System and method for intersection collision avoidance

Through the cellular network and multi-access edge computing processor, the transport network data is processed at the intersection, solving the problems of data delay and inconsistency at the intersection, and achieving more accurate road user behavior prediction and collision avoidance.

CN118946916APending Publication Date: 2024-11-12NISSAN NORTH AMERICA INC
View PDF 4 Cites 0 Cited by

Patent Information

Application Number
CN202280094371.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Priority Date
2022-03-28
Filing Date
2022-11-11
Publication Date
2024-11-12

AI Technical Summary

Technical Problem

At intersections, processing of transport network data from different sources to predict delays and inconsistencies in road user behavior leads to increased difficulty in collision avoidance, especially when intersections are the most complex and dangerous areas in transport networks.

Method used

Using cellular networks and multi-access edge computing processors, the signals from vehicles and infrastructure are received and processed through shared world models, and a conflict detection module is used to determine potential collisions and transmit notifications to vehicles to achieve intersection collision avoidance.

Benefits of technology

Reduces delays in intersection operations, effectively analyzes data, improves notification accuracy to road users, and reduces collision risks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118946916A_ABST
    Figure CN118946916A_ABST
Patent Text Reader

Abstract

Intersection collision avoidance may use a cellular transceiver for a cellular network and a processor located at a cellular access point for multi-access edge computing. The processor includes a shared world model and a conflict detection module. The shared world model is configured to receive, via the cellular transceiver, signals relating to at least two road users near an intersection within the vehicle transportation network, where the at least two road users include self-vehicles, and the signals conform to a standard-based communication protocol. The collision detection module is configured to receive object information from the shared world model, determine a potential future collision between the self-vehicle of the at least two road users and other road users, and transmit a notification of the potential future collision to the self-vehicle over the cellular network.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to navigating intersections, and more particularly to systems and methods for intersection collision avoidance. Background Art

[0002] Transportation network data from and about the transportation network and users of the transportation network and users near the transportation network may be obtained from sensors on vehicles traversing the transportation network and from infrastructure sensors near the transportation network. For example, transportation network data may be received or obtained from fixed infrastructure (such as traffic cameras and inductive loop traffic sensors), self-reported locations, and status information from networked road users and networked onboard sensors. Processing the collected transportation network data to provide meaningful insights into road user behavior is difficult. Summary of the invention

[0003] Aspects, features, elements, and implementations for intersection collision avoidance are disclosed herein.

[0004] One aspect of the disclosed implementation is a system for intersection collision avoidance, comprising: a cellular transceiver for use with a cellular network; and a processor for multi-access edge computing located at a cellular access point. The processor includes (implements, processes, etc.) a shared world model, which is configured to receive, via the cellular transceiver, signals related to at least two road users near an intersection within a vehicle transportation network, wherein the at least two road users include a self-vehicle, and the signals conform to a standards-based communication protocol. The processor also includes a collision detection module, which is configured to receive object information from the shared world model, determine a potential future collision between the self-vehicle and other road users among the at least two road users, and transmit a notification of the potential future collision to the self-vehicle on the cellular network.

[0005] One aspect of the disclosed implementation is a method for intersection collision avoidance, comprising: receiving, by a cellular transceiver used by a cellular network, signals associated with at least two road users near an intersection within a vehicle transportation network at a shared world model, wherein the at least two road users include a self-vehicle, and the signals conform to a standards-based communication protocol; receiving object information from the shared world model at a conflict detection module; determining, by the conflict detection module, a potential future collision between the self-vehicle and other road users of the at least two road users; and transmitting, by the conflict detection module, a notification of the potential future collision to the self-vehicle over the cellular network. The shared world model and the conflict detection module are implemented by a processor for multi-access edge computing located at a cellular access point.

[0006] These and other aspects of the present disclosure are disclosed in the following detailed description of the embodiments, the appended claims and the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The disclosed technology can be best understood from the following detailed description when read in conjunction with the accompanying drawings. It is emphasized that, according to common practice, the various features of the drawings may not be drawn to scale. On the other hand, the dimensions of the various features may be arbitrarily expanded or reduced for clarity. In addition, unless otherwise specified, the same reference numerals refer to the same elements throughout the drawings.

[0008] Figure 1 is a diagram of an example of a portion of a vehicle in which the aspects, features, and elements disclosed herein may be implemented.

[0009] Figure 2 is a diagram of an example of a portion of a vehicle transportation and communication system that may implement the aspects, features, and elements disclosed herein.

[0010] Figure 3 is a diagram of a system for intersection collision avoidance according to an implementation of the present disclosure.

[0011] Figure 4 It is a vehicle and Figure 3 A diagram of an example of communication between systems.

[0012] Figure 5 is a diagram of a system for generating a shared world model for intersection collision avoidance according to an implementation of the present disclosure.

[0013] Figure 6 is a flow chart of a method for determining intent of a vehicle.

[0014] Figure 7 is a diagram of the danger zone at the intersection.

[0015] Figure 8 Is used according to Figure 7 A diagram of a three-way intersection with hazard zones to determine potential conflicts.

[0016] Fig. 9 is a graph illustrating intended paths of two vehicles and a distance between the two vehicles at a future point in time for determining a potential conflict at an intersection.

[0017] Fig.10 is a diagram of a four-way intersection used to illustrate how targeted warnings are generated in response to conflict detection.

[0018] Fig.11 is a diagram of a four-way intersection used to illustrate how conflict detection is performed in the presence of obscured road users.

[0019] Fig. 12A is an example of a notification to a networked vehicle from a conflict detection according to the teachings herein.

[0020] Fig. 12B is another example of notification to a networked vehicle from conflict detection in accordance with the teachings herein.

[0021] Fig. 12C is an example of a notification to a pedestrian from a conflict detection according to the teachings herein. DETAILED DESCRIPTION

[0022] A vehicle may traverse a portion of a vehicle transportation network. The vehicle transportation network may include: one or more non-navigable areas, such as buildings; one or more partially navigable areas, such as parking areas (e.g., parking lots, parking spaces, etc.); one or more navigable areas, such as roads (which include lanes, medians, intersections, etc.); or a combination thereof. As a vehicle traverses the vehicle transportation network, the vehicle may use its local sensors that generate or capture data corresponding to the operating environment of the vehicle or a portion thereof. The vehicle may then use the data to identify potential collisions or hazards (e.g., other road users), which may be used to notify an operator, for input to a safety system, for input to an advanced driver assistance system (ADAS), or some combination thereof.

[0023] As described above, other data may be used for the purpose of identifying potential collisions or hazards. Processing transportation network data collected from vehicle sensors and from other vehicles and infrastructure sensors is complex due to its large volume. Large amounts of data tend to increase the delay in providing insight into future behavior. In addition, data about an individual road user (e.g., from different sources) may be inconsistent or contradictory at any given point in time. Large amounts of data may also result in unwanted notifications to specific road users, such as vehicles of interest, also known as self-driving vehicles. These problems are particularly acute when self-driving vehicles are approaching or within intersections, which are the most complex and dangerous areas in the transportation network.

[0024] Various solutions described herein improve the operation of self-propelled vehicles approaching, navigating, etc., intersections that reduce latency relative to conventional techniques for processing data, parsing road user data from different sources, effectively targeting road users for notification to avoid collisions, or a combination thereof. To describe in more detail some implementations of intersection collision avoidance according to the teachings herein, reference is first made to an environment in which the present disclosure may be implemented.

[0025] Figure 1 1 is a diagram of an example of a portion of a vehicle 100 that may implement aspects, features, and elements disclosed herein. The vehicle system includes a chassis 102, a powertrain 104, a controller 114, wheels 132 / 134 / 136 / 138, and may include any other element or combination of elements of a vehicle. Although the vehicle 100 is shown as including four wheels 132 / 134 / 136 / 138 for simplicity, one or more other propulsion devices (such as pushers or running boards, etc.) may be used. Figure 1 132 / 134 / 136 / 138, the lines interconnecting elements such as the powertrain 104, the controller 114, and the wheels 132 / 134 / 136 / 138 indicate that information such as data or control signals, power such as electricity or torque, or both information and power can be communicated between the various elements. For example, the controller 114 can receive power from the powertrain 104 and communicate with the powertrain 104, the wheels 132 / 134 / 136 / 138, or both to control the vehicle 100, which can include accelerating, decelerating, steering, or otherwise controlling the vehicle 100.

[0026] The powertrain 104 includes a power source 106, a transmission 108, a steering unit 110, a vehicle actuator 112, and may include any other element or combination of elements of the powertrain, such as a suspension, a drive shaft, an axle, or an exhaust system, etc. Although shown separately, wheels 132 / 134 / 136 / 138 may be included in the powertrain 104.

[0027] The power source 106 may be any device or combination of devices operable to provide energy (such as electrical energy, thermal energy, or kinetic energy, etc.). For example, the power source 106 includes an engine (such as an internal combustion engine, an electric motor, or a combination of an internal combustion engine and an electric motor, etc.), and is operable (configured) to provide kinetic energy as a motive force to one or more of the wheels 132 / 134 / 136 / 138. In some embodiments, the power source 106 includes a potential energy unit, such as one or more dry cells (such as nickel-cadmium (NiCd) batteries, nickel-zinc (NiZn) batteries, nickel-metal hydride (NiMH) batteries, lithium-ion (Li-ion) batteries, etc.), solar cells, fuel cells, or any other device capable of providing energy, etc.

[0028] The transmission 108 receives energy (such as kinetic energy, etc.) from the power source 106 and transmits the energy to the wheels 132 / 134 / 136 / 138 to provide motive force. The transmission 108 can be controlled by the controller 114, the vehicle actuator 112, or both. The steering unit 110 can be controlled by the controller 114, the vehicle actuator 112, or both, and the steering unit 110 controls the wheels 132 / 134 / 136 / 138 to turn the vehicle. The vehicle actuator 112 can receive a signal from the controller 114 and can actuate or control the power source 106, the transmission 108, the steering unit 110, or any combination thereof to operate the vehicle 100.

[0029] In the illustrated embodiment, the controller 114 includes a positioning unit 116, an electronic communication unit 118, a processor 120, a memory 122, a user interface 124, a sensor 126, and an electronic communication interface 128. Although shown as a single unit, any one or more of the elements of the controller 114 may be integrated into any number of separate physical units. For example, the user interface 124 and the processor 120 may be integrated into a first physical unit, and the memory 122 may be integrated into a second physical unit. Although illustrated as a single unit, any one or more of the elements of the controller 114 may be integrated into any number of separate physical units. Figure 1 1 , but the controller 114 may include a power source such as a battery, etc. Although shown as separate elements, the positioning unit 116, the electronic communication unit 118, the processor 120, the memory 122, the user interface 124, the sensor 126, the electronic communication interface 128, or any combination thereof may be integrated into one or more electronic units, circuits, or chips.

[0030] In some embodiments, the processor 120 includes any device or combination of devices that are currently available or subsequently developed and can manipulate or process signals or other information, such as an optical processor, a quantum processor, a molecular processor, or a combination thereof. For example, the processor 120 may include one or more special-purpose processors, one or more digital signal processors, one or more microprocessors, one or more controllers, one or more microcontrollers, one or more integrated circuits, one or more special-purpose integrated circuits, one or more field programmable gate arrays, one or more programmable logic arrays, one or more programmable logic controllers, one or more state machines, or any combination thereof. The processor 120 may be operably coupled to the positioning unit 116, the memory 122, the electronic communication interface 128, the electronic communication unit 118, the user interface 124, the sensor 126, the powertrain 104, and any combination thereof. For example, the processor may be operably coupled to the memory 122 via the communication bus 130.

[0031] The processor 120 may be configured to execute instructions. Such instructions may include instructions for remote operation, which may be used to operate the vehicle 100 from a remote location (including an operations center). The instructions for remote operation may be stored in the vehicle 100 or received from an external source (such as a traffic management center) or a server computing device (which may include a cloud-based server computing device). The processor 120 may also implement some or all of the active risk mitigation described herein.

[0032] The memory 122 may include any tangible, non-transitory computer-usable or computer-readable medium capable of, for example, containing, storing, communicating, or transmitting machine-readable instructions or any information associated therewith, for use by or in connection with the processor 120. The memory 122 may include, for example, one or more solid-state drives, one or more memory cards, one or more removable media, one or more read-only memories (ROMs), one or more random access memories (RAMs), one or more registers, one or more low-power double data rate (LPDDR) memories, one or more cache memories, one or more disks (including hard disks, floppy disks, or optical disks), magnetic or optical cards, or any type of non-transitory media suitable for storing electronic information, or any combination thereof.

[0033] The electronic communication interface 128 may be a wireless antenna as shown, a wired communication port, an optical communication port, or any other wired or wireless means capable of interacting with a wired or wireless electronic communication medium 140 .

[0034] The electronic communication unit 118 may be configured to transmit or receive signals via a wired or wireless electronic communication medium 140, such as via the electronic communication interface 128, etc. Figure 1 Although not explicitly shown, the electronic communication unit 118 is configured to transmit, receive, or both via any wired or wireless communication medium, such as radio frequency (RF), ultraviolet (UV), visible light, fiber optics, wireline, or a combination thereof. Figure 1 A single electronic communication unit 118 and a single electronic communication interface 128 are shown, but any number of communication units and any number of communication interfaces may be used. In some embodiments, the electronic communication unit 118 may include a dedicated short range communication (DSRC) unit, a wireless security unit (WSU), an Institute of Electrical and Electronics Engineers (IEEE) 802.11p (WiFi-P), or a combination thereof.

[0035] The positioning unit 116 can determine geographic location information, including but not limited to the longitude, latitude, altitude, direction of travel or speed of the vehicle 100. For example, the positioning unit includes a global positioning system (GPS) unit, such as a National Marine Electronics Association (NMEA) unit enabled with a wide area augmentation system (WAAS), a radio triangulation unit, or a combination thereof. The positioning unit 116 can be used to obtain information indicating, for example, the current heading of the vehicle 100, the current position of the vehicle 100 in two or three dimensions, the current angular orientation of the vehicle 100, or a combination thereof.

[0036] User interface 124 can include any unit that can be used as people's interface, including any one of virtual keyboard, physical keyboard, touch pad, display, touch screen, loud speaker, microphone, camera, sensor and printer.As shown, user interface 124 can be operably coupled with processor 120, or operably coupled with any other element of controller 114.Although being shown as single unit, user interface 124 can include one or more than one physical unit.For example, user interface 124 can include the audio interface for carrying out audio communication with people and the touch display for carrying out the communication based on vision and touch with people.

[0037] Sensors 126 may include one or more sensors, such as a sensor array, operable to provide information that can be used to control the vehicle. Sensors 126 may provide information about current operating characteristics of the vehicle or its surroundings. Sensors 126 include, for example, speed sensors, acceleration sensors, steering angle sensors, traction-related sensors, brake-related sensors, or any sensor or combination of sensors operable to report information about some aspect of the current dynamic situation of the vehicle 100.

[0038] In some embodiments, the sensors 126 include sensors operable to obtain information about the physical environment surrounding the vehicle 100. For example, one or more sensors detect road geometry and obstacles (such as fixed obstacles, vehicles, cyclists, and pedestrians, etc.). The sensors 126 may be or may include one or more cameras, laser sensing systems, infrared sensing systems, acoustic sensing systems, or any other suitable type of on-vehicle environment sensing device, or combination of devices, now known or subsequently developed. The sensors 126 and the positioning unit 116 may be combined.

[0039] Although not shown separately, the vehicle 100 may include a trajectory controller. For example, the controller 114 may include a trajectory controller. The trajectory controller is operable to obtain information describing the current state of the vehicle 100 and the route planned for the vehicle 100, and to determine and optimize the trajectory of the vehicle 100 based on the information. In some embodiments, the trajectory controller outputs a signal operable to control the vehicle 100 so that the vehicle 100 follows the trajectory determined by the trajectory controller. For example, the output of the trajectory controller may be an optimized trajectory, which may be supplied to the powertrain 104, the wheels 132 / 134 / 136 / 138, or both. The optimized trajectory may be a control input such as a set of steering angles, wherein each steering angle corresponds to a point in time or a position. The optimized trajectory may be one or more than one path, route, curve, or a combination thereof.

[0040] One or more of the wheels 132 / 134 / 136 / 138 may be: a steering wheel that pivots to a steering angle under the control of the steering unit 110; a propulsion wheel that twists under the control of the transmission 108 to propel the vehicle 100; or a steering propulsion wheel that steers and propels the vehicle 100.

[0041] The vehicle may include Figure 1 The units or elements shown in (Bluetooth) module, a frequency modulation (FM) radio unit, a near field communication (NFC) module, a liquid crystal display (LCD) display unit, an organic light emitting diode (OLED) display unit, a speaker, or any combination thereof.

[0042] A vehicle, such as vehicle 100, may be an autonomous vehicle or a semi-autonomous vehicle. For example, as used herein, an autonomous vehicle as used herein should be understood to encompass a vehicle that includes an advanced driver assistance system (ADAS). ADAS can automate, adapt, and / or enhance vehicle systems to achieve safe and better driving, such as by avoiding or otherwise correcting driver errors.

[0043] Figure 2 2 is a diagram of an example of a portion of a vehicle transportation and communication system 200 that may implement aspects, features, and elements disclosed herein. The vehicle transportation and communication system 200 includes a vehicle 202 (such as Figure 1 100) and one or more external objects (such as external object 206), which may include any form of transportation (such as Figure 1 ), pedestrians, cyclists, and any form of structure (such as a building). Vehicle 202 can travel via one or more portions of transportation network 208 and can communicate with external objects 206 via one or more of electronic communication networks 212. Figure 2 208, but vehicles may traverse areas that are not explicitly or fully included in the transportation network (such as off-road areas). In some embodiments, transportation network 208 may include one or more of vehicle detection sensors 210, such as inductive loop sensors, which may be used to detect movement of vehicles on transportation network 208.

[0044] The electronic communication network 212 may be a multi-access system that provides communications (such as voice communications, data communications, video communications, messaging communications, or a combination thereof) between the vehicle 202, the external object 206, and the operation center 230. For example, the vehicle 202 or the external object 206 may receive information (such as information representing the transportation network 208) from the operation center 230 via the electronic communication network 212.

[0045] The operation center 230 includes a controller device 232, which includes Figure 1 . Controller device 232 may monitor and coordinate the movement of vehicles, including autonomous vehicles. Controller device 232 may monitor the state or condition of vehicles, such as vehicle 202, and external objects, such as external object 206. Controller device 232 may receive vehicle data and infrastructure data, including any of the following: vehicle velocity; vehicle location; vehicle operating status; vehicle destination; vehicle route; vehicle sensor data; external object velocity; external object location; external object operating status; external object destination; external object route; and external object sensor data.

[0046] In addition, the controller device 232 can establish remote control of one or more vehicles (such as the vehicle 202) or external objects (such as the external object 206). In this way, the controller device 232 can remotely operate the vehicle or external object from a remote location. The controller device 232 can exchange (send or receive) state data with the vehicle, external object, or computing device (such as the vehicle 202, the external object 206, or the server computing device 234) via a wireless communication link (such as the wireless communication link 226) or a wired communication link (such as the wired communication link 228).

[0047] The server computing device 234 may include one or more server computing devices that may exchange (send or receive) status signal data with one or more vehicles or computing devices (including the vehicle 202, external object 206, or operation center 230) via the electronic communication network 212.

[0048] In some embodiments, the vehicle 202 or external object 206 communicates via a wired communication link 228, a wireless communication link 214 / 216 / 224, or a combination of any number or type of wired or wireless communication links. For example, as shown, the vehicle 202 or external object 206 communicates via a ground wireless communication link 214, via a non-ground wireless communication link 216, or via a combination thereof. In some implementations, the ground wireless communication link 214 includes an Ethernet link, a serial link, a Bluetooth link, an infrared (IR) link, an ultraviolet (UV) link, or any link capable of electronic communication.

[0049] A vehicle, such as vehicle 202, or an external object, such as external object 206, may communicate with another vehicle, external object, or operation center 230. For example, a host vehicle or subject vehicle 202 may receive one or more automated inter-vehicle messages, such as basic safety messages (BSMs), from operation center 230 via direct communication link 224 or via electronic communication network 212. For example, operation center 230 may broadcast messages to host vehicles within a defined broadcast range, such as three hundred meters, or to a defined geographic area. In some embodiments, vehicle 202 receives messages via a third party, such as a signal repeater (not shown) or another remote vehicle (not shown). In some embodiments, vehicle 202 or external object 206 periodically transmits one or more automated inter-vehicle messages based on a defined interval, such as one hundred milliseconds.

[0050] Vehicle 202 can communicate with electronic communication network 212 via access point 218. Access point 218, which may include a computing device, is configured to communicate with vehicle 202, electronic communication network 212, operation center 230, or a combination thereof via wired or wireless communication link 214 / 220. For example, access point 218 is a base station, a base transceiver station (BTS), a node B, an enhanced node B (eNode-B), a home node B (HNode-B), a wireless router, a wired router, a hub, a repeater, a switch, or any similar wired or wireless device located at, for example, a cellular tower. Although shown as a single unit, an access point may include any number of interconnected elements. Access point 218 may be a cellular access point.

[0051] Vehicle 202 may communicate with electronic communication network 212 via satellite 222 or other non-terrestrial communication means. Satellite 222, which may include a computing device, may be configured to communicate with vehicle 202, with electronic communication network 212, with operations center 230, or a combination thereof via one or more communication links 216 / 236. Although shown as a single unit, a satellite may include any number of interconnected elements.

[0052] The electronic communication network 212 can be any type of network configured to provide voice, data, or any other type of electronic communication. For example, the electronic communication network 212 includes a local area network (LAN), a wide area network (WAN), a virtual private network (VPN), a mobile or cellular telephone network, the Internet, or any other electronic communication system. The electronic communication network 212 can use a communication protocol such as the Transmission Control Protocol (TCP), the User Datagram Protocol (UDP), the Internet Protocol (IP), the Real-time Transport Protocol (RTP), the Hypertext Transfer Protocol (HTTP), or a combination thereof. Although shown as a single unit, the electronic communication network can include any number of interconnected elements.

[0053] In some embodiments, vehicle 202 communicates with operations center 230 via electronic communications network 212, access point 218, or satellite 222. Operation center 230 may include one or more computing devices capable of exchanging (sending or receiving) data from vehicles such as vehicle 202; data from external objects including external object 206; or data from computing devices such as server computing device 234.

[0054] In some embodiments, vehicle 202 identifies a portion or condition of transportation network 208. For example, vehicle 202 may include one or more on-vehicle sensors 204 (such as Figure 1Sensors 126 are shown, which include speed sensors, wheel speed sensors, cameras, gyroscopes, optical sensors, laser sensors, radar sensors, acoustic wave sensors, or any other sensor or device or combination thereof capable of determining or identifying a portion or condition of transportation network 208.

[0055] Vehicle 202 may traverse one or more portions of transportation network 208 using information communicated via electronic communication network 212, such as information representative of transportation network 208, information identified by one or more on-vehicle sensors 204, or a combination thereof. External object 206 may be capable of all or some of the communications and actions described above with respect to vehicle 202.

[0056] To keep it simple, Figure 2 Vehicle 202 is shown as a host vehicle, external object 206, transportation network 208, electronic communication network 212, and operation center 230. However, any number of vehicles, networks, or computing devices may be used. In some embodiments, vehicle transportation and communication system 200 includes Figure 2 Devices, units or elements not shown in the figure.

[0057] Although the vehicle 202 is shown as communicating with the operation center 230 via the electronic communication network 212, the vehicle 202 (and the external object 206) may communicate with the operation center 230 via any number of direct or indirect communication links. For example, the vehicle 202 or the external object 206 may communicate with the operation center 230 via a direct communication link such as a Bluetooth communication link. Although for simplicity, Figure 2 One of transportation networks 208 and one of electronic communications networks 212 are shown, but any number of networks or communications means may be used.

[0058] External object 206 in Figure 2 2 is shown as a second remote vehicle. The external object is not limited to another vehicle. The external object can be any infrastructure element that has the ability to transmit data to the operation center 230, such as a fence, a sign, a building, etc. The data can be, for example, sensor data from an infrastructure element.

[0059] As briefly mentioned above, the large amount of transportation network data collected from vehicles, infrastructure, etc. can complicate its processing and usefulness, particularly at intersections within the transportation network of vehicles. Systems and methods described herein are used to reduce delays and / or complexities associated with predicting future behavior, resolve inconsistencies in the data, minimize notifications, or some combination thereof.

[0060] Figure 3300 is a diagram of a system 300 for intersection collision avoidance according to an implementation of the present disclosure. As discussed in more detail below, the system 300 can be implemented in a vehicle 302 transportation and communication system (such as the vehicle transportation and communication system 200, etc.). Although described with respect to the vehicle 302 traveling through a vehicle transportation network (such as the vehicle transportation network 208, etc.), the teachings herein can be used in any area where the vehicle is navigable. As used herein, an intersection within a vehicle transportation network contains vehicle navigable paths that intersect each other, including entrances and exits to parking lots / garages and paths within parking lots (e.g., between parking spaces within a parking lot). Other examples of the system 300 may include more, fewer, or other components. In some examples, components may be combined; in other examples, components may be divided into more than one component.

[0061] generally, Figure 3 The multi-layer architecture of cooperative driving automation (CDA) messages sent from vehicles and infrastructure sensors is illustrated using multi-access edge computing (MEC). Then, MEC sends notifications back to vehicles and other road users (e.g., vulnerable road users (VRU), such as pedestrians or bicycles, etc.) to avoid collisions. These other road users may be referred to as non-motorized road users in this article. As shown, system 300 desirably uses standard-based communications (e.g., standard-based communication protocols) that eliminate the requirements for direct vehicle-to-vehicle (V2V) or vehicle-to-pedestrian (V2P) communications. In the described example, network cellular vehicle-to-vehicle (C-V2X) (also referred to as network C-V2X) is used for data / message exchange. Standard-based communications are based on the Society of Automotive Engineers (SAE) J3216 standard for cooperative driving, but any suitable communication protocol that can use cellular technology for wireless communication may be used.

[0062] The system 300 receives a corresponding signal 302a from one or more networked vehicles 302 (which may be vehicles 100, 202). The signal 302a may include a position, speed, or any other information. The signal 302a may include a BSM (e.g., SAE 2735 BSM). In some implementations discussed in further detail below, an intent signal INTENT may be transmitted from the networked vehicle 302.

[0063] The system 300 receives corresponding signals 304a from one or more VRUs, such as pedestrians 304, etc. The signals 304a may include location, speed, or any other information. The signals 304a may include personal safety messages (PSMs) (e.g., SAE2735 BSMs). As described in more detail below, the VRUs or non-motorized road users carry communication devices, such as cellular devices, etc., to transmit PSMs and optionally receive notifications. The cellular devices (also referred to as cellular-enabled devices) may be supported by the road users in any suitable manner.

[0064] The system 300 receives a corresponding signal 306a from one or more infrastructure sensors, such as infrastructure cameras 306, etc. The infrastructure sensors may be associated with infrastructure within a vehicle transportation network. The infrastructure sensors monitor at least a portion of an intersection. The infrastructure sensors may be incorporated into independent roadside units (RSUs), or may be mounted on buildings, traffic lights, street lights, etc. The infrastructure cameras 306 may send a signal 306a that includes information about what is detected (e.g., a vehicle, a VRU, an autonomous vehicle (AV)). The signal 306a may include a location, a speed, or any other information. In the event that a vehicle is detected, the signal 306a may include a BSM, and in the event that a VRU is detected, the signal 306a may include a PSM.

[0065] Signals 302a, 304a, and 306a are received at a cellular interface 308, which may include a wireless cellular transceiver (or a combination of a wireless receiver and a wireless transmitter) or an access point located at a cellular tower (such as access point 218, etc.). Processing of the received data may be performed at MEC 310. MEC 310 includes a signal interface 312, a system for generating a shared world model (SWM) 314, and a conflict detection module 316. MEC 310 is located at the edge of the mobile network (as opposed to a cloud service on the public Internet), such as at network 212, etc. For this reason, MEC 310 provides low latency for the application. In addition, since the computation occurs on the cloud, for example using server computing device 234, MEC 310 is highly scalable compared to computing only within the vehicle, for example using V2V communication.

[0066] In the illustrated implementation, SAE standard based messages are sent from vehicles 302, from pedestrians 304, from infrastructure cameras 306 or other VRUs, or from a combination thereof to MEC 310 using the network C-V2X over a cellular network. Figure 4 See further details of the communication system of MEC 310 (including signal interface 312), Figure 4is a vehicle such as vehicle 302 and Figure 3 FIG400 is a diagram of an example of communication between the systems 300.

[0067] like Figure 4 As shown, a vehicle such as vehicle 100, 202, etc. includes an interface 402. Interface 402 can be implemented at least in part by a processor (such as processor 120). In this example, vehicle 302 is a networked vehicle, but not an autonomous vehicle. A networked vehicle is a vehicle that is connected to a cellular network directly or through an operator's cellular device. Interface 402 uses an intention 404 of the vehicle (e.g., its operator) as input. The intention 404 of the vehicle 302 can be determined in any manner (such as detecting a turn signal, etc.). In some implementations, the intention 404 can be input as a robot operating system (ROS) message. Particularly useful optional techniques for determining the intention 404 of the vehicle are described below.

[0068] The intent signal 404 (also referred to herein as signal INTENT) undergoes data type conversion 406. The converted signal may be a JavaScript object representation (JSON) string 408. The JSON string 408 is converted to bytes 410 for input to an encoding mechanism 412. The encoding mechanism 412 encodes bytes 410 and other sensor data (e.g., GPS) into an encoded signal in a format suitable for device-to-device communication on a cellular network. In an example, the encoding mechanism 412 encodes the data into a JavaScript object representation (MQTT), which is a lightweight publish-subscribe network protocol for transmitting messages between devices. The message 422 is sent to a cellular interface (such as a cellular interface 308, etc.) on a cellular network (such as a mobile network of a specific cellular provider, etc.). The message 422 may be sent on a 4G network, a long-term evolution (LTE) network (such as 4G LTE, etc.), a 5G network, or any other cellular network now known or developed below. In some implementations, the electronic communication unit 118 may be used to send the message 422.

[0069] The cellular interface 308 receives the encoded messages 422 and distributes them to one or more signal interfaces 312 for the MEC 310. That is, as described above, the MEC 310 is scalable. Therefore, the signal interface 312 can be replicated with subsequent components of the MEC 310 to accommodate different parts of the transportation network, data exceeding a defined amount, etc. The cellular interface 308 can thus act as a proxy for the message to determine which MEC 310 should handle the incoming message. The encoded message 422 is transmitted to the appropriate signal interface 312 via a network such as a LAN 424. The signal interface 312 converts the message back to ROS or another format for use by the remaining components of the system 300 (i.e., the SWM 314 and the conflict detection module 316).

[0070] As can be determined from this description, the interface 402 and the signal interface 312 include hardware that collectively acts as a gateway between the cellular network and the messages used by the SWM 314 and the conflict detection module 316. In this example, the interface converts the data to the MQTT format and publishes the data, respectively, and then, as described in further detail below, upon receipt, the MQTT messages are converted back to another format (e.g., the native format of the SWM 314 and the conflict detection module 316) for use in determining conflicts / collisions.

[0071] Although interface 402 receives and encodes signal INTENT, this is not required. Figure 3 The intended use in the processing of is optional. For example, the interface 402 may only include an encoding mechanism 412 that encodes vehicle sensor data such as latitude, longitude, attitude, speed, etc., or any combination thereof (eg, BSM). Figure 4 Interface 402 is described as being implemented in a vehicle such as networked vehicle 302. Similar interfaces may be incorporated into infrastructure sensors such as infrastructure camera 306 for encoding and transmitting detected signals such as signal 306a. Such an interface may include or omit hardware / software to determine and include the intent of a vehicle where the vehicle is the detected object. An interface similar to interface 402 including an encoding mechanism may be included in a cellular enabled device (e.g., a mobile phone) of a VRU to encode sensor data such as latitude, longitude, attitude, velocity, etc., or any combination thereof (e.g., PSM).

[0072] Return to reference Figure 3, the MEC 310 uses object fusion to generate a shared world model (SWM 314, which can be used for prediction and conflict detection). As can be seen from the above, the MEC 310 can receive data related to the same object from more than one source. For example, at an intersection, the MEC 310 can receive a signal 302a related to the location of the networked vehicle 302, etc., and receive a signal 302a including information related to the location of the networked vehicle 302, etc. Similarly, the MEC 310 can receive a signal 304a related to the location of the VRU (e.g., a pedestrian 304), etc., and receive a signal 304a including information related to the location of the VRU, etc. The SWM 314 receives the signals 302a, 304a, 306a, determines (e.g., converts to, detects, etc.) objects from the sensor data, and fuses the objects detected by multiple sources (if any), and generates a single world view of the road user and his surroundings.

[0073] like Figure 3 As shown, SWM 314 includes object association 314a and object fusion 314b. In some implementations, object association 314a can determine objects (e.g., road users) based on received signals 302a, 304a, 306a (e.g., BSM and PSM messages). For example, object association 314a can associate location information within each message with a corresponding road user (e.g., a networked vehicle within a vehicle transportation network, a VRU (e.g., a pedestrian or non-motorized vehicle), or an autonomous vehicle). Object association 314a can generate or maintain states of at least some of the determined objects, such as speed, posture, geometry (such as width, height, and depth, etc.), classification (e.g., bicycle, large truck, pedestrian, road sign, etc.), location, or some combination thereof, etc.

[0074] In addition to signals such as signals 302a, 304a, 306a, etc. (e.g., BSM and PSM messages), object fusion 314b may also receive objects sensed over time. For example, using data such as heading and velocity information, the sensed objects may be fused where appropriate. That is, data associated with each object may be compared to determine whether corresponding objects identified by separate messages are likely to be the same object. Any technique for comparing data for each sensed object may be used. The more similar the data, the more likely it is that two objects are the same object. The data for objects determined to be the same object is fused to generate a tracked object at a position that varies over time. Its fused trajectory (e.g., based on a combination of heading, attitude, and velocity) may be used in the conflict detection module 316. That is, at the output of the SWM 314, each road user is a separate tracked object with a corresponding trajectory or intended path to be supplied to the conflict detection module 316 for use therein.

[0075] Although described as a separate component of SWM 314, the shared world model used in MEC 310 may require many overlapping detections to produce results. That is, object association and fusion are coupled and performed iteratively. Although such an implementation of the shared world model can be used in MEC 310, a particularly desirable implementation of SWM 314 is described in detail below.

[0076] The conflict detection module 316 receives the tracked objects and their corresponding trajectories. The conflict detection module 316 uses this information to predict possible collisions at intersections between a networked vehicle, such as the networked vehicle 302, and a nearby vehicle or VRU, such as the pedestrian 304. In some implementations, the conflict detection module 316 does this by using the trajectories over the look-ahead period to determine where the various road users will be at a point in time in the look-ahead period.

[0077] In some examples herein, infrastructure sensors of the RSU can detect non-networked road users (e.g., pedestrians) and connect to networked road users (e.g., networked vehicles). For non-networked road users, predictions can be made through measurements (e.g., speed and heading) from (one or more than one) infrastructure sensors over time. For networked road users, the intended path can be similarly predicted from such measurements. However, at intersections, the measurements may not provide the best indication of the intended path because there may be changes that cannot be identified from the measurements, such as turns, etc. Therefore, in some implementations, as described in additional detail below, the signal INTENT can be used to determine the intended path of the networked vehicle. The predicted / intended trajectories of the road users can then be compared to determine whether a conflict will occur.

[0078] For conflict detection between non-networked road users (e.g., pedestrians or non-networked vehicles) and networked vehicles, for example, predicted / intended paths and speeds are used to determine where non-networked users may arrive at time points or steps in the look-ahead period, as for networked vehicles. The distance between paths at future time steps can be calculated. Then, when the distance between the paths is shorter than a threshold, a conflict can be detected. In other words, if two or more road users are within a defined proximity of each other at a particular point in time, the conflict detection module 316 can identify a potential conflict and optionally send a notification to the networked vehicle and any other affected road users.

[0079] This is one technique for detecting a potential conflict between two paths at some point in the future. However, other techniques are possible, another of which is described below by way of example. Notification is also described in more detail below.

[0080] In some implementations, conflict detection can use the intent of the operator of the networked vehicle to determine the path of the networked vehicle within at least a portion of the look-ahead period. In some implementations, this is a signal INTENT received along with the signal 302a from the networked vehicle 302. The signal INTENT can be used to share the operator's intent for cooperative driving. Traditional safety systems may not consider intent that is not otherwise indicated by attitude, heading, speed, etc., and therefore may be overly dependent on the proximity of the networked vehicle to other vehicles or VRUs near the intersection.

[0081] In the above example, the turn signal can be used to determine the operator's intent for use in the conflict detection module 316. For example, the turn signal can indicate that the networked vehicle 302 will turn right at a 4-way intersection. Together with other information received from road users near the intersection, a notification can be issued from the conflict detection module 316 that is a result of a more accurate prediction than relying solely on BSM and PSM messages. Specific examples of the signal INTENT are discussed further below.

[0082] In the case of a networked autonomous vehicle (CAV) at or near an intersection that a networked vehicle or VRU is approaching or navigating, the decision making of the CAV may be improved by using the teachings herein. Figure 3 In FIG. 3 , CAV 320 is conventionally shown as including sensor inputs into fusion unit 324. The hardware sensors shown include cameras and light detection and ranging sensors (LiDAR). Other sensors conventionally found on autonomous vehicles may include GPS and radio detection and ranging (RADAR) sensors. Fusion unit 324 receives signals and fuses objects identified by the sensors into tracked objects for inclusion in processing by a processor (such as a CAV 320) Figure 1 In a shared world model executed by processor 120, etc.

[0083] Autonomous vehicles such as CAV 320 conventionally have a shared world model. According to implementations of the present disclosure, the shared world model of CAV 320 may also receive BSM and PSM messages from cellular interface 308 to refine the shared world model. That is, in addition to coordinating its own sensor values ​​to identify objects using fusion unit 324, CAV 320 may also include a processor of CAV 320 (such as Figure 1120) to generate tracked objects and their corresponding trajectories. In some implementations, the shared world model of the CAV 320 may also be different from (i.e., operate in a different manner than) the SWM 314. In either case, the tracked objects and their corresponding trajectories are sent to the decision module 326. The CAV 320 does not require a separate conflict detection module (such as the conflict detection module 316) because the decision module 326 can be a conventional module for decision making that already handles conflict detection and resolution.

[0084] As described above, a shared world model may be used in a system for intersection collision avoidance, whether the system is located within a vehicle or at a remote computing location. Often, it is desirable to combine object detections from multiple sensors to avoid confusing the system. For example, multiple sensors may detect a pedestrian at different locations when only one pedestrian is present. Failure to use a shared world model may result in the self-driving vehicle attempting to maneuver around multiple pedestrian detections instead of a single pedestrian.

[0085] In some implementations of a shared world model that may be used as SWM 314, the time to combine object detections from multiple sources may be dictated by the slowest sensor. This is because the shared world model may need to iteratively perform object association and fusion of overlapping detections. Results may take up to a second to produce. This situation becomes worse when communication delays are increased. For example, in system 300, communication delays may occur when information is sent from networked sensors over a cellular network. Receiving and parsing sensor data in a timely manner is very important for performing safety-critical maneuvers (e.g., activating automatic emergency braking (AEB) or making a sharp turn).

[0086] exist Figure 5 A particularly desirable system 500 for generating a shared world model is shown by way of example in FIG. The system 500 addresses some of the latency issues mentioned above by decoupling the object association and object fusion steps to combine object detections from different sensors. The resulting shared world model can be used as Figure 3 314 in the SWM 314. According to implementations of the present disclosure, the resulting shared world model can be used for intersection collision avoidance. The architecture of the proposed system 500 allows for faster action than conventional techniques and is limited only by the fastest sensor rather than the slowest (e.g., most delayed) sensor. While particularly useful for the MEC 310 and optionally networked autonomous vehicles (such as CAV 320, etc.), the system 500 can be used with any autonomous vehicle that receives external sensor data (i.e., sensor data from sensors other than the autonomous vehicle's sensors).

[0087] like Figure 5As can be seen in FIG. 5 , input 502 is received from sensors numbered 1, 2, ... N. Input 502 may correspond to the sensor 100 as described above with respect to FIG. Figure 3 The inputs 502 may be BSMs from networked vehicles, PSMs from VRUs, PSMs from occupants in networked vehicles, PSMs from infrastructure sensors, BSMs from infrastructure sensors, or some combination thereof. At least some of these inputs 502 are asynchronous signals or messages. That is, each sensor has its own characteristics, such as sampling rate, etc. In addition, each sensor communicates with the SWM 314 (e.g., to the Figure 3 The amount of time required to communicate with the cellular interface 308 in the sensor may vary. Therefore, the corresponding signals of the sensors may be sent at different times and / or received at different times.

[0088] Input 502 is received at a corresponding sensing and filtering module 504. Sensing and filtering module 504 may partially implement object association 314a. Sensing and filtering module 504 generates, determines, senses, or otherwise identifies an object (e.g., a road user) from the corresponding input. Any technique may be used to identify the object from the input, including but not limited to pattern matching, comparison with a database, etc. Figure 5 As shown by the dashed lines in , the detection of perceived objects from different sensors is immediately sent to downstream decisions (e.g., object fusion and prediction module 610 described below) while object association continues in parallel at interpolator 606. The detection can be referred to as an asynchronous detector.

[0089] The interpolator 506 may be provided with a synchronized output with reference to a master clock of various timing sources. As described above, the perceived objects are also provided to the interpolator 506. The perceived objects are provided with the time points at which they are perceived, which are asynchronous. The interpolators 506 for the respective perceived objects may each be used to interpolate the perceived objects at a synchronized timing based on a signal from the master clock. That is, based on the asynchronous detection and other data (e.g., rate, heading, etc.) from the input 502, the location of the perceived object at the synchronized time point indicated by the master clock is determined.

[0090] Each interpolator 506 outputs two signals based on the location of the perceived object at the synchronized time point. The first signal is called a synchronized tracklet. The synchronized tracklet is the location of the perceived object at each time point indicated by the master clock. These tracklets are provided to the track association and calibration module 608 and the object fusion and prediction module 510. The second signal is called a synchronized detection. These synchronized detections are provided to the track association and calibration module 508 and the object fusion and prediction module 510.

[0091] The track association and calibration module 508 receives the synchronized track segments and synchronized detections and over time associates the signals at synchronized time points with corresponding objects. Object association is the matching of objects sensed by one sensor with objects sensed by another sensor (possibly from a different vantage point) (e.g., matching of infrastructure camera observations of a pedestrian with the reported GPS position of the pedestrian from his phone). The track association and calibration module 508 may also compute extrinsic relative sensor calibrations. Object association and sensor calibrations are sent to the object fusion and prediction module 510.

[0092] Object fusion and prediction module 510 fuses duplicate detections in a shared world model. This includes, for example, objects and their predicted paths. The shared world model is sent for decision making 512. For example, a networked road user (vehicle, pedestrian, etc.) can rely on cloud conflict detection decisions, such as at conflict detection module 316, to send timely warnings of detected hazards. An autonomous vehicle first relies on its own sensors to make decisions, such as at decision module 326, but can augment its world model with (delayed) detections from off-board networked sensors (if available).

[0093] Sensor calibration helps with object fusion. Sensor calibration can also be retained to speed up future associations.

[0094] In addition to reducing latency over competing techniques for generating shared world models, system 500 can also produce more accurate shared world models. That is, object fusion with incorrectly associated objects can result in errors that are difficult to correct. The delay in object fusion caused by decoupling object fusion from object association reduces the chance of such errors.

[0095] As about Figure 3 As mentioned in the description of , the intention of the vehicle (e.g., the intention of the operator of the vehicle) may be useful in collision or conflict detection. If the intended path of each vehicle in the next few seconds is known, the probability of a vehicle (e.g., a networked vehicle) colliding with another vehicle or VRU can be predicted with greater accuracy. For example, if a right turn signal is on, it may not be clear from the heading or speed alone whether the vehicle is turning right, overtaking, or changing lanes.

[0096] Generally, the techniques proposed herein may use a high-definition map (HD map) in conjunction with a destination or turn signal entered into a navigation system to predict the future path of a connected vehicle. Figure 66 is a flow chart of a method 600 for determining the intent of a networked vehicle. The method 600 may be performed by a processor of a networked vehicle, such as the processor of the networked vehicle 302. The processor of the networked vehicle may be a stand-alone processor, a processor of an onboard navigation system, or a processor incorporated into a cellular interface of the networked vehicle, such as the interface 402.

[0097] At 602, a destination message for a networked vehicle of interest (e.g., a vehicle entering, passing through, approaching, etc., an intersection) may be determined or received. A destination message may be determined or received from an onboard navigation system of the vehicle (when present (e.g., the vehicle has established a destination message)). At 604, a turn signal direction message for the vehicle may be determined or received. Turn signal direction may also be referred to as the direction of the turn signal or simply referred to herein as direction. Turn signal direction may be determined periodically when the vehicle is within a defined distance from the intersection and / or when the vehicle generates a turn signal change message in response to an operator action to engage or disengage a turn signal. When the turn signal is off, the direction is straight ahead.

[0098] The HD map is used for input at 606. That is, the HD map can provide input at 606 to calculate a possible intended path of the vehicle using the destination (e.g., the destination message) at 612. For example, the possible intended path can be or include a lane-by-lane path to the destination. Since the HD map provides speed limits and other road features (such as stop lines and crosswalks), this information can be used to define multiple waypoints (also called driving goals) along the path for the next few seconds (such as 10-15 seconds, etc.), with information such as the type of waypoint and the speed limit.

[0099] Alternatively or additionally, the HD map may provide input at 606 to calculate a likely intended path of the vehicle using the turn signal direction at 614. Speed ​​limits and other road features of the HD map (such as stop lines and crosswalks) may provide input at 606 to define multiple waypoints along the path for the next few seconds, taking into account, for example, whether the turn signal direction indicates a right turn, a left turn, or off (e.g., when entering an intersection or after completing a turn or lane change), with information such as the type of waypoint and the speed limit.

[0100] Once the possible intended paths are calculated at 612, 614, or both, the method 600 proceeds to determine which possible intended path is the most accurate prediction. In the event that there is an available destination at 602 and the possible intended path is calculated at 612, the method 600 queries whether turn signal directions are available at 622. If not, the method 600 uses the possible intended path calculated from the destination as an indication of the vehicle's intention at 632. Conversely, in the event that there is an available turn signal direction at 604 and the intended path is calculated at 614, the method 600 queries whether there is an available destination at 624. If not, the method 600 uses the possible intended path calculated from the turn signal direction as an indication of the vehicle's intention at 634.

[0101] If there is a turn signal direction at 622 and a destination at 624, the method 600 determines at 630 whether the turn signal direction matches the possible intended path calculated at 612. For example, the method 600 determines whether the intended path includes a right turn or a change to the right lane when the turn signal changes to a right turn. If the turn signal direction matches the possible intended path at 630, the method 600 uses the intended path calculated based on the destination as an indication of the intention of the vehicle at 632. If it does not match, the method 600 uses the intended path calculated based on the turn signal as an indication of the intention of the vehicle at 634. These choices reflect two considerations. First, the turn signal alone is not the most accurate measure of the driver's intention. Second, if both the turn signal and the destination are available, the turn signal can improve the measure of the driver's intention. For example, a turn signal that contradicts the intended path determined at 612 may indicate that the operator of the vehicle has decided to change the most likely path generated using the destination.

[0102] In either case, the driving goal helps determine when and where the vehicle is predicted to be at a specific time in the next few seconds. This information can be used with the presence, intent, or both of other road users (e.g., vehicles, VRUs, etc.) to predict the probability of a conflict or collision. For example, without taking action as described above with respect to the conflict detection module 316, points along the various predicted paths of road users at the intersection can be used to identify possible conflicts.

[0103] In some implementations, such as regarding Figure 3 As described, the intent path determined by repeating method 600 can be used to generate a signal INTENT that indicates the intent of the networked vehicle (eg, the operator of the networked vehicle). Figure 3 When used in an implementation of , it can be used as an input to the conflict detection module 316.

[0104] In an example, when a destination is set in the navigation system, a path to the destination is generated using the HD map at 612. This gives a list of lane segments starting from the car's current location until the destination. To generate an intent, only the portion of the path ahead that the vehicle will travel within a defined amount of time or a defined distance may be considered. For example, only the portion of the next 15 seconds or 500 meters (whichever is greater) of the path is considered. This limits the amount of data that needs to be sent for an intent. Starting from the lane segment where the car is until the end of the selected path (e.g., until the end of that portion of the path), a list of driving objectives (e.g., waypoints, time points, time steps) is generated. Individual driving objectives may contain information such as speed limits, target types (e.g., stop, crosswalk, etc.). An example of the format of an intent message (e.g., signal INTENT) is shown below.

[0105] temp_id Vehicle ID latitude The current location of the vehicle longitude The current location of the vehicle course The vehicle's current heading speed The current speed of the vehicle drive_goal Driving Target List

[0106] The list of driving goals in the intent message can be a separate driving goal message. An example of the format of the driving goals contained in the intent message is as follows.

[0107]

[0108]

[0109] If the turn signal is to be used, the forward path (lane segment) is queried from the HD map. If another intersection appears immediately after the turn, the intended path can be generated only until the new intersection. Then, a new intended path can be generated for the next intersection.

[0110] Using HD maps in conjunction with a destination or turn signal (or both) according to the teachings herein allows prediction of what a connected vehicle may be doing with greater accuracy than using speed and heading. For example, the technology provides not only intent, but also the intended speed at different points along the path. In addition, the technology allows determination of which lanes a vehicle will follow in the next few seconds. This is useful in safety applications for notifying drivers of impending collisions.

[0111] For non-networked vehicles and VRUs, as described above for Figure 3Briefly described, the heading and trajectory can be used to determine a predicted path for a look-ahead period (in this example, 15 seconds or 500 meters). In some implementations, at least a portion of method 600 can be performed by a processor in an RSU that supports infrastructure sensors such as infrastructure cameras 306 (e.g., the infrastructure sensors are housed by the RSU). For example, the RSU can determine a turn signal change message for a non-networked vehicle at 604. The turn signal change message (when present) can be detected from an image received by the infrastructure sensor. Thus, an intended path can be calculated at 614 and used at 634 as a signal INTENT for conflict detection (such as at a conflict detection module 316 or using a processor of the RSU).

[0112] As can be appreciated from the above description, uncertainty may exist in the intended or predicted path, for example, due to technical limitations of infrastructure sensors, imperfections in prediction models, and unknown intentions of road users (particularly VRUs). To address some of these uncertainties and improve detection of potential conflicts (such as at conflict detection module 316), the techniques described herein describe conflict or danger zones (where a VRU may conflict with a vehicle). Figure 7 Describe the technique, Figure 7 This is a diagram of intersection 700.

[0113] Figure 7 700 is a three-way intersection where street 702 has road divider 704. In some implementations, zones may be predefined for the intersection based on locations where VRUs may cross roads, such as locations where the likelihood of conflicts is high, etc. The size of the zone may be determined based on statistics of VRU (e.g., pedestrian) events, such as how far a VRU may travel at different locations and at different speeds within the intersection. Figure 7 Five zones 706 are shown by way of example. A default zone size may be defined. In some implementations, the zone size may be determined based on the location of the VRU relative to the intersection when the VRU is detected and optionally the type of VRU and / or the speed of the VRU (e.g., a bicycle will have a larger zone than a pedestrian).

[0114] In operation, a processor associated with an RSU (e.g., a processor associated with an infrastructure sensor of the RSU) or a processor associated with a shared world model (such as SWM 314) can identify the location of a VRU (as a non-networked road user) over time. Once identified, a zone can be defined for the VRU. The zone can be a predefined zone at the detected location, a default zone size placed according to the location, or a zone size determined as described above placed according to the location. As described above with reference to the example of the conflict detection module 316, the metrics so performed can be used to generate a predicted path.

[0115] Instead of limiting road users to predicted paths for detecting potential collisions within an intersection, zones can be used for conflict detection in the case where at least one of the road users is a VRU. In an example where a vehicle is approaching an intersection where a VRU is also present, a predicted trajectory can be used to determine the time at which the VRU is crossing a zone (such as one of zones 706). The time at which the vehicle will cross a zone can be determined based on a predicted path (e.g., in the absence of a signal INTENT) or an intended path (e.g., in the case of using a signal INTENT). As previously described, this can be done at time steps or points in the look-ahead period. Once these points are known, a potential conflict is identified if the intended path of the vehicle and the predicted path of the VRU will cross the zone at the same time.

[0116] For example, Figure 8 Shown with Figure 7 The intersection 700 shown is similar to the three-way intersection 800 (except that the road divider 704 is not present). Therefore, three zones can be defined for the intersection. Figure 8 8, an ego (e.g., networked) vehicle 802 is traveling along a street 810 in a first direction. Arrow 804 shows the intended path of vehicle 802. (e.g., non-networked) vehicle 806 is traveling along street 810 in the opposite direction. Pedestrian 808 (e.g., VRU) has a predicted path to cross zone 820. Based on when vehicle 802 will cross zone 820 compared to pedestrian 808, a potential conflict is detected. Thereafter, a notification 830 may be issued to ego vehicle 802, such as from a conflict detection module 316. If a conflict is detected, the conflict level may be calculated based on the deceleration level required to avoid the conflict. In some implementations, the deceleration level may be compared to a maximum deceleration such that a notification is not issued until the deceleration level approaches the maximum deceleration.

[0117] As described above with respect to the conflict detection module 316, for conflict detection between vehicles, whether networked or non-networked, a predicted path for each vehicle may be determined. That is, the paths and speeds of each vehicle may be used to compare the future positions of the vehicles. Fig. 9 For example, a first vehicle 902 may have a predicted path 912 at a defined time step 906, and a second vehicle 904 may have a predicted path 914 at the same defined time step 906. That is, the paths and velocities of the vehicles are used to calculate their respective future positions. The distance between the paths 912, 914 at the future time step 906 may be calculated. Fig. 9, distance d1 is a first distance between paths 912, 914, and distance d2 is a second distance between paths 912, 914. Paths 912, 914 converge to a potential conflict at 920. When the distance between paths 912, 914 is less than a threshold at some point before 920, a potential conflict is identified and a notification may be issued. When at least one of the vehicles is a networked vehicle, the associated path 912 or 914 may be an intended path (i.e., a path that takes into account the vehicle's intent (such as a signal INTENT, etc.)).

[0118] While zones may be used for conflict / collision detection in the context of VRUs as described above, zones may be used in a similar manner for other non-networked road users, such as non-networked vehicles, etc.

[0119] Regardless of the type of road user approaching the intersection, conflict detection can be performed by a processor of the RSU (instead of or in addition to the conflict detection module 316). To this end, the RSU can host a shared world model that will match the SWM 314 and conflict detection module 316 of the MEC 310 that receive signals from the cellular interface 308 in a manner similar to the way the signal interface 322 receives signals. Alternatively, the RSU can host a conflict detection module similar to the conflict detection module 316, which receives objects and trajectories from the SWM 314 (e.g., on a wireless cellular network) for conflict detection and issues notifications where appropriate. In another implementation, the intended path of the networked vehicle can be received at the RSU.

[0120] Conflict warnings at intersections can reduce the risk of conflicts with VRUs and other road users. Useful conflict warnings need to be accurate and precise, but also targeted. Warnings should be given to vehicle operators when they are really needed. Providing warnings for all detected conflicts may not really help operators prevent conflicts. Too many warnings may overwhelm operators or distract them from critical conflicts. On the other hand, complex traffic situations may distract vehicle operators from situations that may be critical to VRU safety.

[0121] Next, the following technology is described, which can be used to identify or otherwise model which driving situations (e.g., paths through intersections) are more critical for safety warnings or notifications than other paths. Knowing this, targeted warnings or notifications can be delivered to (e.g., networked) vehicles while avoiding or minimizing less useful warnings. The technology can use a database that includes paths of intersections that are identified as more critical than other paths. The database can be stored in a storage device or memory located at the MEC 310, or in a storage device or memory of an RSU for a given intersection.

[0122] You can refer to Fig.10 The four-way intersection 1000 of FIG. 1 is used to illustrate an example of identifying more critical paths and the contents of the database. Typically, the identified paths are paths where the operator tends to be distracted from the VRU in favor of other road users. In this case, additional attention from the operator may be desired. In a conventional intersection (such as intersection 1000, etc.) where a vehicle is traveling in the right lane, the operator may not be aware of the VRU (e.g., non-motor vehicle user) when navigating a (e.g., unprotected) left turn because the operator is more focused on oncoming traffic. Fig.10 The direction of travel of vehicles in the lanes of the intersection is indicated by solid lines. Fig.10 As shown by the dashed lines in , there are four left turns that the vehicle can take to pass through the intersection 1000. Therefore, as shown in Table 1 below, there are four possible paths that the vehicle can take to pass through the intersection 1000 by turning left.

[0123] Table I

[0124] path Enter leave First left turn Lane 4 Lane 7 Second left turn Lane 2 Lane 5 The third left Lane 8 Lane 3 Fourth left turn Lane 6 Lane 1

[0125] In this implementation, these paths are more critical than the four through paths from lane 4 to lane 1, from lane 2 to lane 7, from lane 8 to lane 5, and from lane 6 to lane 3 through intersection 1000, and are more critical than the four right turn paths from lane 4 to lane 3, from lane 2 to lane 1, from lane 8 to lane 7, and from lane 6 to lane 5 through intersection 1000. In other implementations, the right turn paths may also be considered more critical than the four through paths.

[0126] In operation, an intended path for a networked vehicle, such as networked vehicle 302, may be received. As described above, the signal INTENT may be used to generate the intended path. In some implementations, a predicted path may be received in place of the intended path. As described above, a predicted path may be generated using sequential signals including location, heading, etc., from networked vehicle 302 (e.g., optionally combined into a shared world model such as SWM 314), infrastructure sensors (such as infrastructure cameras 306), or both. The intended path determines (defines, identifies) both the entry lane and the exit lane of the vehicle. The combination of the entry lane and the exit lane for the intersection may then be compared to the intended path to determine whether the path is in the database as a path that requires additional driver or operator attention.

[0127] If the combination is within the database, the path may be marked or otherwise identified within a conflict detection process (such as that performed by conflict detection module 316) for additional consideration. Fig.10 For example, if the vehicle is taking a path from lane 2 to lane 5, the path will be marked because it is in the database as shown in Table 1. In contrast, if the vehicle is taking a path from lane 2 to lane 7, the path will not be marked.

[0128] Once a path is identified for conflict detection processing, additional consideration may be given to the path. That is, the path uses a notification process that is different from the standard notification process. For example, the notification threshold may be modified so that the conflict detection module 316 provides earlier notification of the presence of the VRU to the operator of the networked vehicle than the conflict detection module 316 would for other paths. In some implementations, this may be achieved by reducing the maximum deceleration value previously described. In other implementations, the additional consideration given to the path may correspond to providing a notification based on the VRU being within a defined distance from the networked vehicle, without regard to whether a potential conflict resulting from conflict detection exists.

[0129] Fig.10 and Table I presents an intersection by example. Return to Reference Figure 8 , showing an example of a three-way intersection 800. In this example, there is an unprotected left turn because the street that pedestrian 808 is crossing has a stop sign (as can be seen by the stop line). Therefore, the database includes an entry. Vehicle 802 is taking a left turn as indicated by arrow 804, which corresponds to the path identified in the database for intersection 800. The conflict detection process issues a targeted warning or notification 830 based on the criteria for the path in the database, which is different from the criteria for the straight-ahead path of vehicle 802 or for a vehicle approaching the stop line in another direction.

[0130] It is unnecessary to detect potential collisions or conflicts and send warnings for all paths through the intersection. All such warnings or notifications may overwhelm or distract the operator. According to the teachings of this article, the driver attention model (e.g., using a database) includes the path that the operator may be distracted from the VRU to favor other road users. The path of the networked vehicle included in this is identified so that the operator can give additional attention to the VRU. The attention model is easy to build and easy to maintain, so the model is easily adapted to different intersections. In addition, the model can be easily adjusted based on the statistics of accidents at the intersection, making the system both flexible and robust.

[0131] The above description describes road users that are relatively easy to detect. Some road users (particularly VRUs) may be difficult to detect. This makes it difficult to accurately target notifications.

[0132] For example, occlusion is important for the safety of VRUs at intersections. A VRU that is not easily visible to the operator or cannot be easily detected by onboard sensors may result in a higher risk of collision at intersections. Fig.11 Techniques for detecting whether a VRU is obscured from a vehicle and sending an early warning to the vehicle to reduce the risk of a collision between the vehicle and the obscured VRU at an intersection are described. Fig.11 An intersection is shown integrated with the system 300. However, the technique may be used with only the RSUs at a given intersection.

[0133] Generally, if the RSU can detect the positions of all road users (including dynamic networked road users and non-networked road users) at the intersection on a two-dimensional (2D) plane (such as Fig.11 The RSU may also sense the environment around the intersection, such as static obstacles (buildings, infrastructure, parked vehicles, etc.), in addition to dynamic obstacles. As initially described, this may include the location, shape, and size of each obstacle, as well as other information.

[0134] Typically, once the obstacles and positions are known, it is possible to determine if there is an occlusion between two objects by checking if the line of sight between the two objects is blocked by a static or dynamic obstacle. A conflict warning can then be targeted to the occluded road user.

[0135] Specifically, and with reference to Fig.11In the example of FIG. 1 , the road users include a networked vehicle 302 and a pedestrian 304 as a moving obstacle. Another road user is a parked vehicle 1102. The intended path of the networked vehicle 302 is shown by waypoint 1104. The intended path can be determined using the signal INTENT as described above. In order to check whether a road user is occluded from another road user, the position of each road user is identified. Thereafter, a straight line segment between two positions is calculated. Fig.11 , straight line segment 1106 extends beyond the two initial positions of the networked vehicle 302 and the pedestrian 304 for clarity.

[0136] Whether a calculated line segment (such as line segment 1106 in this example) intersects any other moving or stationary obstacles at the intersection determines whether the road user is obscured from another road user. Fig.11 In the example, pedestrian 304 is marked as being occluded from connected vehicle 302 because there is an intersection between stationary (parked) vehicle 1102 and line segment 1106. Targeted notifications may then be issued to connected vehicle 302, pedestrian 304, or both. This process may be repeated over time using updated positions of road users and line segment(s).

[0137] To minimize notifications, notifications may be omitted when there is a clear line of sight (e.g., no intersection between a line segment and an obstacle). In some implementations, notifications may still be issued when a target deceleration is exceeded in the case of a potential conflict, as previously described. Utilizing this occlusion model, conflict warnings may be more targeted to obscured road users. These targeted warnings may increase the usability of the conflict warning system.

[0138] FIG. 12A to FIG. 12C 2 shows an example of a notification that may be issued when a conflict is detected, such as by the conflict detection module 316 or a processor of the RSU. Fig.11 In the examples of FIG. 1 , the conflict detection module 316 or the processor of the RSU may determine that there is a potential conflict between the connected vehicle 302 and the pedestrian 304 within the intersection 1100. In each of these examples, the connected vehicle 302 is expected to turn right at the intersection, and the pedestrian 304 is on a sidewalk adjacent to the road or crossing the road after turning right.

[0139] Fig. 12A is from Figure 3 An example of a notification (such as notification 302b) issued by the conflict detection module 315 of FIG. 302b to a networked vehicle. The notification is a map display notification showing possible paths through the intersection and the relationship of pedestrians to the path on the left, and a notification showing pedestrians ahead on the right. Fig. 12Bis another example of a notification for the same condition using a heads-up display. Each of these notifications can be sent to the operator of a networked vehicle using a cellular network. Fig. 12C A third example uses a cellular network connection between MEC 310 and a mobile phone. Fig. 12C The example of providing notification 302b to the networked vehicle 302. However, unlike using Fig. 12A and Fig. 12B This is less desirable than the example of notifying the networked vehicle 302. Fig. 12C The example is preferably used from Figure 3 The conflict detection module 315 issues a notification (such as notification 304b) to the pedestrian 304.

[0140] Fig.11 The illustrated technique does not rely on sensory data from the vehicle, although such sensory data may be used as described above with respect to the MEC 310. Instead, the occlusion model may use only detections from infrastructure sensors such as at the RSUs and the basic geometry / physics. Thus, the technique may be generally applicable to all road users. In some implementations, unobstructed road users may be filtered prior to determining potential conflicts between road users. By such filtering, the computations required to check for conflicts between road users may be reduced.

[0141] In the above description, the perspective from a road user of interest (e.g., an ego vehicle such as networked vehicle 302) is unrestricted. Typically, occlusion is determined if the line of sight is blocked by an obstacle. In some implementations, instead of simply assuming that the perspective from the vehicle is unrestricted, the line of sight may be further restricted to a particular angular range. For example, the angular range may depend on a model of the perspective of a human driver. The angular range may be restricted to +60 degrees to -60 degrees relative to the vehicle heading.

[0142] In implementations where line of sight is limited, eye tracking sensors may be utilized to more accurately determine the human driver's perspective. If the eyes can be tracked using sensors within the vehicle and shared with the RSU or MEC 310, occlusion detection may be more accurate. In an example, wireless communications such as cellular communications may be used to measure and transmit the direction of the operator's gaze relative to the heading of the vehicle. The processor of the RSU or MEC 310 may infer the angular range of the line of sight from the relative angle and heading angle of the vehicle. In some implementations, eye tracking may continuously or periodically sense the direction of the gaze relative to the heading of the vehicle, and the inference of the angular range may be similarly updated.

[0143] In some implementations, the human perspective model may be omitted or supplemented. That is, the above relies on the ability to infer line of sight based on a (e.g., world) model using observations made by (one or more) infrastructure sensors at the intersection. In practice, technical limitations of (one or more) sensors may result in the model being insufficient to detect all occlusions or filter out non-occlusions. Instead of or in addition to sensor data, what a human driver or operator can see may be based on perceptual data from onboard sensors. If a vehicle has onboard sensors and perceptual data from the onboard sensors can be shared, more accurate perspectives from the vehicle may be utilized to further improve occlusion detection by integrating observations from the onboard sensors.

[0144] While occlusion detection is described for use in targeted warnings with respect to an operator of a vehicle, occlusion detection may also be used by automated vehicles to increase situational awareness around or in intersections.

[0145] According to some aspects of the teachings herein, a system for intersection collision avoidance may include a processor. The processor may include a shared world model configured to receive signals from at least two road users near an intersection within a vehicle transportation network, wherein the at least two road users include a self-vehicle, and the shared world model is an output of a shared world model generation system. The shared world model generation system includes an object association module and an object fusion module, the object association module associates location information within a corresponding message forming a signal with a corresponding sensing object over time, and the object fusion module is configured to merge the data of the at least two sensing objects to identify the location of the same road user when the at least two sensing objects correspond to the same road user. The processing of the object association module is decoupled from the processing of the object fusion module, so that the speed of the generation of the shared world model is limited by the fastest sensor providing the signal rather than the slowest sensor providing the signal. The processor may also include a conflict detection module, which receives object information from the shared world model, detects a potential future collision between the self-vehicle and another road user among the at least two road users, and transmits a notification of the potential future collision to the self-vehicle.

[0146] In certain variations of the system, the signals from at least two road users include asynchronous signals received at a sensing and filtering module of a shared world model generation system, the sensing and filtering module generates asynchronous detections of objects from the asynchronous signals, and transmits the asynchronous detections to an object fusion module simultaneously with transmitting the asynchronous detections to an interpolator of the shared world model generation system, and the interpolator uses the asynchronous detections to generate synchronized outputs for respective objects to an object association module and an object fusion module.

[0147] In certain variations of the system, the signal from the self-vehicle includes an intention signal (the intention signal includes a set of driving goals), and the intention signal is generated based on at least one of a condition of a turn signal of the self-vehicle and a destination setting of the self-vehicle.

[0148] In some variations of the system, the collision detection module receives the intention signal and uses the intention signal to detect a potential future collision.

[0149] According to some aspects of the teachings herein, a system for intersection collision avoidance may include a processor. The processor may be configured to: receive a first signal identifying a location of a first road user near an intersection within a vehicle transportation network, wherein the first road user is a self-propelled vehicle connected to a cellular network; receive a second signal identifying a location of a second road user near the intersection, wherein the second road user is a non-motorized road user; receive at least one of a condition of a turn signal of the self-propelled vehicle and a destination setting of the self-propelled vehicle; define a conflict zone for the intersection, wherein the conflict zone is an area of ​​the intersection where there is a higher probability of a non-motorized road user colliding with a motorized road user; generate an intended path for the self-propelled vehicle to cross the zone using the first signal and at least one of the condition of the turn signal of the self-propelled vehicle and the destination setting of the self-propelled vehicle; detect a potential future collision between the self-propelled vehicle and the non-motorized road user based on any point where the self-propelled vehicle and the non-motorized road user cross the zone at the same time during a look-ahead period; and transmit a notification of the potential future collision to the self-propelled vehicle over the cellular network.

[0150] In some variations of the system, the non-motorized road users are pedestrians.

[0151] In certain variations of the system, the processor may be configured to enable transmission of a notification of a potential future collision to a non-motorized road user.

[0152] In certain variations of the system, the processor can be configured to: receive a third signal identifying the location of a third road user near the intersection, wherein the third road user is a motorized road user that is not connected to a cellular network; use the third signal to generate a predicted path for the third road user to cross the zone; and detect whether the third road user crosses the zone at the same time as the self-propelled vehicle and the non-motorized road user during a look-ahead period.

[0153] According to some aspects of the teachings herein, a system for intersection collision avoidance may include a processor. The processor may be configured to: receive a first signal identifying a path through an intersection within a vehicle transportation network for a first road user, wherein the first road user is a self-propelled vehicle connected to a cellular network; compare a combination of entry lanes and exit lanes of the path to a database storing combinations of entry lanes and exit lanes of intersections; identify the path as a path requiring a notification process different from a standard notification process based on a match between the combination of the path and the combination of the intersection; receive a second signal identifying a location of a second road user near the intersection, wherein the second road user is a non-motorized road user; and transmit a notification of the presence of the second road user to the self-propelled vehicle over the cellular network based on the notification process and the location of the second road user.

[0154] In some variations of the system, the non-motorized road users are pedestrians.

[0155] In certain variations of the system, the system includes a roadside unit that supports the infrastructure sensor and houses the processor.

[0156] In some variations of the system, the route is an intended route based on at least one of a turn signal and a destination of the first road user.

[0157] According to some aspects of the teachings herein, a system for intersection collision avoidance may include a processor. The processor may be configured to: receive a first signal identifying a location of a first road user near an intersection within a vehicle transportation network, wherein the first road user is a self-propelled vehicle connected to a cellular network; receive a second signal identifying a location of a second road user near the intersection; define a straight line segment between the first road user and the second road user in a two-dimensional plane; determine whether the straight line segment intersects an obstacle between the first road user and the second road user; and if the straight line segment intersects the obstacle, transmit a notification of the presence of the obscured second road user to the first road user over the cellular network.

[0158] In certain variations of the system, the system includes a roadside unit including an infrastructure sensor, and the processor is coupled to the infrastructure sensor, and the first signal and the second signal are generated by the infrastructure sensor.

[0159] In certain variations of the system, the processor is configured to transmit a notification of the presence of the obscured second road user to the second road user over the cellular network if the straight segment intersects the obstacle.

[0160] In this document, the terms "passenger", "driver" or "operator" can be used interchangeably. As used herein, the terms "processor", "computer" or "computing device" include any unit or combination of units capable of performing any method disclosed herein or any one or more than one part thereof.

[0161] As used herein, the term "instruction" may include instructions or expressions for performing any method disclosed herein or one or more than one arbitrary part thereof, and may be implemented in hardware, software, or any combination thereof. For example, an instruction may be implemented as information stored in a memory (such as a computer program, etc.), which may be executed by a processor to perform any of the various methods, algorithms, aspects, or combinations thereof as described herein. In some implementations, an instruction or a portion thereof may be implemented as a dedicated processor or circuit, which may include dedicated hardware for performing any of the methods, algorithms, aspects, or combinations thereof as described herein. In some implementations, a portion of an instruction may be distributed across multiple processors on a single device or across multiple devices, which may communicate directly or across a network (such as a local area network, a wide area network, the Internet, or a combination thereof, etc.).

[0162] As used herein, the terms "example", "embodiment", "implementation", "aspect", "feature" or "element" indicate use as an example, instance or illustration. Unless expressly indicated otherwise, any example, embodiment, implementation, aspect, feature or element is independent of each other example, embodiment, implementation, aspect, feature or element and can be used in combination with any other example, embodiment, implementation, aspect, feature or element.

[0163] As used herein, the terms "determine" and "identify" or any variations thereof include selecting, ascertaining, calculating, searching, receiving, determining, establishing, obtaining, or otherwise identifying or determining in any manner using one or more of the devices shown and described herein.

[0164] As used herein, the term "or" is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless specified otherwise or the context clearly indicates otherwise, "X includes A or B" is intended to indicate any of its natural inclusive permutations. If X includes A; X includes B; or X includes both A and B, then "X includes A or B" is satisfied under any of the foregoing instances. In addition, the articles "a" and "an" used in this application and the appended claims should generally be understood to mean "one or more than one" unless specified otherwise or clear from the context to be directed to a singular form.

[0165] In addition, for simplicity of explanation, although the accompanying drawings and description herein may include the sequence or series of operation or stage, the key element of method disclosed herein may occur in various orders or occur in parallel. Additionally, the key element of method disclosed herein may occur with other key elements not clearly presented and described herein. In addition, all key elements of method described herein may not be required to realize method according to the present invention. Although aspects, features and key elements are described in this article with specific combinations, each aspect, feature or key element may be used independently, or may be used in various combinations with other aspects, features and / or key elements or in various combinations without other aspects, features and / or key elements.

[0166] While the disclosed technology has been described in conjunction with certain embodiments, it should be understood that the disclosed technology is not limited to those embodiments, but, on the contrary, is intended to cover various modifications and equivalent arrangements included within the scope of the appended claims, which scope is to be given the broadest interpretation allowed by law.

Claims

1. A system for avoiding collision at an intersection, comprising: Cellular transceivers used in cellular networks; as well as A processor for multi-access edge computing at a cellular access point, the processor comprising: a shared world model configured to receive, via the cellular transceiver, signals associated with at least two road users proximate an intersection within a vehicle transportation network, wherein the at least two road users include an ego vehicle and wherein the signals conform to a standards-based communication protocol; and A collision detection module is configured to receive object information from the shared world model, determine a potential future collision between the ego-vehicle and another road user among the at least two road users, and transmit a notification of the potential future collision to the ego-vehicle over the cellular network.

2. The system according to claim 1, wherein: The standards-based communication protocols include SAE2735.

3. The system according to claim 1, wherein: The other road users are non-motorized road users, and the conflict detection module is configured to: Notification of the potential future collision is transmitted over the cellular network to cellular enabled devices supported by the other road users.

4. The system according to claim 1, wherein: The signal includes an intent signal, and the signal is transmitted to the cellular transceiver using SAE2735, the intent signal including at least one of a direction indicated by a turn signal of the self-propelled vehicle and a destination setting of the self-propelled vehicle.

5. The system according to claim 4, wherein: The signal of intent is received as an encoded signal converted from a JSON string generated by the self-vehicle, and the system comprises: A signal interface is used to receive the encoded signal from the cellular transceiver and convert the encoded signal into a format usable by the processor.

6. The system according to claim 1, wherein: The signal includes an intention signal including at least one of a direction indicated by a turn signal of the self-propelled vehicle and a destination setting of the self-propelled vehicle, and The shared world model is configured to determine an intended path for the self-propelled vehicle and to supply the intended path as part of the object information to the collision detection module.

7. The system according to claim 6, wherein: The shared world model is configured as follows: upon receiving the direction of the turn signal, generating a possible intended path of the self-propelled vehicle relative to the intersection using a high-definition map and the direction indicated by the turn signal; upon receiving the destination setting, generating a possible intended path of the self-propelled vehicle relative to the intersection using the high-definition map and the destination setting; In the case where the direction indicated by the turn signal and the destination setting are each received: comparing the direction indicated by the turn signal with a possible intended path generated using the high-definition map and the destination setting; as well as Based on a result of the comparison, selecting an intended path for the self-propelled vehicle as a possible intended path generated using the high-definition map and the destination setting or a possible intended path generated using the high-definition map and a direction indicated by the turn signal; as well as A set of driving objectives for the self-propelled vehicle relative to the intersection that is consistent with the intended path is transmitted to the conflict detection module.

8. The system according to claim 7, wherein: Selecting the intent path includes: In the event that the direction matches a possible intended path generated using the high-definition map and the destination setting, selecting the possible intended path generated using the high-definition map and the destination setting as the intended path for the self-propelled vehicle; and In the event that the directions do not match a possible intended path generated using the HD map and the destination, the possible intended path generated using the HD map and the directions is selected as the intended path of the self-propelled vehicle.

9. The system according to claim 7, wherein: The processor is configured to: upon receiving the direction indicated by the turn signal and without receiving the destination setting, selecting a possible intended path generated using the high-definition map and the direction as the intended path of the self-propelled vehicle; as well as In the event that the direction of the turn signal is not received and the destination setting is received, a possible intended path generated using the high-definition map and the destination setting is selected as the intended path of the self-propelled vehicle.

10. The system according to claim 1, wherein: The shared world model is configured to determine an intended path for the ego vehicle and to supply the intended path along with the object information as a set of driving goals to the conflict detection module, and The collision detection module receives the set of driving goals and uses the set of driving goals to determine the potential future collision.

11. The system according to claim 1, wherein: The shared world model is configured to receive signals at the cellular transceiver from infrastructure sensors monitoring at least a portion of the intersection, and Signals from the infrastructure sensors conform to the standards-based communication protocol.

12. The system according to claim 11, wherein: The shared world model is configured to determine, for a look-ahead period, predicted paths of the at least two road users, using signals associated with the at least two road users. The signals associated with the at least two road users include signals received from the self-propelled vehicle and signals from the infrastructure sensors.

13. The system of claim 1, wherein: The processor is configured to control the cellular transceiver to transmit signals associated with the at least two road users over the cellular network to a shared world model of the autonomous vehicle near the intersection.

14. The system of claim 1, wherein: The shared world model is configured to use at least a portion of the signals to determine a predicted path for the self-propelled vehicle; The predicted path passes through the intersection; the signal identifies a location of a non-motorized road user of the at least two road users; and The conflict detection module is configured to: comparing the combination of an entering lane and an exiting lane of the predicted path with a database storing combinations of an entering lane and an exiting lane of the intersection; identifying whether the predicted path is a path requiring a notification process different from a standard notification process based on a match between the combination of the predicted paths and the combination of intersections; in the event that the predicted route is a route that requires a notification process different from the standard notification process, transmitting a notification of the presence of the non-motorized road user to the self-propelled vehicle based on the notification process and the location of the non-motorized road user; Otherwise, a determination is made as to whether the standard notification process should provide notification of the presence of the non-motorized road user to the self-propelled vehicle based on the location of the non-motorized road user.

15. The system of claim 14, wherein: The non-motorized road user carries a cellular device, and the conflict detection module is configured to: A notification of the presence of the self-propelled vehicle is transmitted to the non-motorized road user over the cellular network and toward the cellular device based on the location of the non-motorized road user.

16. A method for intersection collision avoidance, comprising: receiving, by a cellular transceiver used by a cellular network, a signal associated with at least two road users proximate an intersection within a vehicle transportation network at a shared world model, wherein the at least two road users include an ego vehicle and the signal conforms to a standards-based communication protocol; receiving object information from the shared world model at a conflict detection module; determining, by the collision detection module, a potential future collision between the self-propelled vehicle and another road user among the at least two road users; and Notification of the potential future collision is transmitted by the collision detection module to the self-propelled vehicle over the cellular network, wherein the shared world model and the collision detection module are implemented by a processor for multi-access edge computing located at a cellular access point.

17. The method according to claim 16, wherein: Receiving the signal comprises: receiving a first signal identifying a location of the self-propelled vehicle; and receiving a second signal identifying a location of the other road user, wherein the other road user is a non-motorized road user, and the method comprises: Generating the object information by the shared world model includes: generating a predicted path for the self-propelled vehicle using the first signal; and generating a predicted path of the other road user using the second signal; The conflict detection module defines a danger zone at the intersection, wherein: The danger zone is an area at the intersection where non-motorized road users have a higher probability of conflict with motorized road users, and Determining a potential future collision between the ego vehicle and the other road user includes determining the potential future collision based on any point in the look-ahead period where the predicted path of the ego vehicle and the predicted path of the other road user cross the danger zone at the same time.

18. The method according to claim 16, wherein: The other road users are non-motorized road users, and the method comprises: Notification of the potential future collision is transmitted over the cellular network to cellular enabled devices supported by the other road users.

19. The method according to claim 16, wherein: Receiving the signal includes receiving sensor data from an infrastructure sensor monitoring at least a portion of the intersection, and wherein the infrastructure sensor is housed by a roadside unit.

20. The method according to claim 16, wherein: Receiving the signal comprises: receiving a signal identifying a location of the self-propelled vehicle from at least one of the self-propelled vehicle and an infrastructure sensor monitoring at least a portion of the intersection; and receiving a signal identifying a location of a non-motorized road user from at least two road users and a cellular device supported by the non-motorized road user and the infrastructure sensor, and the method comprising: Using the location of the ego-transport vehicle and the location of the non-motorized road user, defining a straight line segment between the ego-transport vehicle and the non-motorized road user in a two-dimensional plane; determining that the straight line segment intersects an obstacle between the self-propelled vehicle and the non-motorized road user; and In response to the determination, a notification is transmitted to the self-propelled vehicle that the non-motorized road user is obscured.

Citation Information

Patent Citations

  • Non-signal control road intersection collision early warning method based on V2I communication

    CN113593273A

  • Vehicle to pedestrian communication system and method

    US20150035685A1

  • Obstacle-Information-Managing Device

    US20170046958A1

  • 3D Occlusion Reasoning for Accident Avoidance

    US20210271249A1