Vehicle interaction method, device, electronic device and autonomous driving vehicle

Abstract

The present disclosure provides a vehicle interaction method, device, electronic device and autonomous driving vehicle, which relate to the field of data processing, and specifically to the field of autonomous driving and map technology. The specific implementation scheme is: obtaining a first identifier of the lane where the vehicle is located; in the case where it is determined that there is a target area on the vehicle's route based on the adjacent relationship between the preset area and the lane, obtaining description information of the target area, the target area is an area in the preset area that matches the first identifier, the preset area is an area that is inaccessible to vehicles and is located at an intersection, and the description information is used to characterize the properties of the target area; in the case where a target object is monitored to exist in the target area, based on the description information, the route of the target object is predicted to obtain a target route, and the target object is an object that can pass through the target area; based on the target route, interaction with the target object is performed.

Description

Technical Field

[0001] The present disclosure relates to the field of data processing technology, in particular to the field of autonomous driving and map technology, and specifically to a vehicle interaction method, device, electronic device and autonomous driving vehicle. Background Art

[0002] During the driving process, vehicles such as autonomous vehicles interact with pedestrians, non-motorized vehicles, etc. in addition to the interactions between the vehicle and the road, the vehicle and road test equipment, and the vehicle and other motor vehicles.

[0003] At present, when the vehicle senses and recognizes that pedestrians and non-motor vehicles are passing through lanes that have been marked on the high-precision map, the travel routes of pedestrians and non-motor vehicles can be predicted based on the lane information on the high-precision map. Summary of the invention

[0004] The present disclosure provides a vehicle interaction method, device, electronic equipment and an autonomous driving vehicle.

[0005] According to a first aspect of the present disclosure, a vehicle interaction method is provided, comprising:

[0006] Obtain the first identifier of the lane where the vehicle is located;

[0007] In the case where it is determined that there is a target area on the passage route of the vehicle based on the adjacent relationship between the preset area and the lane, obtaining description information of the target area, the target area is an area in the preset area that matches the first identifier, the preset area is an area that is not passable by the vehicle and is located at an intersection, and the description information is used to characterize the attributes of the target area;

[0008] In the case where a target object is detected in the target area, a passing route of the target object is predicted based on the description information to obtain a target passing route, wherein the target object is an object that can pass through the target area;

[0009] Interaction with the target object is performed based on the target travel route.

[0010] According to a second aspect of the present disclosure, a vehicle interaction device is provided, comprising:

[0011] A first acquisition module, used to acquire a first identifier of a lane where the vehicle is located;

[0012] A second acquisition module is used to acquire description information of the target area when it is determined that there is a target area on the passage route of the vehicle based on the adjacent relationship between the preset area and the lane, wherein the target area is an area in the preset area that matches the first identifier, the preset area is an area at an intersection where the vehicle is not passable, and the description information is used to characterize the attributes of the target area;

[0013] A prediction module, configured to predict a passage route of the target object based on the description information to obtain a target passage route when a target object is detected to exist in the target area, wherein the target object is an object that can pass through the target area;

[0014] An interaction module is used to interact with the target object based on the target travel route.

[0015] According to a third aspect of the present disclosure, there is provided an electronic device, including:

[0016] at least one processor; and

[0017] a memory communicatively connected to at least one processor; wherein,

[0018] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform any method in the first aspect.

[0019] According to a fourth aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to cause a computer to execute any one of the methods in the first aspect.

[0020] According to a fifth aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements any one of the methods in the first aspect when executed by a processor.

[0021] According to a sixth aspect of the present disclosure, an autonomous driving vehicle is provided, comprising the electronic device as described in the third aspect.

[0022] The technology disclosed in the present invention solves the problem of low security when interacting with objects located in a preset area in the related art, thereby improving the security of interacting with objects located in the preset area.

[0023] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure.

[0025] Figure 1 is a flow chart of a vehicle interaction method according to a first embodiment of the present disclosure;

[0026] Figure 2 This is a schematic diagram of the driving of an autonomous vehicle in a safety island scenario;

[0027] Figure 3 is a structural schematic diagram of a vehicle interaction device according to a second embodiment of the present disclosure;

[0028] Figure 4 is a schematic block diagram of an example electronic device for implementing an embodiment of the present disclosure. DETAILED DESCRIPTION

[0029] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0030] First embodiment

[0031] like Figure 1 As shown, the present disclosure provides a vehicle interaction method, comprising the following steps:

[0032] Step S101: Obtain a first identifier of a lane where a vehicle is located.

[0033] In this embodiment, the vehicle interaction method relates to the field of data processing technology, in particular to the field of autonomous driving and map technology, and can be widely used in autonomous driving scenarios. The vehicle interaction method of the embodiment of the present disclosure can be executed by the vehicle interaction device of the embodiment of the present disclosure. The vehicle interaction device of the embodiment of the present disclosure can be configured in an autonomous driving vehicle to execute the vehicle interaction method of the embodiment of the present disclosure.

[0034] The vehicle may be a motor vehicle, such as an autonomous vehicle. Taking the autonomous vehicle as an example, it may include a vehicle-side regulation and control module, wherein the vehicle-side regulation and control module may predict the passage route of obstacle objects around the autonomous vehicle, so as to interact with the obstacle objects based on the predicted passage route.

[0035] Autonomous driving vehicles usually travel on lanes that have been marked on maps, such as high-precision maps. The vehicle's location can be obtained through positioning technology, and the lane marking of the autonomous driving vehicle's location can be obtained based on the high-precision map to obtain a first marking.

[0036] Step S102: When it is determined that there is a target area on the vehicle's route based on the adjacent relationship between the preset area and the lane, obtain description information of the target area, where the target area is an area in the preset area that matches the first identifier, and the preset area is an area that is not passable by the vehicle and is located at an intersection, and the description information is used to characterize the attributes of the target area.

[0037] In this embodiment, the vehicle-side control module can predict the route of obstacles in a preset area around the autonomous driving vehicle. The preset area may refer to an area where vehicles, i.e., motor vehicles, cannot pass and is located at an intersection.

[0038] The preset area is usually an area at the intersection where pedestrians or non-motorized vehicles are planned to cross the intersection safely. It can be called a safety island. That is, the vehicle-side regulation and control module can predict the routes of pedestrians and non-motorized vehicles on the safety island for the autonomous driving vehicle in the safety island scenario, so as to interact with the pedestrians and non-motorized vehicles on the safety island and avoid the risk of collision with the pedestrians and non-motorized vehicles on the safety island.

[0039] Figure 2 This is a schematic diagram of the driving of an autonomous vehicle in a safety island scenario, such as Figure 2 As shown, the autonomous driving vehicle 201 is located in the right turn lane of an intersection, where there is a safety island 202 with pedestrians passing through.

[0040] In the related technology, autonomous driving vehicles usually predict the routes of surrounding objects (such as pedestrians and non-motorized vehicles) based on the lane information on the high-precision map. If the surrounding objects are located on a safety island, since the high-precision map only provides the geometric information of the safety island and the intersection sign where the safety island is located, the autonomous driving vehicle can obtain the existence of a safety island at the intersection and the geometric position of the safety island from the high-precision map, but since the lane information of pedestrians and non-motorized vehicles on the safety island is unclear, it is impossible to predict the routes of pedestrians and non-motorized vehicles on the safety island based on the lane information, which may lead to the risk of collision between the autonomous driving vehicle and pedestrians and non-motorized vehicles on the safety island.

[0041] This embodiment can predict the routes of pedestrians and non-motorized vehicles in the safety island scene based on the description information of the safety island, so as to improve the interaction safety between the autonomous driving vehicle and the pedestrians and non-motorized vehicles on the safety island. The description information can be used to characterize the attributes of the safety island, such as purpose, type, opening position, adjacent relationship with the lane, and adjacent relationship with the crosswalk.

[0042] That is to say, in this embodiment, the high-precision map not only marks the geometric position of the safety island, but also additionally marks the description information of the safety island, so that the autonomous driving vehicle can predict the traffic routes of pedestrians and non-motorized vehicles on the safety island based on the description information of the safety island in the high-precision map.

[0043] The high-precision map can pre-mark the preset area, that is, the adjacent relationship between the safety island and the lane (the adjacent relationship can be located in the description information of the safety island and is part of the safety island attribute). During the driving process of the autonomous driving vehicle, it can be determined based on the first identifier of the lane where the autonomous driving vehicle is located whether there is a target area in the adjacent relationship that matches the first identifier, that is, is adjacent to the lane of the autonomous driving vehicle. If so, it is necessary to start the route prediction process for pedestrians and non-motorized vehicles in the safety island scenario, and read the description information of the target area in the high-precision map.

[0044] In practical applications, the geometric position of the safety island can be combined with the adjacent relationship between the safety island and the lane to determine whether there is a target area on the vehicle's route. This can help autonomous driving vehicles accurately judge the safety island scenario.

[0045] Step S103: when it is monitored that there is a target object in the target area, a travel route of the target object is predicted based on the description information to obtain a target travel route, and the target object is an object that can pass through the target area.

[0046] In this step, the autonomous vehicle can monitor the surrounding objects through sensing devices such as cameras. If the target object is detected in the target area (the safety island around the autonomous vehicle), the target object's route can be predicted based on the description information of the target area to obtain the target route. The target object can be a pedestrian or a non-motorized vehicle.

[0047] The target passage route may include the passage route of the target object in the safety island, and the target passage route may reflect the relationship with the crosswalk at the intersection, such as which crosswalk at the intersection the target passage route crosses.

[0048] The target object's passage data in the safety island can be monitored, and the passage data can include the passage position, passage speed, and passage direction, etc. The passage route of the target object can be predicted by combining the passage data and the description information of the target area. In an optional embodiment, the passage route of the target object can be predicted based on the passage position of the target object and the opening position of the target area, such as the target passage route includes a line connecting the passage position of the target object to the opening position of the target area.

[0049] Step S104: interacting with the target object based on the target route.

[0050] In this step, the autonomous driving vehicle can confirm the target object's intention to cross the crosswalk on the autonomous driving vehicle's route based on the target route, so that the autonomous driving vehicle can slow down and give way in time to avoid the risk of collision.

[0051] If the target route crosses the crosswalk that the autonomous vehicle needs to pass, the autonomous vehicle can determine the target object's intention to cross the crosswalk based on the target object's traffic data (such as traffic position, traffic speed, traffic acceleration, etc.), so that the autonomous vehicle can slow down and give way in time to avoid collision risks. For example, if the target object's traffic position is at the opening of the target area and the traffic acceleration suddenly increases, the autonomous vehicle determines that the target object needs to accelerate to cross the crosswalk, and accordingly, the autonomous vehicle can decide to slow down and give way.

[0052] In this embodiment, by obtaining the first identification of the lane where the vehicle is located; in the case where it is determined that there is a target area on the passage route of the vehicle based on the adjacent relationship between the preset area and the lane, the description information of the target area is obtained, the target area is the area in the preset area that matches the first identification, the preset area is an area where the vehicle is not passable and is located at an intersection, and the description information is used to characterize the attributes of the target area; in the case where it is monitored that there is a target object in the target area, the passage route of the target object is predicted based on the description information to obtain the target passage route, and the target object is an object that can pass through the target area; based on the target passage route, interaction with the target object is performed. In this way, the passage route of pedestrians and non-motor vehicles on the safety island can be predicted through the description information of the safety island in the high-precision map, thereby improving the interaction safety of the autonomous driving vehicle with pedestrians and non-motor vehicles in the safety island scenario.

[0053] Optionally, the description information includes an opening position of the target area and an adjacent relationship between the target area and a crosswalk, and the step S103 specifically includes:

[0054] Determining a first passage route of the target object within the target area based on the opening position and the passage data of the target object within the target area;

[0055] Based on the adjacent relationship between the target area and the crosswalk, the first travel route is extended and calculated to obtain a target travel route.

[0056] In this embodiment, the descriptive information of the target area may include the opening position of the target area and the adjacent relationship between the target area and the crosswalk. The opening position can be used to identify the position on the edge of the safety island where non-motorized vehicles and pedestrians can enter and exit, and the adjacent relationship between the target area and the crosswalk is used to calculate the identification of the crosswalk closest to the target area.

[0057] In an optional embodiment, the first passage route of the target object in the target area can be determined based on the opening position and the passage data of the target object in the target area at at least one time. The first passage route can be a line connecting the passage position of the target object in the target area and the opening position.

[0058] For example, there are two opening positions in the target area, namely opening position A and opening position B. The autonomous driving vehicle monitors the pedestrian at position A in the target area at time 1, and its travel direction is from opening position A to opening position B, then the first travel route is determined to be from position A to opening position B.

[0059] For another example, the number of opening positions in the target area is three, namely, opening position A, opening position B, and opening position C, and the three opening positions are located in three different directions of the safety island, such as Figure 2 As shown, the safety island 202 includes an opening position 2021 (corresponding to opening position A), an opening position 2022 (corresponding to opening position B), and an opening position 2023 (corresponding to opening position C). The autonomous driving vehicle monitors the pedestrian at position A of the target area at time 1, and position A is a position near opening position A in the target area. As the pedestrian continues to move, the autonomous driving vehicle monitors the pedestrian at position B of the target area at time 2, and position B is a position near opening position B in the target area. It can be determined that the first passage route of the target object is to pass to opening position B.

[0060] In another optional embodiment, a pre-trained deep learning model can be used to input the opening position and the passage data of the target object in the target area into the deep learning model. Accordingly, the deep learning model can output the first passage route of the target object in the target area.

[0061] On the basis of obtaining the first passage route, the first passage route can be extended and calculated according to the adjacent relationship between the safety island and the crosswalk to determine which crosswalk the first passage route can cross and obtain the target passage route. In this way, the target passage route of pedestrians and non-motorized vehicles in the safety island scene can be predicted based on the description information.

[0062] Optionally, the description information further includes a type of the target area, where the type is used to indicate a passable location of the target object in the target area. The method further includes:

[0063] Based on the type, determining a route prediction strategy;

[0064] The determining, based on the opening position and the passage data of the target object in the target area, a first passage route of the target object in the target area includes:

[0065] Based on the opening position and the traffic data, the first traffic route is determined according to the route prediction strategy.

[0066] In this implementation, the description information may also include the type of the target area, which is used to indicate the location where the target object can pass in the target area, and can be used to distinguish the location where the safety island can enter and exit. There are two types, namely:

[0067] Limited exit, i.e. the island is partially covered with vegetation and has a paved surface inside that allows non-motorized vehicles and pedestrians to pass;

[0068] The free area, that is, the safety island, is not covered with vegetation and is paved inside, allowing non-motorized vehicles and pedestrians to pass.

[0069] For different types, the route prediction strategy can be different, and the autonomous driving vehicle can determine the route prediction strategy that matches the type of the target area. Accordingly, the first pass route can be determined based on the opening position and the traffic data according to the route prediction strategy that matches the type of the target area.

[0070] For example, for limited exits, since the routes accessible to pedestrians and non-motorized vehicles have been determined, the first accessible route can be determined from the accessible routes based on the location of the opening and the traffic data of the target object in the target area. Figure 2 , if the pedestrian is monitored to be near the opening position A in the target area, and the direction of travel is away from the exit position A, then the routes that the pedestrian can travel are along the paved road to the opening position B and along the paved road to the opening position C. As the pedestrian moves, if the pedestrian is monitored to be near the opening position C in the target area or the pedestrian's direction of travel is toward the opening position C, then it can be determined that the first route is along the paved road to the opening position C.

[0071] For another example, in the free area, since pedestrians and non-motorized vehicles can move freely, in this scenario, a deep learning model can be used to predict the first route of the target object in the target area based on the opening position and the traffic data of the target object in the target area.

[0072] In this way, different route prediction strategies can be used for different types of safety islands to predict the travel routes of pedestrians and non-motorized vehicles on the safety islands, thereby improving the accuracy of the travel route prediction.

[0073] Optionally, determining a first passage route of the target object in the target area based on the opening position and the passage data of the target object in the target area includes:

[0074] determining a candidate passage route of the target object in the target area based on the opening position and a first passage position of the target object in the target area, wherein the first passage position is a passage position of the target object at a first moment, and the passage data includes the first passage position;

[0075] When the number of the candidate passable routes is one, determining the candidate passable route as the first passable route;

[0076] When the number of the candidate routes is at least two, a first route is determined from the candidate routes based on a second route position of the target object in the target area and / or a route direction at the second route position, the second route position being the route position of the target object at a second moment, the second moment being later than the first moment, and the route data including the second route position and the route direction.

[0077] Safe islands for limited exit types, such as Figure 2 As shown, the autonomous driving vehicle is in a lane closest to the safety island. It recognizes the presence of a pedestrian on the safety island and calculates based on several frames of images obtained in a short period of time that the pedestrian's action intention is to enter from the opening position A and gradually pass into the safety island, which is represented by a dotted line.

[0078] According to the description information obtained from the high-precision map, the autonomous driving vehicle first realizes that there is a safety island next to the current lane and identifies the pedestrian on the safety island. Then, based on the safety island-related attributes provided by the high-precision map, it predicts that the pedestrian has two possible candidate routes, represented by solid lines, one of which will cross the lane where the unmanned vehicle is currently traveling at the crosswalk. As the pedestrian continues to move, the autonomous driving vehicle will determine the most likely route for the pedestrian from the candidate routes based on the target object's second passage position in the target area and / or the passage direction at the second passage position, and obtain the first passage route. In this way, the prediction of the first passage route of the target object in the safety island can be achieved based on the description information of the target area.

[0079] Optionally, the description information includes a purpose of the target area, and the purpose is used to indicate a type of object that is accessible to the target area. The method further includes:

[0080] Based on the purpose, determining an interaction strategy with the target object;

[0081] The step S104 specifically includes:

[0082] When it is determined based on the target passage route that the target object intends to cross a pedestrian crossing on the passage route of the vehicle, interaction with the target object is performed according to the interaction strategy.

[0083] In this implementation, the description information may include the purpose of the target area, which is used to distinguish the types of vulnerable road users that may appear on the safety island. The purpose may include two types, namely:

[0084] a) Pedestrians: The opening of the refuge island has a curb or steps, which only supports pedestrians;

[0085] b) Pedestrians and non-motorized vehicles: There is no height difference between the opening of the safety island and the motor vehicle road surface, and it supports the passage of pedestrians and non-motorized vehicles at the same time.

[0086] For different purposes, the interaction strategies between the autonomous driving vehicle and the objects on the safety island can be different. The autonomous driving vehicle can determine the interaction strategy that matches the purpose of the target area. Accordingly, based on the target route, the interaction with the target object can be performed according to the interaction strategy that matches the purpose of the target area.

[0087] For example, for a safety island that only allows pedestrians to pass, the autonomous driving vehicle can interact with the target object based on the pedestrian's passing characteristics (such as the pedestrian's passing speed is usually lower than the passing speed of non-motorized vehicles) when determining that the target object has the intention to cross the crosswalk on the vehicle's passing route based on the target passing route. Among them, it can be determined whether the target object has the intention to cross the crosswalk on the vehicle's passing route by matching the identification of the crosswalk in the target passing route and the identification of the crosswalk through which the vehicle's passing route passes. In the case of consistency, it is determined that the target object has the intention to cross the crosswalk on the vehicle's passing route.

[0088] For safety islands that allow both pedestrians and non-motorized vehicles to pass, the autonomous driving vehicle can identify the object type of the target object when it determines, based on the target travel route, that the target object has the intention of crossing the crosswalk on the vehicle's travel route. If the object type is a pedestrian, the autonomous driving vehicle can interact with the target object based on the pedestrian's travel characteristics; if the object type is a non-motorized vehicle, the autonomous driving vehicle can interact with the target object based on the non-motorized vehicle's travel characteristics.

[0089] In this way, different interaction strategies can be used to interact with pedestrians and non-motorized vehicles on the safety island according to different uses of the safety island, thereby improving the safety of interaction.

[0090] Second embodiment

[0091] like Figure 3 As shown, the present disclosure provides a vehicle interaction device 300, including:

[0092] A first acquisition module 301 is used to acquire a first identifier of a lane where the vehicle is located;

[0093] A second acquisition module 302 is used to acquire description information of the target area when it is determined that there is a target area on the passage route of the vehicle based on the adjacent relationship between the preset area and the lane, wherein the target area is an area in the preset area that matches the first identifier, the preset area is an area at an intersection where the vehicle is not passable, and the description information is used to characterize the attributes of the target area;

[0094] A prediction module 303 is used to predict a passage route of the target object based on the description information to obtain a target passage route when a target object is detected to exist in the target area, and the target object is an object that can pass through the target area;

[0095] The interaction module 304 is used to interact with the target object based on the target route.

[0096] Optionally, the description information includes an opening position of the target area and an adjacent relationship between the target area and a crosswalk, and the prediction module 303 includes:

[0097] a route determination unit, configured to determine a first passage route of the target object within the target area based on the opening position and the passage data of the target object within the target area;

[0098] The extension calculation unit is used to perform an extension calculation on the first travel route based on the adjacent relationship between the target area and the crosswalk to obtain a target travel route.

[0099] Optionally, the description information further includes a type of the target area, where the type is used to indicate a passable position of the target object in the target area, and the device further includes:

[0100] A first determination module, configured to determine a route prediction strategy based on the type;

[0101] The route determination unit is specifically configured to determine the first passage route according to the route prediction strategy based on the opening position and the passage data.

[0102] Optionally, the route determination unit is specifically configured to:

[0103] determining a candidate passage route of the target object in the target area based on the opening position and a first passage position of the target object in the target area, wherein the first passage position is a passage position of the target object at a first moment, and the passage data includes the first passage position;

[0104] When the number of the candidate passable routes is one, determining the candidate passable route as the first passable route;

[0105] When the number of the candidate routes is at least two, a first route is determined from the candidate routes based on a second route position of the target object in the target area and / or a route direction at the second route position, the second route position being the route position of the target object at a second moment, the second moment being later than the first moment, and the route data including the second route position and the route direction.

[0106] Optionally, the description information includes a purpose of the target area, where the purpose is used to indicate a type of object that is accessible to the target area, and the device further includes:

[0107] A second determination module, configured to determine an interaction strategy with the target object based on the usage;

[0108] The interaction module 304 is specifically configured to interact with the target object according to the interaction strategy when it is determined based on the target route that the target object intends to cross a crosswalk on the vehicle's route.

[0109] The vehicle interaction device 300 provided in the present disclosure can implement each process implemented in the vehicle interaction method embodiment and can achieve the same beneficial effects. To avoid repetition, it will not be described here.

[0110] In the technical solution of the present disclosure, the collection, storage, use, processing, transmission, provision and disclosure of user personal information involved are in compliance with the provisions of relevant laws and regulations and do not violate public order and good morals.

[0111] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium and a computer program product.

[0112] Figure 4A schematic block diagram of an example electronic device that can be used to implement an embodiment of the present disclosure is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present disclosure described and / or required herein.

[0113] like Figure 4 As shown, the device 400 includes a computing unit 401, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 402 or a computer program loaded from a storage unit 408 into a random access memory (RAM) 403. In the RAM 403, various programs and data required for the operation of the device 400 can also be stored. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0114] A number of components in the device 400 are connected to the I / O interface 405, including: an input unit 406, such as a keyboard, a mouse, etc.; an output unit 407, such as various types of displays, speakers, etc.; a storage unit 408, such as a disk, an optical disk, etc.; and a communication unit 409, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0115] The computing unit 401 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 401 performs the various methods and processes described above, such as the vehicle interaction method. For example, in some embodiments, the vehicle interaction method may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 408. In some embodiments, part or all of the computer program may be loaded and / or installed on the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded into the RAM 403 and executed by the computing unit 401, one or more steps of the vehicle interaction method described above may be performed. Alternatively, in other embodiments, the computing unit 401 may be configured to perform the vehicle interaction method in any other appropriate manner (e.g., by means of firmware).

[0116] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0117] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0118] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0119] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0120] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0121] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0122] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps recorded in this disclosure can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0123] The above specific implementations do not constitute a limitation on the protection scope of the present disclosure. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present disclosure shall be included in the protection scope of the present disclosure.

Claims

1. A vehicle interaction method, comprising: Obtain the first identifier of the lane where the vehicle is located; In the case where it is determined that there is a target area on the passage route of the vehicle based on the adjacent relationship between the preset area and the lane, obtaining description information of the target area, the target area is an area in the preset area that matches the first identifier, the preset area is an area that is not passable by the vehicle and is located at an intersection, and the description information is used to characterize the attributes of the target area; In the case where a target object is detected in the target area, a passing route of the target object is predicted based on the description information to obtain a target passing route, wherein the target object is an object that can pass through the target area; Interacting with the target object based on the target route; The description information includes the opening position of the target area and the adjacent relationship between the target area and the crosswalk, and the prediction of the passage route of the target object based on the description information to obtain the target passage route includes: Determining a first passage route of the target object within the target area based on the opening position and the passage data of the target object within the target area; Based on the adjacent relationship between the target area and the crosswalk, the first travel route is extended and calculated to obtain a target travel route.

2. The method according to claim 1, wherein: The description information further includes a type of the target area, where the type is used to indicate a location where the target object is accessible in the target area. The method further includes: Based on the type, determining a route prediction strategy; The determining, based on the opening position and the passage data of the target object in the target area, a first passage route of the target object in the target area comprises: Based on the opening position and the traffic data, the first traffic route is determined according to the route prediction strategy.

3. The method according to claim 1, wherein: The determining, based on the opening position and the passage data of the target object in the target area, a first passage route of the target object in the target area comprises: determining a candidate passage route for the target object in the target area based on the opening position and a first passage position of the target object in the target area, wherein the first passage position is a passage position of the target object at a first moment, and the passage data includes the first passage position; When the number of the candidate passable routes is one, determining the candidate passable route as the first passable route; When the number of the candidate routes is at least two, a first route is determined from the candidate routes based on a second route position of the target object in the target area and / or a route direction at the second route position, the second route position being the route position of the target object at a second moment, the second moment being later than the first moment, and the route data including the second route position and the route direction.

4. The method according to claim 1, wherein: The description information includes a purpose of the target area, and the purpose is used to indicate the type of objects that are accessible to the target area. The method further includes: Based on the purpose, determining an interaction strategy with the target object; The interacting with the target object based on the target travel route includes: When it is determined based on the target passage route that the target object intends to cross a pedestrian crossing on the passage route of the vehicle, interaction with the target object is performed according to the interaction strategy.

5. A vehicle interaction device, comprising: A first acquisition module, used to acquire a first identifier of a lane where the vehicle is located; A second acquisition module is used to acquire description information of the target area when it is determined that there is a target area on the passage route of the vehicle based on the adjacent relationship between the preset area and the lane, wherein the target area is an area in the preset area that matches the first identifier, the preset area is an area at an intersection where the vehicle is not passable, and the description information is used to characterize the attributes of the target area; A prediction module, configured to predict a passage route of the target object based on the description information to obtain a target passage route when a target object is detected to exist in the target area, wherein the target object is an object that can pass through the target area; An interaction module, used for interacting with the target object based on the target travel route; The description information includes the opening position of the target area and the adjacent relationship between the target area and the crosswalk, and the prediction module includes: a route determination unit, configured to determine a first passage route of the target object within the target area based on the opening position and the passage data of the target object within the target area; The extension calculation unit is used to perform an extension calculation on the first travel route based on the adjacent relationship between the target area and the crosswalk to obtain a target travel route.

6. The device according to claim 5, wherein: The description information further includes a type of the target area, where the type is used to indicate a location where the target object is accessible in the target area. The device further includes: A first determination module, configured to determine a route prediction strategy based on the type; The route determination unit is specifically configured to determine the first passage route according to the route prediction strategy based on the opening position and the passage data.

7. The device according to claim 5, wherein: The route determination unit is specifically used for: determining a candidate passage route for the target object in the target area based on the opening position and a first passage position of the target object in the target area, wherein the first passage position is a passage position of the target object at a first moment, and the passage data includes the first passage position; When the number of the candidate passable routes is one, determining the candidate passable route as the first passable route; When the number of the candidate routes is at least two, a first route is determined from the candidate routes based on a second route position of the target object in the target area and / or a route direction at the second route position, the second route position being the route position of the target object at a second moment, the second moment being later than the first moment, and the route data including the second route position and the route direction.

8. The device according to claim 5, wherein: The description information includes a purpose of the target area, and the purpose is used to indicate a type of object that is accessible to the target area. The device further includes: A second determination module, configured to determine an interaction strategy with the target object based on the usage; The interaction module is specifically configured to interact with the target object according to the interaction strategy when it is determined based on the target route that the target object intends to cross a crosswalk on the vehicle's route.

9. An electronic device, comprising: at least one processor; as well as a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 4.

10. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-4.

11. A computer program product, comprising a computer program, which, when executed by a processor, implements the method according to any one of claims 1 to 4.

12. An autonomous driving vehicle comprising the electronic device as claimed in claim 9.

Images