped automatic transmission, a continuously variable transmission (CVT), or other suitable transmission. The braking system 26 is configured to provide braking torque to the wheels 17. In various embodiments, the braking system 26 may include friction brakes, brake-by-wire brakes, regenerative braking systems such as electric motors, and / or other suitable braking systems. The steering system 24 influences the position of the wheels 17. Although described for illustrative purposes as including a steering wheel, in some embodiments contemplated within the scope of this disclosure, the steering system 24 may also not include a steering wheel.

[0029] Sensor system 28 includes one or more sensors 40 (i.e., sensing devices) that sense observable conditions of the external and / or internal environment of vehicle 10. Sensors 40 may include, but are not limited to, radar, lidar, GPS, optical cameras, thermal imagers, ultrasonic sensors, and / or other sensors. Actuator system 30 includes one or more actuator devices 42 that control one or more vehicle features, such as, but not limited to, propulsion system 20, drivetrain 22, steering system 24, and braking system 26. In various embodiments, vehicle features may also include internal and / or external vehicle features, such as, but not limited to, doors, trunk, and cabin features, such as air, music, lighting, etc. (unnumbered). Sensor system 28 includes one or more GPS transceivers 40g configured to detect and monitor route data (i.e., route information). GPS transceivers 40g are configured to communicate with GPS to locate the position of vehicle 10 globally. GPS transceivers 40g communicate electronically with controller 34. Because sensor system 28 provides object data to controller 34, sensor system 28 and its sensors 40 are considered information sources (or simply sources). Sensor system 28 also includes one or more optical cameras 40c. Figure 1 The designation of the optical camera 40c is intended only to show the contents of the optical camera 40c and is not intended to imply any limitation on the position or field of view of the optical camera 40c.

[0030] Data storage device 32 stores data for automatically controlling vehicle 10. In various embodiments, data storage device 32 stores a defined map of the navigable environment. In various embodiments, the defined map may be predefined by a remote system and obtained from the remote system (e.g., regarding...). Figure 2 (To be described in further detail). For example, the defined map may be assembled by a remote system and transmitted to vehicle 10 (wirelessly and / or via wire) and stored in data storage device 32. It is understood that data storage device 32 may be part of controller 34, separate from controller 34, or simultaneously part of controller 34 and a separate system.

[0031] The controller 34 includes at least one processor 44 and a computer-readable storage device or medium 46. The processor 44 may be a custom or commercially available processor, a central processing unit (CPU), a graphics processing unit (GPU), an auxiliary processor among several processors associated with the controller 34, a semiconductor-based microprocessor (in the form of a microchip or chipset), a macroprocessor, a combination thereof, or generally a device for executing instructions. For example, the computer-readable storage device or medium 46 may include volatile and non-volatile memory in the form of 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 operational variables when the processor 44 is powered off. The computer-readable storage device or medium 46 may be implemented using many known memory devices, such as PROM (programmable read-only memory), EPROM (electrical PROM), EEPROM (electrically erasable PROM), flash memory, or other electrical, magnetic, optical, or combined storage devices capable of storing data, some of which represents executable instructions used by the controller 34 when controlling the vehicle 10.

[0032] The instructions may include one or more separate programs, each including an ordered list of executable instructions for implementing logical functions. When executed by processor 44, the instructions receive and process signals from sensor system 28, execute logic, calculations, methods, and / or algorithms for automatically controlling components of vehicle 10, and generate control signals to actuator system 30 based on the logic, calculations, methods, and / or algorithms to automatically control components of vehicle 10. Although Figure 1 Only one controller 34 is shown in the diagram, but embodiments of vehicle 10 may also include multiple controllers 34 that communicate and cooperate via suitable communication media or combinations of communication media to process sensor signals, perform logic, calculations, methods and / or algorithms, and generate control signals to automatically control the features of vehicle 10.

[0033] In various embodiments, one or more instructions of controller 34 are embodied in control system 98. Vehicle 10 includes user interface 23, which may be a touchscreen in the dashboard. User interface 23 communicates electronically with controller 34 and is configured to receive input from a user (e.g., a vehicle operator). Therefore, controller 34 is configured to receive input from a user via user interface 23. User interface 23 includes a display configured to show information to a user (e.g., a vehicle operator or passenger).

[0034] Communication system 36 is configured to wirelessly exchange information with other entities 48, such as, but not limited to, other vehicles ("V2V" communication), infrastructure ("V2I" communication), remote systems, and / or personal devices. In an exemplary embodiment, communication system 36 is a wireless communication system configured to communicate using a wireless local area network (WLAN) of the IEEE 802.11 standard or using cellular data communication. However, additional or alternative communication methods, such as dedicated short-range communication (DSRC) channels, are also considered within the scope of this disclosure. A DSRC channel refers to a one-way or two-way short-to-medium-range wireless communication channel designed specifically for automotive use, along with a set of corresponding protocols and standards. Therefore, communication system 36 may include one or more antennas and / or transceivers for receiving and / or transmitting signals, such as cooperative sensing messages (CSM).

[0035] Figure 1 A schematic block diagram of a control system 98 configured to control vehicle 10 is included. The controller 34 of the control system 98 communicates electronically with a braking system 26, a propulsion system 20, and a sensor system 28. The braking system 26 includes one or more brake actuators (e.g., brake calipers) coupled to one or more wheels 17. Upon actuation, the brake actuators apply braking pressure to one or more wheels 17 to decelerate vehicle 10. The propulsion system 20 includes one or more propulsion actuators for controlling the propulsion of vehicle 10. For example, as described above, the propulsion system 20 may include an internal combustion engine, and in this case, the propulsion actuator may be a throttle valve specifically configured to control airflow in the internal combustion engine. The sensor system 28 may include one or more accelerometers (or one or more gyroscopes) coupled to one or more wheels 17. The accelerometers communicate electronically with the controller 34 and are configured to measure and monitor the longitudinal and lateral acceleration of vehicle 10. The sensor system 28 may include one or more speed sensors configured to measure the speed (or rate) of vehicle 10. The speed sensors are coupled to the controller 34 and communicate electronically with one or more wheels 17.

[0036] refer to Figure 2 Vehicle 10 is the vehicle itself depicted in a traffic scene on a two-lane road 50. The traffic flow direction in each of the two lanes is indicated by arrows 52 and 53. Figure 2Vehicles 54 and 56 ahead of vehicle 10 are also depicted traveling in the same direction as vehicle 10. Another vehicle 58 is shown traveling in the opposite direction to vehicle 10. A roadside unit (RSU) 60 is shown adjacent to road 50. RSU 60 includes sensors, such as one or more cameras and / or one or more lidar sensors capable of detecting the position, speed, and / or direction of travel of nearby vehicles 10, 54, 56, and 58 on road 50. RSU 60 also includes communication devices that allow RSU 60 to broadcast the position, speed, and / or direction of travel of nearby detected vehicles 10, 54, 56, and 58 via any of several available protocols, including but not limited to cellular (4G / 5G), Dedicated Short Range Communication (DSRC), and Cellular Vehicle-to-Everything (C-V2X).

[0037] Vehicle outline 62 is also Figure 2 The dashed line indicates vehicle 62. The dashed line associated with vehicle 62 indicates that vehicle 62 does not actually exist, but is a "ghost" vehicle created by a malicious entity. In a Sybil attack, a malicious entity forges numerous false identities to disrupt the normal operation of V2X applications, broadcasting V2X signals to make it appear as if a real vehicle exists at the location indicated for ghost vehicle 62. The malicious entity may generate false traffic information that differs from real-world information and broadcast it to the V2X network to disrupt road traffic or cause collisions. (Continue to reference...) Figure 2 Vehicle 54 in front of vehicle 10 may obstruct the driver's view of the left lane. Malicious V2X broadcasts conveying the presence of a (non-existent) ghost vehicle 62 may influence the driver's decisions, such as whether to initiate an overtaking maneuver around vehicle 54.

[0038] refer to Figure 3 The image depicts a traffic scene at an intersection. Vehicle 10 is approaching the intersection, while other vehicles 54 and 56 are already crossing it. The ghost vehicle 62 is also depicted using a dashed outline. (As mentioned earlier...) Figure 2 The ghost vehicle 62 does not actually exist; it is perceived as a vehicle due to V2X communication broadcast by a malicious entity. Based on this malicious V2X communication, the vehicle 10 may react by slowing down and / or braking suddenly, and may not enter the intersection. This results in decreased traffic efficiency and could even lead to a traffic collision. If the vehicle 10 can determine that the ghost vehicle 62 is not real but a fabrication of malicious V2X communication, it can safely ignore the ghost vehicle 62 and continue driving normally.

[0039] refer to Figure 4 A flowchart of algorithm 100 for V2X misbehavior detection is presented. The steps of algorithm 100 are relative to... Figure 1 Executed in controller 34 as described. See reference... Figure 1 The vehicle 10 under discussion includes a perception system comprising one or more optical cameras 40c and / or lidar sensors and / or ultrasonic sensors, capable of identifying nearby objects within the vehicle 10's line of sight. In step 102, the vehicle 10 retrieves perception data from the perception system. The perception data from step 102 is provided as signal 154 to a sensor fusion step 104 to provide estimates of the distance, velocity, and direction of travel of the nearby objects relative to the vehicle 10, as referenced to... Figure 5 As discussed further. In step 106, a Basic Safety Message (BSM) is received from nearby vehicles. The BSM contains information including time, latitude, longitude, altitude, speed, direction of travel, acceleration, and the size of nearby vehicles. In step 108, based on the sensor fusion data from step 104, it is determined whether the location indicated in the BSM data corresponds to an object visible to the vehicle. If the BSM location is determined to be within the visible area based on the sensor fusion data in step 108, the algorithm proceeds from step 108 to step 110.

[0040] In step 110, it is determined whether the information provided in the BSM data matches a visible vehicle. If the information does not match a visible vehicle, the algorithm proceeds to step 116, where the BSM data is marked as malicious. If the information provided in the BSM data matches a visible vehicle, algorithm 100 proceeds from step 110 to step 112. In step 112, a secondary check is performed on the BSM data, such as a vehicle speed reasonableness check or a message consistency check. If the BSM data passes the secondary check in step 112, the algorithm proceeds to step 114, where the BSM data is marked as trustworthy. If the secondary check in step 112 fails, the algorithm proceeds to step 116, where the BSM data is marked as malicious.

[0041] Continue to refer to Figure 4 If, in step 108, it is determined based on sensor fusion data that the BSM location is not within the visible area, the algorithm proceeds from step 108 to step 118. In step 118, a sensor self-test is performed to verify that the camera and / or lidar sensor and / or ultrasonic sensor that provided the perception data in step 102 are operating correctly. If the sensor self-test in step 118 indicates a sensor problem, the algorithm proceeds to step 130. In step 130, a sensor problem notification is generated to indicate that the sensor needs to be repaired, and the improper system operation is downgraded to using only secondary checks, such as vehicle speed reasonableness checks or message consistency checks.

[0042] If the sensor self-test in step 118 indicates that all sensors are operating correctly, the algorithm proceeds to sensor refinement step 120. In sensor refinement step 120, sensor calibration parameters such as limits, range, and field of view are refined for the sensing sensors that provided the perception data in step 102, and the refined parameters are provided from step 120 to sensor fusion step 104. Simultaneously, the algorithm executes step 122, in which a secondary check is performed on the BSM data, such as a vehicle speed reasonableness check or a message consistency check. If the secondary check of the BSM data fails in step 122, the algorithm proceeds to step 116, where the BSM data is marked as malicious. If the BSM data passes the secondary check in step 122, the algorithm proceeds to step 124, where the BSM data is compared with data received from other sources, such as data received from roadside unit 60. If the BSM data can be correlated with other data with high confidence, the algorithm proceeds to step 126, where the BSM data is marked as trustworthy. If the BSM data cannot be correlated with other data with high confidence, the algorithm proceeds to step 128, where the BSM data is marked as reliable.

[0043] refer to Figure 5 and Figure 4 A flowchart is provided that presents a further description of the elements related to sensor fusion step 104. (As opposed to...) Figure 4 In the sensor refinement step 120, sensor calibration parameters such as limits, range, and field of view are refined for the sensing sensors that provided perception data in step 102 to better understand objects around the vehicle 10. In step 104, the refined parameters are provided to element 140, where calibration and synchronization are required if multiple sensors do not share the same acquisition time scale. If the time is not fully synchronized, a Kalman filter 146 is used to calculate the gain matrix for further reference. After calibration and synchronization in element 140, a deep learning-based camera recognition algorithm occurs in element 142, and radar or lidar point cloud generation occurs in element 144. Results information about detected objects, including object type, direction of travel, and estimated distance, is stored in shared memory 152. Shared memory 152 is accessible from multiple electronic control units (ECUs) to allow multiple processes to access information without increasing input / output time and cost.

[0044] Continue to refer to Figure 5In element 148, points outside the camera detection area in the radar / liDAR point cloud generated in element 144 are filtered out. Based on the fused data, distance estimation to nearby objects is performed in element 150. The results from sensor fusion step 104, including bounding boxes, object type, direction of travel, object features, distance, estimated GPS coordinates, and relative velocity, are provided as signal 154 to determination step 108, such as... Figure 4 and Figure 5 As shown.

[0045] Figure 6 Results are presented evaluating the inappropriate behavior detection (MDB) algorithm 100 disclosed herein in an intersection movement assist (IMA) scenario. To obtain... Figure 6 The evaluation results presented here demonstrate that the MDB algorithm 100 was simulated using non-ideal camera and radar sensor enhancements. It is conceivable that camera-based recognition is not 100% accurate, and that MDB accuracy is limited by the accuracy of vision-based recognition and radar accuracy. Experimental results are based on a hardware-in-the-loop (HIL) simulation system simulating the real characteristics of the physical sensors. The results are presented in a graph 600 of the F1 score, plotted proportionally along the vertical axis 605 and along the horizontal axis 610 for each of the ten individual experimental runs. The F1 score is defined as the harmonic mean of precision and recall. In calculating the F1 score, precision represents the percentage of truly positive items out of all items predicted as positive, i.e., (true positives # / (true positives # + false positives #)), and recall represents the percentage of truly positive items that are identified as positive, i.e., (true positives # / (true positives # + false negatives #)).

[0046] refer to Figure 6 The F1 score of the MBD algorithm 100 disclosed in this paper is plotted as Data Series 615, where MDB detection is based on both camera and radar data. For comparative purposes, the F1 score of the algorithm based on camera data without radar data is shown as Data Series 620. Figure 6 The results show that the F1 score produced by the MDB algorithm 100 disclosed in this paper is higher than that of the baseline camera-only algorithm, indicating that the MDB algorithm 100 disclosed in this paper provides excellent identification of Sybil attack ghost vehicles in IMA scenarios.

[0047] The methods and systems disclosed herein for detecting improper behavior in V2X communications have several advantages. These advantages include the potential to avoid traffic congestion or accidents caused by receiving malicious instructions from ghost vehicles and mistakenly believing there are vehicles nearby. Furthermore, in some respects, the vehicle itself can provide information about identified malicious V2X messages to benefit other vehicles.

[0048] The description in this disclosure is exemplary in nature only, and any changes that do not depart from the spirit and scope of this disclosure are intended to fall within its scope. Such changes should not be considered as departing from the spirit and scope of this disclosure.

Claims

1. A method for detecting malicious wireless V2X communication, the method comprising: Retrieve sensing data from the vehicle's own sensing system; Information about nearby objects is extracted from the sensed data using sensor fusion technology; Receive the first basic security message (BSM) from the first V2X source; Determine whether the vehicle location indicated in the first BSM corresponds to a location visible to the sensing system; If the vehicle location indicated in the first BSM does not correspond to a location visible to the sensing system: Perform a sensor self-test to verify that the sensors in the sensing system are operating correctly; In response to the sensor self-test indicating that the sensor is operating correctly, the sensor parameters of the sensors in the sensing system are refined; Receive second V2X communication from a second V2X source different from the first V2X source, and determine whether the second V2X communication indicates that the vehicle is at the vehicle location indicated in the first BSM; as well as If the second V2X communication does not indicate that the vehicle is at the vehicle location indicated in the first BSM, the first BSM data is marked as malicious.

2. The method according to claim 1, wherein, The first BSM includes the time, location, speed, and direction of travel of nearby vehicles.

3. The method according to claim 1, wherein, The information about nearby objects determined based on the perceived data includes estimates of distance, speed, and direction of travel relative to the vehicle's own position.

4. The method according to claim 1 further includes performing a secondary check on the first BSM.

5. The method according to claim 4, wherein, The secondary inspection includes checking the reasonableness of the vehicle speed.

6. The method according to claim 4, wherein, The secondary check includes a message consistency check.

7. The method according to claim 1, wherein, The second V2X source is a roadside unit.

8. The method of claim 1, wherein the sensor fusion process includes accessing a shared memory through multiple electronic control units.

Images