Managing vehicle behavior based on the predicted behavior of other vehicles

Abstract

Various embodiments include methods and systems for managing vehicle behavior. In some embodiments, a vehicle processor of a first vehicle can receive dynamic traffic flow feature information related to movement of a second vehicle within a predetermined proximity to a host vehicle, determine probabilities of multiple potential behaviors of the second vehicle based on the received dynamic traffic flow feature information, predict a future path of the second vehicle, and use the predicted future path of the second vehicle in vehicle control functions. In some embodiments, a vehicle processor of the first vehicle can predict a behavior of a third vehicle based on the received intent information for the second vehicle, and adjust the behavior of the first vehicle based on the predicted behavior of the third vehicle.

Description

[Technical field]

[0001] Related Applications

[0001] This application claims the benefit of priority from U.S. Non-Provisional Patent Application No. 17 / 455,853, filed November 19, 2021, the entire contents of which are incorporated herein by reference. [Background technology]

[0002]

[0002] Standards and protocols for Intelligent Transportation Systems (ITS) supported by next-generation 5G NR communication systems are under development. Appropriately configured devices of vehicles and pedestrians can participate in the ITS by sending and receiving vehicle-to-everything (V2X) messages, such as Basic Safety Messages (BSMs), that contain information about the current and / or future behavior of the ITS participants, enabling other ITS participants to operate more safely. However, while autonomous vehicles can receive information, perform route planning, and make steering decisions very quickly, they may be limited to reacting to information perceived from the environment and / or information received from other vehicles (e.g., BSMs). Summary of the Invention

[0003]

[0003] Various aspects include a method of managing vehicle behavior performed by a vehicle processing system, such as a vehicle-to-everything (V2X) processing device. Various aspects may include receiving, by a first vehicle (also referred to as a host vehicle), dynamic traffic flow feature information related to movement of a second vehicle within a predetermined proximity to the first vehicle, determining probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow feature information, each of the plurality of potential behaviors taking into account the received dynamic traffic flow feature information, predicting a future path of the second vehicle based on the determined probabilities of the plurality of potential behaviors of the second vehicle, and using the predicted future path of the second vehicle in a vehicle control function.

[0004]

[0004] Some aspects may include receiving additional vehicle dynamic traffic flow characteristic information indicative of a movement of a third vehicle within a predetermined proximity to the first vehicle. In such aspects, determining probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information may include determining probabilities of a plurality of potential behaviors of the second vehicle taking into account the additional vehicle dynamic traffic flow characteristic information. In some aspects, using the predicted future path of the second vehicle in a vehicle control function includes adjusting a behavior of the first vehicle.

[0005] Some aspects may include receiving a probability of a potential behavior of a third vehicle from a vehicle-to-everything (V2X) resource remote from the first vehicle. In such aspects, determining the probability of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information may include determining the probability of a plurality of potential behaviors of the second vehicle taking into account the received probability of the potential behavior of the third vehicle. In some aspects, the plurality of potential behaviors of the second vehicle may include two or more route options available to the second vehicle.

[0006]

[0006] Some aspects may include receiving historical information regarding vehicle behavior in an area traveled by the first vehicle. In such aspects, determining probabilities of a plurality of potential behaviors of the second vehicle may include determining probabilities of a plurality of potential behaviors of the second vehicle based on the received historical information. In some aspects, receiving dynamic traffic flow characteristic information may further include receiving a probability for each of a plurality of route options available to the second vehicle from a database and receiving observational information related to movement of the second vehicle from a sensor. In some aspects, the received dynamic traffic flow characteristic information may be received via vehicle-to-everything (V2X) communication.

[0007] In some aspects, determining probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow feature information may include determining probabilities of a plurality of potential behaviors of the second vehicle based on updated map feature information included in the received dynamic traffic flow feature information. In some aspects, determining probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow feature information may include determining probabilities of a plurality of potential behaviors of the second vehicle using at least one of a regression model or a classification model for predicted movements of vehicles surrounding the first vehicle.

[0008]

[0008] A further aspect includes a vehicle processing system including a memory and a processor configured to perform operations of any of the methods summarized above. A further aspect may include a vehicle processing system having various means for performing functions corresponding to any of the methods summarized above. A further aspect may include a non-transitory processor-readable storage medium having stored thereon processor-executable instructions configured to cause a processor of the vehicle processing system to perform various operations corresponding to any of the methods summarized above. [Brief description of the drawings]

[0009]

[0009] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the claims and, together with the provided schematic description and "Form for implementing the invention," serve to explain features herein. [Figure 1A]

[0010] FIG. 1 is a system block diagram illustrating an example V2X system suitable for implementing various embodiments. [Figure 1B]

[0011] FIG. 1 is a conceptual diagram illustrating an example V2X communication protocol stack suitable for implementing various embodiments. [Diagram 2]

[0012] FIG. 1 is a component diagram of an exemplary vehicle system suitable for implementing various embodiments. [Diagram 3]

[0013] FIG. 1 is a component block diagram illustrating a system configured to perform operations for managing vehicle behavior, in accordance with various embodiments. [Figure 4A]

[0014] FIG. 1 is a conceptual diagram illustrating an environment in which a processor in a vehicle can use predicted future paths of one or more other vehicles to manage vehicle behavior, according to various embodiments. [Figure 4B] FIG. 1 is a conceptual diagram illustrating an environment in which a processor in a vehicle can use predicted future paths of one or more other vehicles to manage vehicle behavior, according to various embodiments. [Figure 4C]

[0015] FIG. 1 is a system block diagram illustrating aspects of a forecasting system suitable for implementing various embodiments. [Figure 5A]

[0016] FIG. 5 is a process flow diagram of an example method 500a for managing vehicle behavior, according to various embodiments. [Figure 5B]

[0017] 5 is a process flow diagram of example operations 500b-500e that may be performed as part of a method 500a for managing vehicle behavior, according to various embodiments. [Figure 5C]5 is a process flow diagram of example operations 500b-500e that may be performed as part of a method 500a for managing vehicle behavior, according to various embodiments. [Figure 5D] 5 is a process flow diagram of example operations 500b-500e that may be performed as part of a method 500a for managing vehicle behavior, according to various embodiments. [Figure 6A]

[0018] FIG. 2 is a process flow diagram of an exemplary method for managing vehicle behavior, according to various embodiments. [Figure 6B]

[0019] FIG. 2 is a process flow diagram of example operations that may be performed as part of a method for managing vehicle behavior, according to various embodiments. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0010]

[0020] Various embodiments are described in detail with reference to the accompanying drawings. Wherever possible, the same reference numbers are used throughout the drawings to refer to the same or like parts. References made to specific examples and implementations are for illustrative purposes only and do not limit the scope of the claims.

[0011]

[0021] Various embodiments include methods and mechanisms for managing vehicle behavior based on traffic flow due to dynamic traffic flow characteristics and behavior of other vehicles. Various embodiments enable a vehicle processor (e.g., a V2X processor, processing device, or processing system) to predict future behavior of other vehicles and perform vehicle control functions or adjust vehicle behavior based on the predicted behavior of the other vehicles. In various embodiments, a vehicle processor of a host vehicle (referred to as the first vehicle in the claims and in some descriptions herein) may receive dynamic traffic flow characteristic information related to the movement of a second vehicle within a predetermined proximity to the host vehicle. The vehicle processor may determine probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information, each of the plurality of potential behaviors taking into account the received dynamic traffic flow characteristic information. Based on the determined probabilities of the plurality of potential behaviors of the second vehicle, the vehicle processor may predict a future path of the second vehicle and may use the predicted future path of the second vehicle in vehicle control functions. In various embodiments, a vehicle processor of a host vehicle may receive intent information of the second vehicle indicating an intended behavior of the second vehicle. The vehicle processor can predict a behavior of the third vehicle based on the received intent information of the second vehicle. The vehicle processor can adjust a behavior of the host vehicle based on the predicted behavior of the third vehicle.

[0012]

[0022] As used herein, a “vehicle” generally refers to a sender and / or receiver of a V2X message in an ITS, such as a car, truck, bus, train, boat, pedestrian, bicycle, motorcycle, scooter, any other type of ITS station, or any other suitable ITS participant type.

[0013]

[0023] The term "system on chip" (SOC) is used herein to refer to a single integrated circuit (IC) chip that includes multiple resources and / or processors integrated on a single substrate. A single SOC may include circuits for digital, analog, mixed signal, and radio frequency functions. A single SOC may also include any number of general purpose and / or special purpose processors (digital signal processors, modem processors, video processors, etc.), memory blocks (e.g., ROM, RAM, Flash, etc.), and resources (e.g., timers, voltage regulators, oscillators, etc.). A SOC may also include software for controlling the integrated resources and processors as well as for controlling peripheral devices.

[0014]

[0024] The term "system in a package" (SIP) may be used herein to refer to a single module or package that contains multiple resources, computing units, cores, and / or processors on two or more IC chips, substrates, or SOCs. For example, a SIP may include a single substrate on which multiple IC chips or semiconductor dies are stacked in a vertical configuration. Similarly, a SIP may include one or more multi-chip modules (MCMs) on which multiple ICs or semiconductor dies are packaged in a singulated substrate. A SIP may also include multiple independent SOCs packaged in close proximity, coupled to each other via high-speed communication circuits, such as on a single motherboard or within a single wireless device. The proximity of the SOCs facilitates high-speed communication and sharing of memory and resources.

[0015]

[0025] As used herein, the terms "network," "system," "wireless network," "cellular network," and "wireless communications network" may interchangeably refer to some or all of a wireless network of a carrier associated with a wireless device and / or a subscription on a wireless device. The techniques described herein may be used for various wireless communications networks, such as Code Division Multiple Access (CDMA), Time Division Multiple Access (TDMA), FDMA, Orthogonal FDMA (OFDMA), Single Carrier FDMA (SC-FDMA), and other networks. In general, any number of wireless networks may be deployed in a given geographic area. Each wireless network may support at least one radio access technology that may operate on one or more frequencies or ranges of frequencies. For example, a CDMA network may implement Universal Terrestrial Radio Access (UTRA) (including the Wideband Code Division Multiple Access (WCDMA) standard), CDMA2000 (including the IS-2000, IS-95, and / or IS-856 standards), and the like. In another example, the TDMA network may implement GSM Enhanced Data Rates for GSM Evolution (EDGE). In another example, the OFDMA network may implement Evolved UTRA (E-UTRA) (including the LTE standard), Institute of Electrical and Electronics Engineers (IEEE) 802.11 (Wi-Fi), IEEE 802.16 (WiMAX), IEEE 802.20, Flash-OFDM, etc. Reference may be made to wireless networks using the LTE standard, and thus the terms "Universal Terrestrial Radio Access," "E-UTRAN," and "eNodeB" may also be used interchangeably herein to refer to wireless networks. However, such references are provided by way of example only and do not exclude wireless networks using other communication standards.For example, although various third generation (3G), fourth generation (4G), and fifth generation (5G) systems are described herein, these systems are mentioned by way of example only and future generation systems (e.g., sixth generation (6G) or higher systems) may be used instead in various instances.

[0016]

[0026] Standards for vehicle-based communication systems and functions are under development in several regions of the world, such as those developed by the Institute of Electrical and Electronics Engineers (IEEE) and the Society of Automotive Engineers (SAE) for use in North America, and the European Telecommunications Standards Institute (ETSI) and the European Committee for Standardization (CEN) for use in Europe. The IEEE 802.11p standard is the basis for the Dedicated Short Range Communication (DSRC) and ITS-G5 communication standards. IEEE 1609 is a higher-level standard based on IEEE 802.11p. The Cellular Vehicle-to-Everything (C-V2X) standard is a competing standard developed under the auspices of the 3rd Generation Partnership Project. These standards serve as the foundation for vehicle-based wireless communications and can be used to support intelligent highways, autonomous and semi-autonomous vehicles, and improve the overall efficiency and safety of highway transportation systems. Other V2X wireless technologies are also being considered in multiple different regions of the world. The techniques described herein are applicable to any V2X wireless technology.

[0017]

[0027] The C-V2X protocol specifies two transmission modes that together provide 360° non-line-of-sight awareness and higher levels of predictability for enhanced road safety and autonomous driving. The first transmission mode includes Direct C-V2X, which includes vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), and vehicle-to-pedestrian (V2P) communications and provides extended communication range and reliability in a dedicated Intelligent Transportation Systems (ITS) 5.9 gigahertz (GHz) spectrum that is independent of cellular networks. The second transmission mode includes vehicle-to-network (V2N) communications in mobile broadband systems and technologies, such as third generation wireless mobile communications technologies (3G) (e.g., Global System for Mobile Communications (GSM) Evolution (EDGE) systems, Code Division Multiple Access (CDMA) 2000 systems, etc.), fourth generation wireless mobile communications technologies (4G) (e.g., Long Term Evolution (LTE) systems, LTE-Advanced systems, Mobile Worldwide Interoperability for Microwave Access (Mobile WiMAX) systems, etc.), fifth generation new radio wireless mobile communications technologies (5G NR systems, etc.). The processing of such messages in the transmitting and receiving vehicles may be performed by a processor or processing system (referred to herein as a "vehicle processor") of an onboard device that provides a vehicle-to-everything communications (V2X) function.

[0018]

[0028] V2X systems and technologies hold great promise for improving traffic flow and vehicle safety by allowing vehicles to share information about their location, speed, heading, braking, and other factors that may be useful to other vehicles for collision avoidance and other safety functions. An element of a V2X system is the ability for vehicles to broadcast V2X information, such as Basic Safety Messages (BSM) or Cooperative Awareness Messages (CAM), in V2X messages that other vehicles can receive and process to improve road safety. Vehicles can transmit V2X messages frequently, up to 20 times per second in some implementations. With most or all vehicles transmitting V2X information, the receiving vehicle can receive information from the other vehicles and control its own speed, direction, steering, route planning, etc., to avoid collisions and efficiently and safely position vehicles relative to each other. Furthermore, V2X-equipped vehicles may be able to improve traffic flow by safely reducing separation distances, platooning several vehicles together, and avoiding vehicles experiencing malfunctions.

[0019]

[0029] Although an autonomous vehicle can receive information, perform route planning, and make maneuvering decisions very quickly, the autonomous vehicle may be limited to reacting to information sensed from the environment and / or received from other vehicles (e.g., BSM). Predicting the behavior of other vehicles is a challenge for the vehicle processor. The vehicle processor may receive information about other vehicles from sensors (e.g., cameras, radar, lidar, etc.). The vehicle processor may also receive access to a map of the environment, which in some implementations may be an information-rich map, such as a high-definition (HD) map. The vehicle processor may also receive location information from a positioning system or a communication network.

[0020]

[0030] The vehicle processor may be configured to use various such information to predict, for example, the future behavior of other vehicles over a short period of time (e.g., seconds or minutes). Such behavior prediction may enable the vehicle processor to make safe operating decisions (such as maneuvering, path planning, and subsystem selection) and utilize computational resources more efficiently. However, conventional approaches are limited to making predictions over short periods of time and using information received from or perceived about other vehicles. In some implementations, the short-term prediction problem may be addressed as a regression problem in which the vehicle processor estimates the location of one or more neighboring vehicles and their states and interactions over the next few seconds, or as a classification problem in which the vehicle processor estimates the behavioral intent of one or more other vehicles, such as whether the vehicle plans to make a left lane change, a right lane change, accelerate, decelerate, etc.

[0021]

[0031] Some conventional approaches can predict other vehicle behavior over short periods of time by designing a rasterized view of the environment and applying trained neural networks. Many classification behavior prediction techniques use perceived features (e.g., received by vehicle sensors), such as lateral distance, distance from a boundary, blinker observation from the senses, lateral speed, other vehicle positions, map cues such as road curvature, and the presence of lane information (to the left or right). As mentioned above, a vehicle can typically make such observations (e.g., via one or more sensors) over a short period of time (e.g., a 5-second observation window). However, conventional approaches typically do not take advantage of long-term temporal cues presented by traffic flow or determinable from the environment, such as upcoming road teachers, structure, configuration, and / or other conditions. Given the safety-critical nature of autonomous vehicle behavior, early prediction of other vehicle behavior with low computational overhead can improve driving decisions made by the vehicle processor, improve the overall quality of driving, and help prevent catastrophic accidents.

[0022]

[0032] Various embodiments include methods and mechanisms for managing vehicle behavior that enable a vehicle processor (e.g., a V2X processor, processing device, or processing system) to predict future behavior of other vehicles and perform vehicle control functions or adjust vehicle behavior based on the predicted behavior of the other vehicles.

[0023]

[0033] Various embodiments may use behavior prediction of other vehicles to control the host vehicle. Behavior prediction may include predicted future paths of other vehicles within a given proximity to the host vehicle (also referred to as the first vehicle), such as lane changing, lane keeping, acceleration, deceleration, combinations thereof, etc. Human decision-making processes generally determine future possibilities and outcomes based on known and / or observable information. In the context of autonomous vehicle (AV) systems, similar decisions regarding future possibilities and outcomes may enable AV systems to predict future states of other vehicles, which are required for path planning, collision avoidance, and overall vehicle safety. Using a combination of sensory inputs, positioning inputs, and map data may enable behavior prediction of other vehicles by the AV system. Such behavior prediction may enable the AV system to plan ahead, allocate computational resources, and / or switch between different subsystems to effectively predict the behavior of other vehicles and determine vehicle maneuvers and path planning accordingly.

[0024]

[0034] Various embodiments include a method performed by a processor of a host vehicle that predicts a future path of another vehicle (e.g., a second vehicle, a third vehicle, etc.) within a predetermined proximity to the host vehicle based on dynamic traffic flow feature information associated with the movement of the other vehicle. Based on the received dynamic traffic flow feature information, the vehicle processor can determine probabilities of a plurality of potential behaviors of the other vehicle. In determining each of the plurality of potential behaviors, the vehicle processor may take into account the received dynamic traffic flow feature information. Based on the determined probabilities of the plurality of potential behaviors of the second vehicle, the vehicle processor can predict a future path of the second vehicle and use the predicted future path of the second vehicle in vehicle control functions, such as generating commands to perform or modify a vehicle maneuver, performing or updating a route plan, adjusting a behavior of the host vehicle, etc.

[0025]

[0035] Some embodiments may include the vehicle processor receiving additional vehicle dynamic traffic flow characteristic information indicative of a movement of a third vehicle within a predetermined proximity to the host vehicle. The vehicle processor may determine probabilities of a plurality of potential behaviors of the second vehicle by considering the additional vehicle dynamic traffic flow characteristic information.

[0026]

[0036] Some embodiments may include a vehicle processor receiving probabilities of potential behaviors of the third vehicle from a vehicle-to-everything (V2X) resource remote from the host vehicle and determining probabilities of multiple potential behaviors of the second vehicle taking into account the received probabilities of the potential behaviors of the third vehicle. In some embodiments, the multiple potential behaviors of the second vehicle may include two or more route options available to the second vehicle.

[0027]

[0037] Some embodiments may include a vehicle processor receiving historical information regarding vehicle behavior within an area traveled by the host vehicle and determining probabilities of a plurality of potential behaviors of the second vehicle based on the received historical information.

[0028]

[0038] Some embodiments may further include the vehicle processor receiving or retrieving from a database a probability for each of a plurality of route options available to the second vehicle, receiving observational information from a sensor related to movement of the second vehicle, such as via vehicle-to-everything (V2X) communications, and determining probabilities of a plurality of potential behaviors of the second vehicle based on updated map feature information included in the received dynamic traffic flow feature information. In some embodiments, the vehicle processor may determine probabilities of a plurality of potential behaviors of the second vehicle using at least one of a regression model or a classification model for predicted movement of vehicles surrounding the host vehicle.

[0029]

[0039] Various embodiments include a method performed by a vehicle processor of a host vehicle (also referred to as a first vehicle) to manage the behavior of the host vehicle. In various embodiments, the vehicle processor of the host vehicle may receive second vehicle intent information indicating the intended behavior of the second vehicle. The host vehicle processor may predict the behavior of a third vehicle based on the received second vehicle intent information. Based on the predicted behavior of the third vehicle, the host vehicle processor may adjust the behavior of the host (i.e., first) vehicle.

[0030]

[0040] In some embodiments, the vehicle processor may use information received (e.g., from another vehicle) or perceived (e.g., via sensors) to perform such predictions. In some embodiments, the vehicle processor may determine a "social context" to facilitate prediction of vehicle behavior. The vehicle processor may build a rich information context including information received (e.g., from another vehicle) or perceived (e.g., via sensors), HD map information, environmental information observed during driving, etc. The vehicle processor may also incorporate information about changes in traffic conditions or traffic flow, such as average lane speed(s), lane changes, braking behavior, acceleration behavior, traffic exits, traffic ingresses, etc. The vehicle processor may also incorporate information about changes in the driving environment, such as lane closures, accidents, the presence of emergency vehicles, etc., that may affect the behavior of other vehicles and / or traffic flow (e.g., from a closed lane to an open lane). In some embodiments, the vehicle processor may scale up the lane change probability or sample from the lane change trajectory distribution.

[0031]

[0041] In some embodiments, the vehicle processor may apply one or more prediction or planning algorithms to predict the behavior of the third vehicle. In some embodiments, the vehicle processor may perform different prediction calculations based on the priority and / or map information assigned to the second or third vehicle. For example, vehicles within a distance threshold from the host vehicle, e.g., vehicles immediately before, immediately after, or beside the host vehicle, may be assigned a relatively high priority, and vehicles further away from the host vehicle (e.g., beyond the distance threshold) may be assigned a lower priority. In some embodiments, for vehicles assigned a relatively high priority, the vehicle processor may apply a prediction algorithm to predict the behavior of such vehicles. In some embodiments, for vehicles assigned a lower priority, the vehicle processor of the host vehicle may query another vehicle, a roadside unit, and / or another network element for prediction information regarding such vehicles. In some embodiments, the prediction or planning algorithms may be distributed among vehicles and / or network elements, such as roadside units. For example, a common process or procedure, such as map feature extraction, may be distributed among different vehicles, network elements, etc., even though different vehicles and / or network elements may employ different prediction algorithms, computing infrastructure, etc.

[0032]

[0042] In some embodiments, the vehicle processor of the host vehicle may receive V2X information from the second vehicle, the V2X information including the intent information of the second vehicle. In some embodiments, the vehicle processor of the host vehicle may receive dynamic traffic flow characteristic information associated with the second vehicle and predict a behavior of the third vehicle based on the dynamic traffic flow characteristic information associated with the second vehicle.

[0033]

[0043] In some embodiments, the vehicle processor can generate vehicle motion commands to cause the vehicle to execute a maneuver based on the predicted behavior of the third vehicle. In some embodiments, the vehicle processor can generate vehicle motion commands to modify an ongoing maneuver based on the predicted behavior of the third vehicle. In some embodiments, the vehicle processor can adjust a planned travel path based on the predicted behavior of the third vehicle.

[0034]

[0044] For ease of reference, some embodiments are described herein with reference to a host vehicle (also referred to herein as a first vehicle) using a particular V2X system, device, and / or protocol. However, it should be understood that various embodiments encompass any or all of V2X or vehicle-based communication standards, devices, messages, protocols, and / or techniques. Thus, the description of various embodiments should not be construed to limit the claims to a particular system (e.g., V2X) or message or messaging protocol (e.g., BSM or CAM) unless expressly recited as such in the claims. In addition, embodiments described herein may refer to a V2X processing system in a vehicle. Other embodiments are contemplated in which a V2X processing system may operate in or be included in mobile devices, mobile computers, roadside units (RSUs), and other devices equipped to monitor road and vehicle conditions and participate in V2X communications.

[0035]

[0045] FIG 1A is a system block diagram illustrating an example V2X system 100 suitable for implementing various embodiments. FIG 1B is a conceptual diagram illustrating an example V2X communication protocol stack 150 suitable for implementing various embodiments. With reference to FIG 1A and FIG 1B, vehicles 12, 14, 16 may each include a vehicle processor 102, 104, 106 (e.g., a V2X processing device such as V2X on-board equipment) that may be configured to periodically broadcast V2X messages (e.g., BSM, CAM) 112, 114, 116 for receipt and processing by processing systems (e.g., 102, 104, 106) of other vehicles.

[0036]

[0046] By sharing vehicle location, speed, direction, behavior (e.g., braking), and other information, the vehicles can maintain a safe separation and identify and avoid potential collisions. For example, a following vehicle 12 receiving a V2X message 114 from a leading vehicle 16 can determine the speed and location of the vehicle 16, allowing the following vehicle 12 to match the leading vehicle's speed and maintain a safe separation distance 20. By being notified through the V2X message 114 when the leading vehicle 16 applies its brakes, the vehicle processor 102 in the following vehicle 12 can simultaneously apply the brakes to maintain the safe separation distance 20, even if the leading vehicle 16 suddenly stops. As another example, the vehicle processor 104 in the truck vehicle 14 can receive V2X messages 112, 116 from two vehicles 12, 16 and thus be notified that the truck vehicle 14 should stop at an intersection to avoid a collision. Additionally, each of the vehicle processors 102, 104, 106 can communicate with each other using any of a variety of very close communication protocols.

[0037]

[0047] Additionally, the vehicles 12, 14, 16 may be capable of transmitting data and information related to V2X messages to various network elements 132, 134, 136 over the communications network 18 (e.g., V2X, cellular, Wi-Fi, etc.) via communications links 122, 124, 146. For example, the network elements 132 may be incorporated into or in communication with the RSUs, gantry units, etc. The network elements 134, 136 may be configured to perform functions or services related to the vehicles 12, 14, 16, such as payment processing, road condition monitoring, emergency provider message processing, etc. The network elements 134, 136 may be configured to communicate with each other via wired or wireless networks 142, 144 to exchange information related to payment processing, road condition monitoring, emergency provider message processing, and similar services.

[0038]

[0048] FIG. 2 is a component diagram of an exemplary vehicle system 200 suitable for implementing various embodiments. With reference to FIGS. 1A-2, the system 200 can include a first vehicle 202 (e.g., a host vehicle) including a vehicle processing system 204, such as a V2X processing device, such as a telematics control unit or on-board unit (TCU / OBU). The vehicle processing system 202 can communicate with various systems and devices, such as an in-vehicle network 210, an infotainment system 212, various sensors 214, various actuators 216, and a wireless module 218. The vehicle processing system 202 can also communicate with various one or more other vehicles 220, a roadside unit 222, a base station 224, and other external devices. The vehicle processing system 204 can be configured to perform operations of fraud detection, as described further below. The first vehicle 202 and the one or more other vehicles 220 can include elements of and operate similarly to the vehicles (e.g., 12, 14, 16) described with respect to FIG. 1A.

[0039]

[0049] The vehicle processing system 204 may include a processor 205, a memory 206, an input module 207, an output module 208, and a wireless module 218. The processor 205 may be coupled to the memory 206 (i.e., a non-transitory storage medium) and may be configured with processor-executable instructions stored in the memory 206 for performing operations of methods according to various embodiments described herein. The processor 205 may also be coupled to an output module 208, which may control an in-vehicle display, and an input module 207 for receiving information from vehicle sensors and driver inputs.

[0040]

[0050] Vehicle processing system 204 may include a V2X antenna 219 coupled to a radio module 218 configured to communicate with one or more other vehicles 220, roadside units 222, and one or more ITS participants (e.g., stations), such as a base station 224 or another suitable network access point. V2X antenna 219 and radio module 218 may be configured to receive dynamic traffic flow characteristic information via vehicle-to-everything (V2X) communications. In various embodiments, vehicle processing system 204 may receive information from multiple sources, such as in-vehicle network 210, infotainment system 212, various sensors 214, various actuators 216, and radio module 218. Vehicle processing system 204 may be configured to detect fraudulent behavior in V2X messages from an ITS participant (e.g., another vehicle), as described further below.

[0041]

[0051] Examples of in-vehicle networks 210 include a Controller Area Network (CAN), a Local Interconnect Network (LIN), a network using the FlexRay protocol, a Media Oriented Systems Transport (MOST) network, and an in-vehicle Ethernet network. Examples of vehicle sensors 214 include location determination systems (such as Global Navigation Satellite Systems (GNSS) systems), cameras, radar, lidar, ultrasonic sensors, infrared sensors, and other suitable sensor devices and systems. Examples of vehicle actuators 216 include various physical control systems such as steering, braking, engine operation, lights, turn signals, etc.

[0042]

[0052] 3 is a component block diagram illustrating a system 300 configured to perform operations to manage vehicle behavior, according to various embodiments. With reference to FIGS. 1A-3, the system 300 may include a vehicle processing system 204 of a host vehicle (e.g., vehicle 202 of FIG. 2), one or more other vehicles 220, a roadside unit 222, and / or a base station 224.

[0043]

[0053] Vehicle processing system 204 may include one or more processors 205, memory 206, wireless module 218, and other components. Vehicle processing system 204 may include multiple hardware, software, and / or firmware components that operate together to provide the functionality attributed to processor 205 herein.

[0044]

[0054] Memory 206 may include non-transitory storage media that electronically store information. The electronic storage media of memory 206 may include one or both of system storage that is integral with vehicle processing system 204 (i.e., substantially non-removable) and / or removable storage that is removably connectable to vehicle processing system 204, for example, via a port (e.g., a Universal Serial Bus (USB) port, a Firewire port, etc.) or a drive (e.g., a disk drive, etc.). In various embodiments, memory 206 may include one or more of a charge-based storage medium (e.g., EEPROM, RAM, etc.), a solid-state storage medium (e.g., flash drive, etc.), an optically readable storage medium (e.g., optical disk, etc.), a magnetically readable storage medium (e.g., magnetic tape, magnetic hard drive, floppy drive, etc.), and / or other electronically readable storage medium. Memory 206 may include one or more virtual storage resources (e.g., cloud storage, a virtual private network, and / or other virtual storage resources). The memory 206 may store software algorithms, information determined by the processor(s) 205, information received from one or more other vehicles 220, information received from the roadside unit 222, information received from the base station 224, and / or other information that enables the vehicle processing system 204 to function as described herein.

[0045]

[0055] The processor(s) 205 may include one or more local processors that may be configured to provide information processing capabilities in the vehicle processing system 204. Thus, the processor(s) 205 may include one or more of a digital processor, an analog processor, a digital circuit designed to process information, an analog circuit designed to process information, a state machine, and / or other mechanisms for electronically processing information. Although the processor(s) 205 is shown in FIG. 3 as a single entity, this is for illustrative purposes only. In some embodiments, the processor(s) 205 may include multiple processing units. These processing units may be physically located within the same device, or the processor(s) 205 may represent the processing functions of multiple devices operating in concert.

[0046]

[0056] The vehicle processing system 204 may be configured with machine-readable instructions 320, which may include one or more instruction modules. The instruction modules may include computer program modules. In various embodiments, the instruction modules may include one or more of a traffic movement feature module 322, a behavior probability module 324, a behavior prediction module 326, a behavior adjustment module 328, and / or other modules.

[0047]

[0057] The traffic flow feature module 322 may be configured to receive dynamic traffic flow feature information related to the movement of a second vehicle within a predetermined proximity to the host vehicle. The dynamic traffic flow feature information related to the movement of the second vehicle received by the traffic flow feature module 322 may include the closest distance and / or other distance to the host vehicle, the distance of the second vehicle from the lane center (Dlat), the derivative of Dlat (Vlat), acceleration / deceleration, speed, heading, etc. In addition, the predetermined proximity to the host vehicle may be within a preset distance from the host vehicle in its vicinity. For example, the predetermined distance may be within the range of a dedicated short-range communication used to exchange BSMs (e.g., about 1000 m). Alternatively, a shorter or longer distance may be used as the predetermined distance by the traffic flow feature module 322.

[0048]

[0058] The traffic flow feature module 322 may be configured to receive additional vehicular dynamic traffic flow feature information indicative of the movement of one or more other vehicles (e.g., a third vehicle) within a predetermined proximity to the host vehicle. The additional vehicular dynamic traffic flow feature information related to the one or more other vehicles received by the traffic flow feature module 322 may include closest distance and / or other distance to the host vehicle and / or the second vehicle, the distance of the other vehicle from the lane center (Dlat), derivative of Dlat (Vlat), acceleration / deceleration, speed, heading, etc.

[0049]

[0059] The traffic flow features module 322 may be configured to receive historical information regarding vehicle behavior within an area traveled by the host vehicle. For example, the historical information received by the traffic flow features module 322 may include information regarding vehicle traffic path (e.g., lane changes or lane keeping), speed, acceleration / deceleration, density, proximity, etc., including specific locations on roads associated with the historical information. The traffic flow features module 322 may be configured to receive a probability for each of a plurality of route options available to the second vehicle from a database. The probability for each of a plurality of route options received by the traffic flow features module 322 may reflect the degree of likelihood of something happening, the likelihood that each route option will occur, or the circumstances under which such a situation exists.

[0050]

[0060] The traffic flow features module 322 may be configured to receive (e.g., from a sensor) observational information related to the movement of the second vehicle. The observational information may include the action or process of closely observing the second vehicle to obtain information related to the movement of the second vehicle. For example, the observational information may include the closest and / or other distances of the second vehicle to the host vehicle, the distance of the second vehicle from the lane center (Dlat), the derivative of Dlat (Vlat), acceleration / deceleration, speed, heading, etc.

[0051]

[0061] The traffic flow features module 322 may be configured to receive intent information of the second vehicle (e.g., within or together with the V2X information) indicating the intended behavior of the second vehicle.

[0052]

[0062] The behavior probability module 324 may be configured to determine a probability of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information. The behavior probability module 324 may be configured to take into account the dynamic traffic flow characteristic information received by the traffic flow characteristic module 322 in determining the probability of the plurality of potential behaviors. The behavior probability module 324 may be configured to determine the probability of a plurality of potential behaviors of the second vehicle taking into account the additional vehicle dynamic traffic flow characteristic information. The behavior probability module 324 may be configured to receive a probability of a potential behavior of at least one third vehicle from a V2X resource away from the host vehicle. The behavior probability module 324 may be configured to determine the probability of a plurality of potential behaviors of the second vehicle taking into account the received probability of the potential behavior of the at least one third vehicle. The behavior probability module 324 may be configured to determine the probability of a plurality of potential behaviors of the second vehicle based on the received historical information. The behavior probability module 324 may be configured to determine probabilities of multiple potential behaviors of the second vehicle based on updated map feature information included in the received dynamic traffic flow feature information. For example, the updated map feature information may identify lane closures / blockages, obstacles, hazards, road / lane changes, etc. The behavior probability module 324 may be configured to determine probabilities of multiple potential behaviors of the second vehicle using at least one of a regression model or a classification model for the predicted movement of vehicles surrounding the host vehicle.

[0053]

[0063] The behavior prediction module 326 may be configured to predict a future path of the second vehicle based on the determined probabilities of multiple potential behaviors of the second vehicle. The behavior prediction module 326 may be configured to determine an intent of the second vehicle, such as whether the vehicle is about to perform a lane change, lane keeping, turn, accelerate, decelerate, etc., and use such intent in predicting the future path of the second vehicle. The behavior prediction module 326 may be configured to determine multiple route options available to the second vehicle.

[0054]

[0064] The behavior prediction module 326 may be configured to predict a behavior of a third vehicle based on the dynamic traffic flow characteristic information associated with the second vehicle.

[0055]

[0065] The behavior adjustment module 328 may be configured to use the future path of the second vehicle predicted by the behavior prediction module 326 in a vehicle control function. As used herein, the term "vehicle control function" may include generating a path plan and / or commands for execution by a vehicle control system to perform or adjust a maneuver, alert a driver in the vehicle, or a combination thereof. The behavior adjustment module 328 may be configured to generate commands for execution by the vehicle control system to perform a maneuver, such as accelerating, decelerating, and / or turning, to avoid or reduce the possibility of a collision with another vehicle, based on the predicted behavior of the third vehicle. The behavior adjustment module 328 may be configured to generate commands to be executed by the vehicle control system to modify an ongoing maneuver, based on the predicted behavior of the third vehicle. The behavior adjustment module 328 may be configured to adjust the behavior of the host vehicle, such as updating or modifying a planned driving path, based on the predicted behavior of the third vehicle.

[0056]

[0066] The processor(s) 205 may be configured to execute modules 322-328 and / or other modules via software, hardware, firmware, any combination of software, hardware, and / or firmware, and / or other mechanisms that configure processing power on the processor(s) 205.

[0057]

[0067] The description of the functionality provided by the various modules 322-328 is for purposes of example and is not intended to be limiting, as any of the modules 322-328 may provide more or less functionality than described. For example, one or more of the modules 322-328 may be excluded, with some or all of its functionality being provided by others of the modules 322-328. As another example, the processor(s) 205 may be configured to execute one or more additional modules that may perform some or all of the functionality attributed to one of the following modules 322-328:

[0058]

[0068] 4A and 4B are conceptual diagrams illustrating environments 400a and 400b in which a processor of a host vehicle can use predicted future paths of other vehicles to manage vehicle behavior, according to various embodiments. FIG. 4C is a system block diagram illustrating aspects of a prediction system 400c suitable for implementing various embodiments. With reference to FIGS. 1A-4C, the operations described with respect to the vehicles in environments 400a and 400b may be performed by a vehicle processing system or vehicle processor or V2X processing device (e.g., vehicle processor 102, 104, 106, 204), which may be implemented in hardware elements, software elements, or a combination of hardware and software elements (collectively referred to as a "vehicle processing system" or "vehicle processor").

[0059]

[0069] 4A, an environment 400a includes a road 410 having four lanes A, B, C, D merging into two center lanes B, C. In the example shown in FIG. 4A, a host vehicle 420 (i.e., the host vehicle) is operating in a third lane C, with a number of other vehicles 431-437 on the road 410 in relatively close proximity. The host vehicle 420 may include elements of and / or operate similarly to the vehicles (e.g., 12, 14, 16, 202, 220) described with respect to FIGS. 1A and 2.

[0060]

[0070] According to various embodiments, the processor of the host vehicle 420 may predict a future path of the second vehicle 431 traveling in the fourth lane D. In particular, the processor of the host vehicle 420 may predict the future path of the second vehicle 431 based on determined probabilities of a plurality of potential behaviors of the second vehicle 431. The determined probabilities of a plurality of potential behaviors of the second vehicle 431 may be determined based on received dynamic traffic flow characteristic information related to the movement of the second vehicle 431, such as lane convergence as illustrated, other vehicles reacting to such flow characteristics, etc. The processor may take the received dynamic traffic flow characteristic information into account in determining the plurality of potential behaviors. For example, the processor may predict the future path of the second vehicle 431 due to the proximity of the second vehicle 431 to the host vehicle 420, in particular because the second vehicle 431 is within a predetermined proximity to the host vehicle 420. Additionally, the processor may predict a future path of the second vehicle 431 in response to dynamic traffic flow feature information related to the movement of the second vehicle 431 received by the host vehicle 420. In response to predicting the future path of the second vehicle 431 (e.g., a lane change from the fourth lane D to the third lane C), the processor of the host vehicle 420 may use the predicted future path of the second vehicle 431 in vehicle control functions. For example, the vehicle control functions may instruct the host vehicle 420 to slow down, maintain speed, change lanes, etc.

[0061]

[0071] In some embodiments, the processor of the host vehicle 420 may receive additional vehicle dynamic traffic flow feature information indicative of the movement of the third vehicle 432 within a predetermined proximity to the host vehicle 420. The movement of the third vehicle 432 in the fourth lane D ahead of the second vehicle 431 may affect how and / or when the second vehicle 431 behaves. For example, the additional vehicle dynamic traffic flow feature information may indicate or suggest that the third vehicle 432 will make a lane change due to the closing of the fourth lane D. Thus, when the processor of the host vehicle 420 determines the probabilities of multiple potential behaviors of the second vehicle 431, such determination may take into account the additional vehicle dynamic traffic flow feature information indicative of the movement of the third vehicle 432. In some embodiments, the processor of the host vehicle 420 may receive the probabilities of the potential behaviors of the third vehicle 432 from a V2X resource 222 away from the host vehicle 420. In this way, the processor of the host vehicle 420 can determine probabilities of multiple potential behaviors of the second vehicle 431 taking into account the received probabilities of potential behaviors of the third vehicle 432.

[0062]

[0072] In some embodiments, the processor of the host vehicle 420 may receive historical information regarding vehicle behavior within an area traveled by the host vehicle 420. For example, such historical information may demonstrate that vehicles traveling in the first lane A and the fourth lane D typically change lanes approximately 50 meters before the lane ends. As another example, such historical information may demonstrate that vehicles traveling in the first lane A and the fourth lane D typically slow down and / or speed up before changing lanes. As another example, such historical information may demonstrate that vehicles traveling in the second lane B and the third lane C typically slow down as the vehicles turn into those lanes. In this manner, the processor of the host vehicle 420 may determine probabilities of multiple potential behaviors of the second vehicle 431 using or based at least in part on the received historical information.

[0063]

[0073] The processor of the host vehicle 420 may use extended sensing, such as receiving sensor information from other vehicles 431-437 or one or more roadside units 222, to obtain a richer social context for predicting the future path of the second vehicle 431 as well as all vehicles 431-437. Such predictions by the processor may take into account changes in traffic conditions. The processor of the host vehicle 420 may consider features such as the average speed of the lane when determining whether the vehicle will make a lane change. This information may be estimated / calculated by the processor based on predictions and historical information regarding the other vehicles. Such information may help the processor make both the host vehicle's path planning and predictions for the other vehicles. In addition, changes in the environment around the host vehicle may affect the predictions made by the processor. For example, lane closures, accidents, emergency vehicle operations, etc. may be communicated to the host vehicle, which may lead to the processor predicting lane changes by other vehicles before such maneuvers are observed.

[0064]

[0074] Providing a processor in the host vehicle with information reflecting the intent of one or more other vehicles may assist the processor in predicting future paths of those other vehicles. In some embodiments, such other vehicle intent information may be communicated to the host vehicle through coded signals transmitted by other vehicles, by roadside units, or by other intermediate devices or vehicles.

[0065]

[0075] 4B, the environment 400b includes a roadway 412 having a first vehicle 450, a second vehicle 452, a third vehicle 454, and one or more roadside units 222. The first vehicle 450 may include elements of and / or operate similarly to the vehicles (e.g., 12, 14, 16, 202, 220, 420, 431-437) described with respect to FIGS. 1A, 2, and 4A. The first vehicle 450 may plan a maneuver 460 to change lanes, for example, from a left lane to a right lane. In some embodiments, the first vehicle 450 may currently be performing (i.e., may be performing) the maneuver 460 to change lanes.

[0066]

[0076] The first vehicle 450 may receive the intent information of the second vehicle 452 indicating the intended behavior of the second vehicle. In some embodiments, the first vehicle 450 may determine the intent information of the second vehicle 452 based on a perceived behavior of the second vehicle 452 (e.g., from information received via one or more sensors). In some embodiments, the first vehicle 450 may receive the intent information of the second vehicle 452 from the second vehicle 452 (e.g., via a V2X message or V2X information). In some embodiments, the first vehicle 450 may receive the intent information of the second vehicle 452 from a network element, such as a roadside unit (RSU) 222.

[0067]

[0077] As an example, the intent information of the second vehicle 452 may indicate that the vehicle 452 intends to execute a braking maneuver 462. The braking maneuver 462 reduces the distance between the second vehicle 452 and the third vehicle 454. In some embodiments, the vehicle processor of the first vehicle 450 may predict, based on the intent information of the second vehicle 452, that the third vehicle 454 has a high probability of executing the braking maneuver 464.

[0068]

[0078] The high probability braking maneuver 464 places the third vehicle 454 in the path of the maneuver 460 planned or being executed by the first vehicle 450. In some embodiments, the vehicle processor of the first vehicle 450 can adjust the behavior of the first vehicle 450 based on the predicted behavior of the third vehicle 454. For example, the vehicle processor of the first vehicle 450 can cancel the planned execution of the maneuver 460 (i.e., cancel the lane change). As another example, the vehicle processor of the first vehicle 450 can execute a braking maneuver to slow down and maneuver behind the third vehicle 454. As another example, the vehicle processor of the first vehicle 450 may swerve to avoid a collision with the third vehicle 454. As another example, the vehicle processor of the first vehicle 450 may steer back into the left lane to avoid getting too close to the vehicle 454 (i.e., to maintain a threshold distance) or to avoid a potential collision with the third vehicle 454.

[0069]

[0079] 4C, a prediction system 400 suitable for implementing various embodiments may be implemented in a processor (e.g., 205) of a vehicle processing system or vehicle processor or V2X processing device (e.g., vehicle processors 102, 104, 106, 204, etc.), which may be implemented in hardware elements, software elements, or a combination of hardware and software elements (collectively referred to as a "vehicle processor"). In various embodiments, the prediction system 400c may include a dynamic feature module 470, a map feature module 472, an interaction feature module 474, and a probabilistic multi-modal joint trajectory decoder 476.

[0070]

[0080] In some embodiments, the dynamic features module 470 may predict (determine, calculate, provide as output) a dynamic behavior. In some embodiments, the predicted dynamic behavior may be based on or associated with a temporal pattern. For example, the dynamic features module 470 may provide as output an indication that a vehicle detected moving from one lane to another is performing a lane change. In some embodiments, the dynamic features module 470 may be trained to provide such a prediction using historical samples. In some embodiments, the dynamic features module 470 may be configured to apply (fit) the historical samples (and possibly sensor data) to a trained model, or may apply the historical samples and / or sensor data to a trained neural network.

[0071]

[0081] The map features module 472 may be configured to define geometry for interactions (e.g., with the environment, other vehicles, etc.). The map features module 472 may be configured to provide one or more predicted alignments of the trajectory as an output. For example, the map features module 472 may utilize map information such as an upcoming road curvature to provide an alignment of the trajectory along the upcoming road curvature as an output. In some embodiments, the map features module 472 may be configured to provide map features as an output that may affect or indicate a possible trajectory (e.g., an approaching T-junction).

[0072]

[0082] The interaction feature module 474 may be configured to provide as an output contextual information regarding one or more other vehicles. For example, the interaction feature module 474 may provide information regarding an adjacent vehicle that may help determine (predict, calculate) whether the adjacent vehicle is likely to make a lane change, exit the road, etc. For example, if the adjacent vehicle is in the right lane and drifting to the right, the interaction feature module 474 may provide an output indicating that the adjacent vehicle is likely to make a lane change to the right. The interaction feature module 474 can provide an output indicating that the adjacent vehicle is unlikely to perform an action or maneuver. For example, if there is insufficient spacing between vehicles to the left of the adjacent vehicle, the interaction feature module 474 can provide an output indicating that the adjacent vehicle is unlikely to make a lane change to the left.

[0073]

[0083] In some embodiments, the probabilistic multi-modal joint trajectory decoder 476 may receive outputs from each of the dynamic features module 470, the map features module 472, and the interaction features module 474. In some embodiments, the probabilistic multi-modal joint trajectory decoder 476 may provide as output a pair of predicted trajectories for the target agent 478 with estimated probabilities.

[0074]

[0084] FIG 5A is a process flow diagram of an example method 500a for managing vehicle behavior according to various embodiments. FIG 5B-5D are process flow diagrams of example operations 500b-500e that may be performed as part of the method 500a for using predicted future paths of other vehicles in vehicle control functions according to various embodiments. With reference to FIG 1A-5A, the method 500a and its operations may be performed by a processor (e.g., 205) of a vehicle processing system or vehicle processor or V2X processing device (e.g., vehicle processors 102, 104, 106, 204, etc.), which may be implemented in hardware elements, software elements, or a combination of hardware and software elements (collectively referred to as a "vehicle processor").

[0075]

[0085] 5A, the vehicle processor may receive dynamic traffic flow feature information related to movement of a second vehicle within a predetermined proximity to a first vehicle at block 502. In some embodiments, receiving the dynamic traffic flow feature information may include the vehicle processor receiving a probability for each of a plurality of route options available to the second vehicle from a database. In some embodiments, receiving the dynamic traffic flow feature information by the vehicle processor may include the vehicle processor receiving observational information related to the movement of the second vehicle from a sensor. In some embodiments, the dynamic traffic flow feature information may be received by the vehicle processor via V2X communications. In some embodiments, the dynamic traffic flow feature information may include contextual information related to the behavior and / or intended behavior of the second vehicle.

[0076]

[0086] In some embodiments, the dynamic traffic flow feature information may include one or more of information received from another vehicle, information sensed or acquired from a sensor of the host vehicle, HD map information, and / or environmental information observed by the host vehicle or other vehicles during travel. In some embodiments, the dynamic traffic flow feature information may include information about changes in traffic conditions or traffic flow, such as average lane speed(s), lane changes, braking behavior, acceleration behavior, traffic exits, traffic entry, etc. In some embodiments, the dynamic traffic flow feature information may include information about changes in the driving environment, such as lane closures, accidents, presence of emergency vehicles, etc., that may affect the behavior of other vehicles and / or traffic flow (e.g., from a closed lane to an open lane). The means for performing the operations of block 502 may include the vehicle processing system 102, 104, 106, 204, the in-vehicle network 210, the wireless module 218, the processor(s) 205, and the traffic flow feature module 322.

[0077]

[0087] At block 504, the vehicle processor may determine probabilities of a plurality of potential behaviors of the second vehicle based on the dynamic traffic flow feature information received at block 502. The vehicle processor may take into account the received dynamic traffic flow feature information in determining the plurality of potential behaviors. In some embodiments, the plurality of potential behaviors of the second vehicle determined by the vehicle processor at block 504 may include two or more route options available to the second vehicle. In some embodiments, determining the probabilities of the plurality of potential behaviors of the second vehicle based on the dynamic traffic flow feature information received by the vehicle processor may include determining the probabilities of the plurality of potential behaviors of the second vehicle taking into account additional vehicle dynamic traffic flow feature information. In some embodiments, determining the probabilities of the plurality of potential behaviors of the second vehicle based on the dynamic traffic flow feature information received by the vehicle processor may include determining the probabilities of the plurality of potential behaviors of the second vehicle taking into account a received probability of a potential behavior of a third vehicle. In some embodiments, determining by the vehicle processor the probability of the plurality of potential behaviors of the second vehicle may include determining the probability of the plurality of potential behaviors of the second vehicle based on the received historical information. In some embodiments, determining by the vehicle processor the probability of the plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow feature information may include determining the probability of the plurality of potential behaviors of the second vehicle based on updated map feature information included in the received dynamic traffic flow feature information. In some embodiments, determining by the vehicle processor the probability of the plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow feature information may include determining the probability of the plurality of potential behaviors of the second vehicle using at least one of a regression model or a classification model for predicted movements of vehicles surrounding the first vehicle. The means for performing the operations of block 504 may include the vehicle processing system 102, 104, 106, 204, the in-vehicle network 210, the processor(s) 205, and the behavior probability module 324.

[0078]

[0088] In block 506, the vehicle processor may predict a future path of the second vehicle based on the determined probabilities of the multiple potential behaviors of the second vehicle. Means for performing the operations of block 506 may include the vehicle processing system 102, 104, 106, 204, the in-vehicle network 210, the processor(s) 205, and the behavior prediction module 326.

[0079]

[0089] In block 508, the vehicle processor may use the predicted future path of the second vehicle in a vehicle control function. In some embodiments, the vehicle processor may use the predicted future path of the second vehicle in a vehicle control function to generate control commands to adjust the behavior of the first vehicle, such as to execute a maneuver, adjust an ongoing maneuver, update or adjust a path plan, etc. Means for performing the operations of block 508 may include the vehicle processing system 102, 104, 106, 204, the in-vehicle network 210, the processor(s) 205, and the behavior adjustment module 328.

[0080]

[0090] 5B-5D are process flow diagrams of example operations 510-514 that may be performed as part of a method 500a for managing vehicle behavior, according to various embodiments. Operations 510-514 may be performed by a processor (e.g., 205) of a vehicle processing system or vehicle processor or V2X processing device (e.g., vehicle processors 102, 104, 106, 204, etc.), which may be implemented in hardware elements, software elements, or a combination of hardware and software elements (collectively referred to as a "vehicle processor").

[0081]

[0091] 5B illustrates operations 510 of method 500b that may be performed by a vehicle processor, according to some embodiments. Referring to FIGS. 1A-5B, following operations at block 502 of method 500a, the vehicle processor may receive additional vehicle dynamic traffic flow feature information at block 510 indicative of a movement of a third vehicle within a predetermined proximity to the first vehicle. In response to receiving the additional vehicle dynamic traffic flow feature information at block 510, the processor may determine probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow feature information at block 504 of method 500a, as described. Means for performing operations of block 510 may include vehicle processing system 102, 104, 106, 204, in-vehicle network 210, processor(s) 205, and traffic flow feature module 322.

[0082]

[0092] 5C illustrates operation 512 of method 500c that may be performed by a vehicle processor, according to some embodiments. Referring to FIGS. 1A-5C, following the operations at block 502 of method 500a, the vehicle processor may receive, at block 512, a probability of a potential behavior of a third vehicle from a V2X resource remote from the first vehicle. In response to receiving the probability of the potential behavior of the third vehicle at block 512, the processor may determine probabilities of a plurality of potential behaviors of the second vehicle based on the dynamic traffic flow feature information received at block 504 of method 500a, as described. Means for performing the operations of block 510 may include the vehicle processing system 102, 104, 106, 204, the in-vehicle network 210, the processor(s) 205, and the traffic flow feature module 322.

[0083]

[0093] 5D illustrates operation 514 of method 500d that may be performed by a vehicle processor, according to some embodiments. Referring to FIGS. 1A-5D, following the operations at block 502 of method 500a, the vehicle processor may receive, at block 514, historical information regarding vehicle behavior in an area traveled by the first vehicle. In response to receiving the historical information at block 514, the processor may determine probabilities of a plurality of potential behaviors of the second vehicle based on the dynamic traffic flow feature information received at block 504 of method 500a, as described. Means for performing the operations of block 510 may include the vehicle processing system 102, 104, 106, 204, the in-vehicle network 210, the processor(s) 205, and the traffic flow feature module 322.

[0084]

[0094] FIG 6A is a process flow diagram of an example method 600a of managing vehicle behavior according to various embodiments. FIG 6B is a process flow diagram of example operations 600b that may be performed as part of the method 600a of managing vehicle behavior according to various embodiments. With reference to FIGS. 1A-6B, the method 600a and operations 600b may be performed by a processor (e.g., 205) of a vehicle processing system or vehicle processor or V2X processing device (e.g., vehicle processors 102, 104, 106, 204, etc.), which may be implemented in hardware elements, software elements, or a combination of hardware and software elements (collectively referred to as a "vehicle processor").

[0085]

[0095] 6A, the vehicle processor may receive intent information of the second vehicle indicative of an intended behavior of the second vehicle in block 602. In some embodiments, the vehicle processor may determine the intent information of the second vehicle from sensor information received by a sensor of the first vehicle, from messages (e.g., V2X messages) received by the first vehicle from the second vehicle, and / or from messages (e.g., V2X messages) received from a communication network (e.g., and RSU). Means for performing the operations of block 602 may include the vehicle processing system 102, 104, 106, 204, the in-vehicle network 210, the wireless module 218, the processor(s) 205, and the traffic flow features module 322.

[0086]

[0096] In block 604, the vehicle processor may predict the behavior of the third vehicle based on the received intent information of the second vehicle. In some embodiments, the vehicle processor may apply the received intent information of the second vehicle to a prediction system (e.g., prediction system 400) that may provide as an output a prediction of the behavior of the third vehicle. Means for performing the operations of block 604 may include the vehicle processing system 102, 104, 106, 204, the in-vehicle network 210, the processor(s) 205, the behavior probability module 224, and the behavior prediction module 326.

[0087]

[0097] In block 606, the vehicle processor may adjust the behavior of the first vehicle based on the predicted behavior of the third vehicle. In some embodiments, the vehicle processor may execute a maneuver based on the predicted behavior of the third vehicle. In some embodiments, the vehicle processor may modify an ongoing maneuver based on the predicted behavior of the third vehicle. In some embodiments, the vehicle processor may adjust a planned travel path based on the predicted behavior of the third vehicle. For example, the vehicle processor may cancel a planned maneuver based on the predicted behavior of the third vehicle. As another example, the vehicle processor may execute a maneuver (e.g., braking, turning, changing lanes, accelerating, etc.) based on the predicted behavior of the third vehicle. As yet another example, the vehicle processor may modify an ongoing maneuver based on the predicted behavior of the third vehicle. The means for performing the operations of block 606 may include the vehicle processing system 102, 104, 106, 204, the in-vehicle network 210, the processor(s) 205, the behavior probability module 224, and the behavior prediction module 326.

[0088]

[0098] Referring to FIG. 6A, in some embodiments, after receiving the second vehicle, the second vehicle's intent information indicating the intended behavior in block 602 of method 600a, the processor may receive dynamic traffic flow feature information related to the second vehicle in block 610. In some embodiments, the dynamic traffic flow feature information may include contextual information related to the behavior and / or intended behavior of the second vehicle. In some embodiments, the dynamic traffic flow feature information may include one or more of information received (e.g., from another vehicle) or sensed (e.g., via a sensor), HD map information, and environmental information observed during driving. In some embodiments, the dynamic traffic flow feature information may include information about changes in traffic conditions or traffic flow, such as average lane speed(s), lane changes, braking behavior, acceleration behavior, traffic exits, traffic entry, etc. In some embodiments, the dynamic traffic flow feature information may include information about changes in the driving environment, such as lane closures, accidents, presence of emergency vehicles, etc., that may affect the behavior of other vehicles and / or traffic flow (e.g., from a closed lane to an open lane). The means for performing the operations of block 610 may include the vehicle processing system 102 , 104 , 106 , 204 , the in-vehicle network 210 , the wireless module 218 , the processor(s) 205 , and the traffic flow features module 322 .

[0089]

[0099] In block 612, the vehicle processor may predict the behavior of the third vehicle based on the received second vehicle intent information and the dynamic traffic flow characteristic information associated with the second vehicle. Means for performing the operations of block 612 may include the vehicle processing system 102, 104, 106, 204, the in-vehicle network 210, the processor(s) 205, the behavior probability module 324, and the behavior prediction module 326.

[0090]

[0100] The vehicle processor may adjust the behavior of the first vehicle based on the predicted behavior of the third vehicle, in block 606, as described.

[0091]

[0101] Implementation examples are described in the following paragraphs. Although some of the implementation examples below are described with respect to example methods, further example implementations may include the example methods described in the following paragraphs implemented by a vehicle processing device, which may be an on-board unit, a mobile device unit, a mobile computing unit, or a fixed roadside unit, including a processor configured with processor-executable instructions for performing operations of the methods of the following implementation examples, and the example methods described in the following paragraphs implemented by a vehicle processing device, which may be a vehicle-mounted unit, a mobile device unit, a mobile computing unit, or a fixed roadside unit, including a processor configured with processor-executable instructions for performing operations of the methods of the following implementation examples, and the example methods described in the following paragraphs may be implemented as a non-transitory processor-readable storage medium having stored thereon processor-executable instructions configured to cause a processor of the vehicle processing device to perform operations of the methods of the following implementation examples.

[0092]

[0102] Example 1. A method executed by a processor of a first vehicle for using a predicted future route of another vehicle in a vehicle control function, the method including: receiving dynamic traffic flow feature information relating to movement of a second vehicle within a predetermined proximity to the first vehicle; determining probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow feature information, each of the plurality of potential behaviors taking into account the received dynamic traffic flow feature information; predicting a future route of the second vehicle based on the determined probabilities of the plurality of potential behaviors of the second vehicle; and using the predicted future route of the second vehicle in the vehicle control function.

[0093]

[0103] Example 2. The method of Example 1, further comprising receiving additional vehicle dynamic traffic flow characteristic information indicating movement of a third vehicle within a predetermined proximity to the first vehicle, wherein determining probabilities of multiple potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information comprises determining probabilities of multiple potential behaviors of the second vehicle taking into account the additional vehicle dynamic traffic flow characteristic information.

[0094]

[0104] Example 3. The method of example 2, wherein using the predicted future path of the second vehicle in a vehicle control function includes adjusting a behavior of the first vehicle.

[0095]

[0105] Example 4. The method of any of claims 1 to 3, further comprising receiving probabilities of potential behaviors of a third vehicle from a vehicle-to-everything (V2X) resource remote from the first vehicle, wherein determining probabilities of multiple potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information comprises determining probabilities of multiple potential behaviors of the second vehicle taking into account the received probabilities of the potential behaviors of the third vehicle.

[0096]

[0106] Example 5. The method of claim 1, wherein the plurality of potential behaviors of the second vehicle includes two or more route options available to the second vehicle.

[0097]

[0107] Example 6. The method of any of claims 1 to 5, further comprising receiving historical information regarding vehicle behavior in an area traveled by the first vehicle, wherein determining probabilities of a plurality of potential behaviors of the second vehicle comprises determining probabilities of a plurality of potential behaviors of the second vehicle based on the received historical information.

[0098]

[0108] Example 7. A method according to any one of claims 1 to 6, wherein receiving dynamic traffic flow characteristic information further includes receiving from a database a probability for each of a plurality of route options available to the second vehicle, and receiving from a sensor observational information relating to the movement of the second vehicle.

[0099]

[0109] Example 8. The method of any of claims 1 to 7, wherein the received dynamic traffic flow characteristic information is received via vehicle-to-everything (V2X) communication.

[0100]

[0110] Example 9. A method according to any one of claims 1 to 8, wherein determining the probabilities of multiple potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information includes determining the probabilities of multiple potential behaviors of the second vehicle based on updated map characteristic information included in the received dynamic traffic flow characteristic information.

[0101]

[0111] Example 10. A method according to any one of claims 1 to 9, wherein determining the probability of multiple potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information includes determining the probability of multiple potential behaviors of the second vehicle using at least one of a regression model or a classification model for the predicted movement of vehicles surrounding the first vehicle.

[0102]

[0112] The various embodiments shown and described are provided merely as examples to illustrate various features of the claims. However, features shown and described with respect to any given embodiment are not necessarily limited to the associated embodiment, and may be used with or combined with other embodiments shown and described. Furthermore, the claims are not limited by any one exemplary embodiment. For example, one or more of the operations of the method may be replaced or combined with one or more operations of the method.

[0103]

[0113] The above method descriptions and process flow diagrams are provided as illustrative examples only and do not require or imply that the operations of the various embodiments must be performed in the order presented. As will be appreciated by one of ordinary skill in the art, the order of operations in the above-described embodiments may be performed in any order. Words such as "thereafter," "then," and "next" do not limit the order of operations. These words are used merely to guide the reader through the method description. Furthermore, any reference to a claim element in the singular, for example using the articles "a," "an," or "the," should not be construed as limiting the element to the singular.

[0104]

[0114] The various exemplary logic blocks, modules, circuits, and algorithmic operations described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or a combination of both. To clearly illustrate this interchangeability of hardware and software, the various exemplary components, blocks, modules, circuits, and operations have been described above generally in terms of their functionality. Whether such functionality is implemented as hardware or software depends on the particular application and design constraints imposed on the overall system. Those skilled in the art may implement the described functionality in various ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the claims.

[0105]

[0115] The hardware used to implement the various example logic, logic blocks, modules, and circuits described in connection with the embodiments disclosed herein may be implemented or performed using general purpose processors, digital signal processors (DSPs), application specific integrated circuits (TCUASICs), field programmable gate arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but alternatively, the processor may be any conventional processor, controller, microcontroller, or state machine. A processor may also be implemented as a combination of computing devices, e.g., a combination of a DSP and a microprocessor, multiple microprocessors, one or more microprocessors in conjunction with a DSP core, or any other such configuration. Alternatively, some operations or methods may be performed by circuitry specific to a given function.

[0106]

[0116] In one or more embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented in software, the functions may be stored as one or more instructions or code on a non-transitory computer-readable medium or a non-transitory processor-readable medium. The operations of a method or algorithm disclosed herein may be embodied in a processor-executable software module that may reside on a non-transitory computer-readable storage medium or a non-transitory processor-readable storage medium. A non-transitory computer-readable storage medium or a non-transitory processor-readable storage medium may be any storage medium that may be accessed by a computer or a processor. By way of example and not limitation, such a non-transitory computer-readable medium or a non-transitory processor-readable medium may include RAM, ROM, EEPROM, FLASH memory, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium that may be used to store desired program code in the form of instructions or data structures and that may be accessed by a computer. Disk and disc as used herein include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk, and Blu-ray disc, where disks typically reproduce data magnetically and discs reproduce data optically using lasers. Combinations of the above are also included within the scope of non-transitory computer-readable and processor-readable media. Additionally, operations of a method or algorithm may reside as one or any combination or set of code and / or instructions on a non-transitory processor-readable medium and / or a non-transitory computer-readable medium that may be embodied in a computer program product.

[0107]

[0117] The foregoing description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the claims. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be applied to other embodiments without departing from the scope of the claims. Thus, the present disclosure is not intended to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the following claims and the principles and novel features disclosed herein.

Claims

1. 1. A method executed by a processor of a first vehicle for using a predicted future path of another vehicle in a vehicle control function, comprising: receiving dynamic traffic flow characteristic information relating to movement of a second vehicle within a predetermined proximity to the first vehicle; receiving historical information regarding vehicle behavior in an area in which the first vehicle has traveled; determining probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information, each of the plurality of potential behaviors taking into account the received dynamic traffic flow characteristic information, and determining the probabilities of the plurality of potential behaviors of the second vehicle includes determining the probabilities of the plurality of potential behaviors of the second vehicle based on the received historical information; predicting a future path of the second vehicle based on the determined probabilities of the plurality of potential behaviors of the second vehicle; using the predicted future path of the second vehicle in a vehicle control function; A method comprising:

2. 10. The method of claim 1, further comprising receiving additional vehicle dynamic traffic flow characteristic information indicative of movement of a third vehicle within the predetermined proximity to the first vehicle, 2. The method of claim 1, wherein determining probabilities of the plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information includes determining the probabilities of the plurality of potential behaviors of the second vehicle taking into account the additional vehicle dynamic traffic flow characteristic information.

3. The method of claim 2 , wherein using the predicted future path of the second vehicle in the vehicle control function comprises adjusting a behavior of the first vehicle.

4. 10. The method of claim 1, further comprising receiving a probability of a potential behavior of a third vehicle from a vehicle-to-everything (V2X) resource remote from the first vehicle, 2. The method of claim 1, wherein determining probabilities of multiple potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information includes determining the probabilities of the multiple potential behaviors of the second vehicle taking into account the received probabilities of the potential behaviors of the third vehicle.

5. The method of claim 1 , wherein the plurality of potential behaviors of the second vehicle includes two or more route options available to the second vehicle.

6. receiving dynamic traffic flow characteristic information; receiving from a database a probability for each of a plurality of route options available to the second vehicle; receiving observations related to movement of the second vehicle from a sensor; The method of claim 1 further comprising:

7. The method of claim 1 , wherein the received dynamic traffic flow characteristic information is received via vehicle-to-everything (V2X) communications.

8. 2. The method of claim 1, wherein determining probabilities of multiple potential behaviors of the second vehicle based on the received dynamic traffic flow feature information includes determining the probabilities of the multiple potential behaviors of the second vehicle based on updated map feature information included in the received dynamic traffic flow feature information.

9. 2. The method of claim 1, wherein determining probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information comprises determining the probabilities of the plurality of potential behaviors of the second vehicle using at least one of a regression model or a classification model for predicted movements of vehicles surrounding the first vehicle.

10. a vehicle processing device of a first vehicle, a processor, the processor comprising: receiving dynamic traffic flow characteristic information relating to movement of a second vehicle within a predetermined proximity to the first vehicle; receiving historical information regarding vehicle behavior in an area in which the first vehicle has traveled; determining probabilities of a plurality of potential behaviors of the second vehicle based on the received dynamic traffic flow characteristic information, each of the plurality of potential behaviors taking into account the received dynamic traffic flow characteristic information, the processor further comprising processor-executable instructions for determining the probabilities of the plurality of potential behaviors of the second vehicle based on the received historical information; predicting a future path of the second vehicle based on the determined probabilities of the plurality of potential behaviors of the second vehicle; using the predicted future path of the second vehicle in a vehicle control function. Vehicle processing device.

11. The vehicle processing device of claim 10, further comprising processor-executable instructions for executing a method according to any one of claims 2 to 9.

Images