Data processing methods, devices, equipment, autonomous vehicles and media

Abstract

This disclosure provides data processing methods, devices, electronic devices, autonomous vehicles, storage media, and program products for autonomous vehicles, relating to the field of artificial intelligence technology, particularly to autonomous driving, the Internet of Things, intelligent transportation, cloud services, and high-precision maps. The specific implementation scheme is as follows: in response to determining that the vehicle is in the process of changing lanes, determining lane change scenario data; based on the lane change scenario data, determining the target lane change scenario category; based on the target lane change scenario category, determining target scenario data from the lane change scenario data; and based on the target scenario data, determining a lane change recognition result, the lane change recognition result being used to characterize whether the lane change process is in a safe state.

Description

Technical Field

[0001] This disclosure relates to the field of artificial intelligence technology, and in particular to the fields of autonomous driving, vehicle networking, intelligent transportation, cloud services, and high-precision maps, and especially to data processing methods, devices, electronic devices, autonomous vehicles, storage media, and software products for autonomous vehicles. Background Technology

[0002] Vehicles operating in autonomous driving mode can free occupants, especially the driver, from certain driving-related duties. When operating in autonomous driving mode, the vehicle can use onboard sensors to navigate to various locations, allowing the vehicle to operate with minimal human-machine interaction or in situations where there are no passengers.

[0003] Lane changing typically involves moving into the corresponding lane in response to a steering instruction, or changing lanes in response to an instruction to avoid road construction. However, in complex lane-changing scenarios, many dynamic obstacles may suddenly appear, preventing the vehicle from safely following the intended lane-changing trajectory. Summary of the Invention

[0004] This disclosure provides a data processing method, apparatus, electronic device, autonomous vehicle, storage medium, and program product for autonomous vehicles.

[0005] According to one aspect of this disclosure, a data processing method for an autonomous vehicle is provided, comprising: determining lane change scenario data in response to determining that the vehicle is in the process of changing lanes; determining a target lane change scenario category based on the lane change scenario data; determining target scenario data from the lane change scenario data based on the target lane change scenario category; and determining a lane change identification result based on the target scenario data, wherein the lane change identification result is used to characterize whether the lane change process is in a safe state.

[0006] According to another aspect of this disclosure, a data processing apparatus for an autonomous vehicle is provided, comprising: a response module for determining lane change scenario data in response to determining that the vehicle is in the process of changing lanes; a category determination module for determining a target lane change scenario category based on the lane change scenario data; a data determination module for determining target scenario data from the lane change scenario data based on the target lane change scenario category; and a result determination module for determining a lane change recognition result based on the target scenario data, wherein the lane change recognition result is used to characterize whether the lane change process is in a safe state.

[0007] According to another aspect of this disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as disclosed herein.

[0008] According to another aspect of this disclosure, a non-transitory computer-readable storage medium is provided storing computer instructions, wherein the computer instructions are used to cause the computer to perform the methods as disclosed herein.

[0009] According to another aspect of this disclosure, a computer program product is provided, including a computer program that, when executed by a processor, implements the method as disclosed herein.

[0010] According to another aspect of this disclosure, an autonomous vehicle is provided, including electronic devices as described above.

[0011] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of this disclosure, nor is it intended to limit the scope of this disclosure. Other features of this disclosure will become readily apparent from the following description. Attached Figure Description

[0012] The accompanying drawings are provided to better understand this solution and do not constitute a limitation of this disclosure. Wherein:

[0013] Figure 1 This illustration schematically shows an exemplary system architecture that can be applied to data processing methods and apparatus for autonomous vehicles according to embodiments of the present disclosure;

[0014] Figure 2 This diagram schematically illustrates an application scenario of a data processing method for autonomous vehicles according to embodiments of the present disclosure.

[0015] Figure 3 A flowchart illustrating a data processing method for an autonomous vehicle according to an embodiment of the present disclosure is shown schematically.

[0016] Figure 4 The illustration shows a flowchart of determining the target lane change scenario category according to an embodiment of the present disclosure;

[0017] Figure 5 A schematic flowchart of a data processing method for an autonomous vehicle according to an embodiment of the present disclosure is shown.

[0018] Figure 6 A block diagram of a data processing apparatus for an autonomous vehicle according to embodiments of the present disclosure is illustrated schematically; and

[0019] Figure 7 A block diagram of an electronic device suitable for implementing a data processing method for autonomous vehicles, according to an embodiment of the present disclosure, is illustrated schematically. Detailed Implementation

[0020] The exemplary embodiments of this disclosure are described below with reference to the accompanying drawings, including various details of the embodiments to aid understanding, and should be considered merely exemplary. Therefore, those skilled in the art will recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of this disclosure. Similarly, for clarity and brevity, descriptions of well-known functions and structures are omitted in the following description.

[0021] This disclosure provides a data processing method, apparatus, electronic device, autonomous vehicle, storage medium, and program product for autonomous vehicles.

[0022] According to embodiments of this disclosure, a data processing method for autonomous vehicles is provided, comprising: determining lane change scenario data in response to determining that the vehicle is in the process of changing lanes; determining a target lane change scenario category based on the lane change scenario data; determining target scenario data from the lane change scenario data based on the target lane change scenario category; and determining a lane change identification result based on the target scenario data, wherein the lane change identification result is used to characterize whether the lane change process is in a safe state.

[0023] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure, and application of user personal information comply with the provisions of relevant laws and regulations, necessary confidentiality measures have been taken, and there is no violation of public order and good morals.

[0024] In the technical solution disclosed herein, the user's authorization or consent is obtained before acquiring or collecting the user's personal information.

[0025] Figure 1 The illustration schematically shows an exemplary system architecture that can be applied to data processing methods and apparatus for autonomous vehicles according to embodiments of the present disclosure.

[0026] It is important to note that Figure 1 The examples shown are merely examples of system architectures applicable to embodiments of this disclosure, intended to help those skilled in the art understand the technical content of this disclosure. They do not imply that embodiments of this disclosure cannot be used in other devices, systems, environments, or scenarios. For instance, in another embodiment, an exemplary system architecture applicable to the data processing methods and apparatus for autonomous vehicles may include an onboard terminal for the autonomous vehicle. However, the onboard terminal may implement the data processing methods and apparatus for autonomous vehicles provided by embodiments of this disclosure without needing to interact with a server.

[0027] like Figure 1 As shown, the system architecture 100 according to this embodiment may include an autonomous vehicle 101, a network 102, and a server 103. The autonomous vehicle 101 can communicatively connect to one or more servers 103 via the network 102. The network 102 can be any type of network, such as a wired or wireless local area network (LAN), a wide area network (WAN) such as the Internet, a cellular network, a satellite network, or a combination thereof. The server 103 can be any type of server or server cluster, such as a network or cloud server, an application server, a backend server, or a combination thereof. The server can be a data analysis server, a content server, a traffic information server, a map and point of interest (MPOI) server, or a location server, etc.

[0028] Automated vehicle 101 can refer to a vehicle configured to operate in automated driving mode. However, it is not limited to this. Automated vehicles can also operate in manual mode, fully automated driving mode, or partially automated driving mode.

[0029] The autonomous vehicle 101 may include: an on-board terminal, a vehicle control module, a wireless communication module, a user interface module, and a sensing module. The autonomous vehicle 101 may also include common components found in ordinary vehicles, such as: an engine, wheels, a steering wheel, and a transmission. These common components can be controlled by the on-board terminal and the vehicle control module using various communication commands, such as: acceleration commands, deceleration commands, steering commands, and braking commands.

[0030] The various modules in the autonomous vehicle 101 can be communicatively connected to each other via interconnects, buses, networks, or combinations thereof. For example, they can be communicatively connected to each other via a Controller Area Network (CAN) bus. The CAN bus is a vehicle bus standard designed to allow microcontrollers and devices to communicate with each other in applications without a master.

[0031] The sensing module may include, but is not limited to, one or more cameras, a Global Positioning System (GPS) unit, an Inertial Measurement Unit (IMU), a radar unit, and a Light Detection and Ranging (LIDAR) unit. The GPS unit may include a transceiver operable to provide information about the autonomous vehicle's position. The IMU unit may sense changes in the autonomous vehicle's position and orientation based on inertial acceleration. The radar unit may represent a system that uses radio signals to sense obstacles in the autonomous vehicle's surrounding environment. In addition to sensing obstacles, the radar unit may also sense the speed and / or direction of travel of the obstacles. The LIDAR unit may use lasers to sense obstacles in the autonomous vehicle's environment. Among other components, the LIDAR unit may also include one or more laser sources, a laser scanner, and one or more detectors. The camera may include one or more devices for acquiring images of the autonomous vehicle's surrounding environment. The camera may be a still camera and / or a video camera. The camera may be mechanically movable, for example, by mounting the camera on a rotating or tilting platform.

[0032] The sensing module may also include other sensors, such as sonar sensors, infrared sensors, steering sensors, throttle sensors, brake sensors, and audio sensors (e.g., microphones). The audio sensor can be configured to collect sound from the environment surrounding the autonomous vehicle. The steering sensor can be configured to sense the steering angle of the steering wheel, the wheels of the autonomous vehicle, or a combination thereof. The throttle and brake sensors sense the throttle and brake positions of the autonomous vehicle, respectively. In some cases, the throttle and brake sensors can be integrated into an integrated throttle / brake sensor.

[0033] The vehicle control module may include, but is not limited to, a steering unit, a throttle unit (also known as an acceleration unit), and a braking unit. The steering unit is used to adjust the direction or forward trajectory of the autonomous vehicle. The throttle unit is used to control the speed of the electric motor or engine, thereby controlling the speed and acceleration of the autonomous vehicle. The braking unit decelerates the autonomous vehicle by providing friction to slow down the wheels or tires.

[0034] The wireless communication module allows communication between autonomous vehicles and external modules such as devices, sensors, and other vehicles. For example, the wireless communication module can communicate directly with one or more devices, or wirelessly via a communication network, such as communicating with a server through a network. The wireless communication module can use any cellular communication network or wireless local area network (WLAN), for example, using WiFi, to communicate with another component or module. The user interface module can be part of the peripheral devices implemented within the autonomous vehicle, including, for example, a keyboard, a touchscreen display, a microphone, and a speaker.

[0035] Some or all of the functions of the autonomous vehicle 101 can be controlled or managed by an onboard terminal, especially when operating in autonomous driving mode. The onboard terminal includes the necessary hardware (e.g., processor, memory, storage device) and software (e.g., operating system, planning and route scheduling program) to receive information from sensing modules, control modules, wireless communication modules, and / or user interface modules, process the received information, and generate instructions for controlling the autonomous vehicle. Alternatively, the onboard terminal may be integrated with the control module.

[0036] For example, a passenger can specify the start and destination of their trip via a user interface module. The in-vehicle terminal obtains trip-related data. For instance, the in-vehicle terminal can obtain location and drivable routes from an MPOI server, which may be part of a server. The location server provides location services, and the MPOI server provides map services. Alternatively, such locations and maps can be cached locally in the in-vehicle terminal's persistent storage.

[0037] As the autonomous vehicle moves along a drivable path, the onboard terminal can obtain real-time traffic information from a traffic information system or server. The server can be operated by a third-party entity. The server's functionality can be integrated with the onboard terminal. Based on real-time traffic information, location information, and real-time local environmental data detected or sensed by sensor modules, the onboard terminal can plan the optimal route and, for example, control the autonomous vehicle via a control module to safely and efficiently reach the designated destination.

[0038] It should be understood that Figure 1 The number of autonomous vehicles, networks, and servers shown is merely illustrative. Any number of autonomous vehicles, networks, and servers can be included depending on implementation needs.

[0039] It should be noted that the sequence numbers of the operations in the following methods are for descriptive purposes only and should not be considered as indicating the execution order of the operations. Unless explicitly stated otherwise, the method does not need to be executed in the exact order shown.

[0040] Figure 2 The diagram illustrates an application scenario of a data processing method for autonomous vehicles according to an embodiment of the present disclosure.

[0041] like Figure 2As shown, vehicle (i.e., autonomous vehicle, hereinafter referred to as vehicle) ADC201 is traveling in the first lane and begins to change lanes from the first lane to the second lane. Obstacle OBS201, which is in the first lane and located behind vehicle ADC201, also begins to change lanes from the first lane to the second lane. Obstacle OBS202, which is in the second lane and located to the left rear of vehicle ADC201, suddenly accelerates along the direction of travel. Obstacle OBS203, which is in the third lane and parallel to vehicle ADC201, begins to change lanes from the third lane to the second lane.

[0042] During lane changing, for the complex lane changing scenarios mentioned above, it is necessary to determine whether to control the vehicle ADC1 to follow the strategy of moving to the initial lane or the strategy of changing lanes according to the predetermined lane changing trajectory, in order to improve driving safety and reduce the risk of collision.

[0043] According to embodiments of this disclosure, an on-board terminal in a vehicle or a server connected to the on-board terminal can use the data processing method provided in the embodiments of this disclosure to receive lane change scenario data from a sensing module, determine lane change recognition results such as whether the lane change process is in a safe state based on the lane change scenario data such as traffic conditions, obstacle data, and vehicle data, and generate a reasonable lane change strategy based on the lane change recognition results, thereby improving the intelligence and flexibility of the lane change process when the vehicle is in autonomous driving mode.

[0044] Figure 3 A flowchart illustrating a data processing method for an autonomous vehicle according to an embodiment of the present disclosure is shown schematically.

[0045] like Figure 3 As shown, the method includes operations S310 to S340.

[0046] In operation S310, in response to determining that the vehicle is in the process of changing lanes, lane change scenario data is determined.

[0047] When operating S320, the target lane change scenario category is determined based on lane change scenario data.

[0048] When operating S330, target scenario data is determined from lane change scenario data based on the target lane change scenario category.

[0049] During operation of S340, the lane change recognition result is determined based on the target scene data. The lane change recognition result is used to characterize whether the lane change process is in a safe state.

[0050] According to embodiments of this disclosure, lane change scenario data may include at least one of the following: data on obstacles related to lane change, vehicle data, scenario data, and road traffic rule data.

[0051] According to embodiments of this disclosure, data related to lane change obstacles may include: obstacle size, obstacle speed, obstacle direction, and obstacle acceleration, as well as other state and attribute data.

[0052] According to embodiments of this disclosure, vehicle data may include status data and attribute data such as vehicle size, vehicle speed, vehicle direction, and vehicle drivability.

[0053] According to embodiments of this disclosure, scene data may include objective driving scene data such as weather, visibility, road mud level, traffic congestion, and construction conditions.

[0054] According to embodiments of this disclosure, road traffic rule data may include subjective driving rule data such as speed limit rules, no-reverse-driving rules, and no-crossing-solid-line lane-changing rules.

[0055] According to embodiments of this disclosure, the target lane change scenario category can refer to the traffic scenario category formed by the vehicle and surrounding obstacles during the lane change process. For example, a scenario category where the vehicle and a parallel obstacle change lanes simultaneously, a scenario category where an obstacle behind the vehicle and the vehicle change lanes simultaneously, a scenario category where an obstacle suddenly accelerates, etc. However, it is not limited to these. The target lane change scenario category can also refer to the relative positional relationship between the vehicle and obstacles surrounding the vehicle during the lane change process. For example, a scenario category where there are obstacles in one or more directions—in front of, behind, to the left, and to the right of the vehicle.

[0056] According to embodiments of this disclosure, the target lane change scenario category can be determined based on lane change scenario data. For example, obstacle data of obstacles around the vehicle can be determined based on the lane change scenario data, such as whether the obstacle is a dynamic obstacle, the relative position between the obstacle and the vehicle, and the predetermined trajectory of the dynamic obstacle.

[0057] According to embodiments of this disclosure, target scene data may refer to a portion of lane change scene data, and target scene data may be determined from lane change scene data based on the target lane change scene category.

[0058] For example, different processing models or decision rules can be used to process data based on the target lane change scenario category, thereby extracting target scenario data that matches the target lane change scenario category from the lane change scenario data.

[0059] For example, the target lane change scenario category might be a scenario where there is an obstacle to the side of the vehicle. The vehicle and the obstacle may be changing lanes simultaneously, posing a risk of a collision. Therefore, the target scenario data could include data for determining the vehicle's predetermined lane change trajectory and data for determining the obstacle's predetermined trajectory. Another example is a scenario where an obstacle is traveling behind the vehicle. The target scenario data could include data for determining the difference between the vehicle's speed and the obstacle's speed.

[0060] The data processing method for autonomous vehicles provided in this disclosure can determine the target lane change scenario category from lane change scenario data. Based on the target lane change scenario category, different driving decision-making or processing models can be employed for processing, making the analysis more accurate, targeted, and detailed. Furthermore, based on the target lane change scenario category, target scenario data can be determined from the lane change scenario data, and then the lane change recognition result can be determined based on the target scenario data. This simplifies the processing of complex and ever-changing lane change scenario data, improving processing efficiency while simultaneously increasing the recognition accuracy of the final lane change recognition result.

[0061] According to embodiments of this disclosure, for operation S320, determining the target lane change scenario category based on lane change scenario data may include: determining target template lane change scenario data that matches the lane change scenario data from multiple template lane change scenario data; and determining the target lane change scenario category that matches the target template lane change scenario data based on the mapping relationship between template lane change scenario data and lane change scenario categories.

[0062] According to other embodiments of this disclosure, for operation S320, determining the target lane change scenario category based on lane change scenario data may further include: inputting the lane change scenario data into a scenario category recognition model to obtain the target lane change scenario category. The network structure of the scenario category recognition model is not limited, as long as it is a deep learning model capable of obtaining the target lane change scenario category based on the lane change scenario data.

[0063] Figure 4 The illustration shows a flowchart of determining the target lane change scenario category according to an embodiment of the present disclosure.

[0064] like Figure 4As shown in the template lane change scenario, the lane change scenario can be pre-classified according to the relative position of the obstacles between the vehicle ADC401 and the obstacles, resulting in multiple template lane change scenario categories. For example, a lane change scenario category may include one or more obstacles OBS401 to OBS411 surrounding the vehicle ADC401. Obstacles OBS401, OBS402, OBS403, and OBS404 are obstacles in front of the vehicle ADC401; obstacles OBS405, OBS406, and OBS407 are obstacles on the sides of the vehicle ADC401; and obstacles OBS408, OBS409, OBS410, and OBS411 are obstacles behind the vehicle ADC401. Template lane change scenario data corresponding to the lane change scenario categories is determined, and a mapping relationship is established between the lane change scenario categories and the corresponding template lane change scenario data.

[0065] like Figure 4 As shown in the lane change scenario, based on the lane change scenario data, vehicle ADC402 is determined, for example, a vehicle currently in a lane change operation state. Surrounding obstacles include forward obstacles OBS412, OBS413, and OBS414; rearward obstacles OBS415 and OBS416; and lateral obstacle OBS417. The lane change scenario data can be compared one-to-one with multiple template lane change scenario data to determine the target template lane change scenario data. For example, the target template lane change scenario data can be determined based on the relative position of obstacles to the vehicle. The target lane change scenario category is determined based on the mapping relationship between template lane change scenario data and lane change scenario categories.

[0066] According to embodiments of this disclosure, lane change scenario categories can be determined based on pre-defined relative positions of obstacles between the vehicle and surrounding obstacles. This enables fine-grained classification of lane change scenarios based on the relative positions of obstacles, making the relationship between obstacles and vehicles clearer and more granular. Different processing models or decision rules can be applied to different obstacles for analysis, thereby enabling a more accurate assessment of whether there is a risk of collision between the vehicle and the obstacle.

[0067] According to embodiments of this disclosure, obstacle trajectories can be determined from lane change scenario data based on a target lane change scenario category. If the relationship between the obstacle's trajectory and the vehicle's predetermined lane change trajectory satisfies a predetermined obstacle discrimination relationship, the obstacle is designated as a target obstacle. Data related to the target obstacle is determined from the lane change scenario data and used as target scenario data. If the relationship between the obstacle's trajectory and the vehicle's predetermined lane change trajectory does not satisfy the predetermined obstacle discrimination relationship, data processing operations on that obstacle can be stopped. For example, data related to the obstacle in the lane change scenario data can be deleted.

[0068] According to embodiments of this disclosure, the predetermined obstacle discrimination relationship may refer to: a predetermined collision relationship, or a predetermined trajectory intersection relationship.

[0069] For example, if a vehicle is changing lanes and an obstacle directly behind the vehicle is traveling straight, then there is no intersection between the vehicle's planned lane-changing trajectory and the obstacle's trajectory directly behind the vehicle. Therefore, the relationship between the vehicle's planned lane-changing trajectory and the obstacle's trajectory does not satisfy the predetermined obstacle discrimination relationship, and the obstacle is a non-target obstacle.

[0070] For example, if a vehicle is changing lanes and an obstacle directly behind it is also changing lanes, and both are heading into the same lane, then the vehicle's planned lane-changing trajectory and the obstacle's trajectory directly behind it may intersect. If the relationship between these two trajectories satisfies the predetermined obstacle identification relationship, then the obstacle is the target obstacle.

[0071] According to embodiments of this disclosure, a target lane change scenario category can be determined based on the relative positions of obstacles between the vehicle and obstacles in lane change scenario data, thus achieving a preliminary understanding of the vehicle's lane change scenario. Based on the target lane change scenario category, the relationship between the vehicle's predetermined lane change trajectory and the obstacle's trajectory in the lane change scenario data is determined, and the target obstacle is identified from multiple obstacles, achieving a refined understanding of the vehicle's lane change scenario. Based on the target obstacle, target scenario data is filtered from the lane change scenario data, thereby achieving a precise understanding of the lane change scenario. Thus, through a step-by-step filtering method, complex and variable lane change scenarios can be analyzed simply and accurately.

[0072] According to embodiments of this disclosure, for operation S340, determining the lane change recognition result based on the target scene data may include: determining predetermined safe lane change conditions that match the target lane change scene category. The lane change recognition result is then determined based on the target scene data and the predetermined safe lane change conditions.

[0073] According to embodiments of this disclosure, a first lane change identification result is determined when the target scene data meets predetermined safe lane change conditions. The first lane change identification result is used to characterize that the lane change process is in a safe state. If the target scene data does not meet the predetermined safe lane change conditions, a second lane change identification result is determined. The second lane change identification result is used to characterize that the lane change process is in an unsafe state.

[0074] According to embodiments of this disclosure, predetermined safe lane-change conditions can be pre-set based on the target lane-change scenario category. These predetermined safe lane-change conditions can serve as standard conditions for determining whether a lane-change process is in a safe state. If the target scenario data meets the predetermined safe lane-change conditions, the lane-change process is in a safe state; otherwise, the lane-change process is in an unsafe state.

[0075] For example, if the target lane change scenario category is a lane change scenario where an obstacle is behind the vehicle changing lanes, the predetermined safe lane change condition may include a relative speed between the two vehicles being greater than or equal to a predetermined speed threshold. Another example is a lane change scenario category where the target lane change scenario category is a lane change scenario where the vehicle and an obstacle simultaneously change lanes into the same lane. The predetermined safe lane change condition may include a relative distance between the two vehicles being greater than or equal to a predetermined distance threshold, or a relative distance between the two vehicles being greater than or equal to a predetermined distance threshold, and a relative speed being greater than or equal to a predetermined speed threshold.

[0076] For example, the target lane change scenario category is one where the obstacle is located to the side of the vehicle. Predetermined safe lane change conditions may include a relative distance between the vehicle and the obstacle greater than or equal to a predetermined distance threshold. Along the driving direction, there is a negative longitudinal relative distance between the vehicle and the obstacle, less than the predetermined distance threshold. For example, if the obstacle is ahead of the vehicle, the target scenario data does not meet the predetermined safe lane change conditions, and the vehicle's lane change strategy may include obstacle avoidance, such as yielding. If the obstacle is behind the vehicle, and there is a positive longitudinal relative distance between the vehicle and the obstacle, greater than the predetermined distance threshold, then the target scenario data meets the predetermined safe lane change conditions, and the vehicle's lane change strategy may include changing lanes according to a predetermined lane change trajectory, such as overtaking. When the obstacle is located to the side of the vehicle and the obstacle is at the same level as the vehicle, the predetermined safe lane change conditions also include relative speed. For example, if the vehicle's speed is faster than or equal to the obstacle's speed, and the relative speed is greater than or equal to a predetermined speed threshold, then the target scenario data meets the predetermined safe lane change conditions, and the vehicle's lane change strategy may include changing lanes according to a predetermined lane change trajectory, such as overtaking. If the vehicle's speed is slower than the obstacle's speed, and the relative speed is less than a predetermined speed threshold, then the target scenario data does not meet the predetermined safe lane-changing conditions. The vehicle's lane-changing strategy can include obstacle avoidance lane-changing strategies, such as yielding.

[0077] According to embodiments of this disclosure, lane changing can be made safer and smarter by utilizing target lane change data and predetermined safe lane change conditions.

[0078] According to other embodiments of this disclosure, the target lane change data can also be corrected so that the lane change identification result is more consistent with reality, and the actual lane change risk is controlled more accurately and effectively.

[0079] For example, based on target scene data, the relative distance change between the vehicle and the target obstacle within a predetermined time period is determined. The relative distance change is then corrected to obtain the corrected distance change. Based on the corrected distance change and predetermined safe lane-changing conditions, the lane-change recognition result is determined.

[0080] According to embodiments of this disclosure, the relative distance can be corrected using the following formula.

[0081]

[0082] Where Δv represents the change in relative driving speed, s[t[i]] represents the relative distance between the vehicle and the obstacle at time t[i], and s[t[i-1]] represents the relative distance between the vehicle and the obstacle at time t[i-1].

[0083] bias = w t *Δv; Formula (2)

[0084] Where bias represents velocity bias, w t Indicates the weight.

[0085] new_acc=acc-bias; formula (3)

[0086] Where new_acc represents the corrected acceleration of the obstacle, and acc represents the initial acceleration of the obstacle.

[0087] According to embodiments of this disclosure, the corrected relative distance change between the obstacle and the vehicle can be determined by linear extrapolation based on the corrected acceleration. This can be applied to lane-changing scenarios where the vehicle is in front of an obstacle, and the obstacle's acceleration is greater than the vehicle's. In situations where it is difficult to predict the obstacle's trajectory in a timely manner, correcting the relative distance change between the vehicle and the obstacle improves the accuracy of obstacle trajectory prediction, enhances lane-change recognition accuracy, and ultimately ensures the safety of the lane-change process.

[0088] Figure 5 A schematic flowchart of a data processing method for an autonomous vehicle according to an embodiment of the present disclosure is shown.

[0089] like Figure 5 As shown in the first lane change scenario, the onboard terminal can respond to a lane change command and perform operations during the lane change preparation phase. For example, it can acquire scene data and determine the lane change merging point of the target lane based on the scene data, such as the merging point between the first obstacle OBS501 and the second obstacle OBS502. Based on the location of the vehicle ADC501 and the lane change merging point of the target lane, a predetermined lane change trajectory is determined.

[0090] like Figure 5 As shown in the second lane-change scenario, the onboard terminal controls the vehicle ADC501 to change lanes according to a predetermined lane-change trajectory. During the lane-change process, the onboard terminal acquires lane-change scenario data through the sensor module and determines the target lane-change scenario category based on the data. For example, the target lane-change scenario category is where there is a second obstacle OBS502 behind the vehicle ADC501 and a first obstacle OBS501 in front of the vehicle ADC501. Based on the target lane-change scenario category, it can be determined from the lane-change scenario data that the second obstacle OBS502 suddenly accelerates, and the relationship between the predetermined lane-change trajectory of the vehicle ADC501 and the obstacle trajectory of the second obstacle OBS502 satisfies the predetermined obstacle discrimination relationship. The second obstacle OBS502 is then identified as the target obstacle. Data related to the target obstacle in the lane-change scenario data is used as the target scenario data. Based on the target scenario data, the lane-change recognition result is determined. And based on the target lane-change scenario recognition result, a lane-change strategy is generated.

[0091] like Figure 5 As shown in the third lane change scenario A, the target lane change scenario recognition result can include: continuing to change lanes according to the predetermined lane change trajectory will result in a collision risk, such as the risk of being rear-ended by an obstacle. A strategy for driving back to the initial lane can be generated.

[0092] like Figure 5 As shown in the third lane change scenario B-1, the target lane change scenario recognition result can include: continuing to change lanes according to the predetermined lane change trajectory will result in a collision risk, such as the risk of being rear-ended by an obstacle. An obstacle avoidance lane change strategy can be generated. For example, during the lane change process, a combined lateral and longitudinal obstacle avoidance lane change strategy can be generated so that while avoiding the second obstacle OBS502 that suddenly accelerates from behind, the lane change process can proceed simultaneously. Figure 5 As shown in the third lane change scenario B-2, once it is determined that the second obstacle OBS502 has moved in front of the vehicle and the risk has been eliminated, the predetermined lane change trajectory can be updated, and the vehicle can drive according to the updated predetermined lane change trajectory to finally complete the lane change task.

[0093] like Figure 5 As shown in the third lane change scenario C, the target lane change scenario recognition result can include: continuing to change lanes according to the predetermined lane change trajectory without collision risk. For example, the distance between the second obstacle OBS502 and the vehicle ADC501 is large enough that even if the second obstacle OBS502 suddenly accelerates, it is still in a safe lane change state. A strategy for changing lanes according to the predetermined lane change trajectory can be generated, and the vehicle can drive according to the predetermined lane change trajectory to finally complete the lane change task.

[0094] Figure 6 A block diagram of a data processing apparatus for an autonomous vehicle according to an embodiment of the present disclosure is shown schematically.

[0095] like Figure 6 As shown, the data processing device 600 for autonomous vehicles includes: a response module 610, a category determination module 620, a data determination module 630, and a result determination module 640.

[0096] The response module 610 is used to determine lane change scenario data in response to the determination that the vehicle is in the process of changing lanes.

[0097] The category determination module 620 is used to determine the target lane change scenario category based on lane change scenario data.

[0098] The data determination module 630 is used to determine the target scenario data from the lane change scenario data based on the target lane change scenario category.

[0099] The result determination module 640 is used to determine the lane change recognition result based on the target scene data. The lane change recognition result is used to characterize whether the lane change process is in a safe state.

[0100] According to embodiments of this disclosure, the category determination module includes: a template determination unit and a category determination unit.

[0101] The template determination unit is used to determine the target template lane change scene data that matches the lane change scene data from multiple template lane change scene data.

[0102] The category determination unit is used to determine the target lane change scenario category that matches the target template lane change scenario data based on the mapping relationship between the template lane change scenario data and the lane change scenario category.

[0103] According to embodiments of this disclosure, the template determination unit includes: a first determination subunit and a second determination subunit.

[0104] The first determining subunit is used to determine the obstacles around the vehicle and the relative positions of the obstacles between the vehicle and the obstacles based on lane change scenario data.

[0105] The second determining subunit is used to determine the target template lane change scene data that matches the relative position of the obstacle from multiple template lane change scene data.

[0106] According to embodiments of this disclosure, the data determination module includes: a trajectory determination unit, a relationship determination unit, and a data determination unit.

[0107] The trajectory determination unit is used to determine the obstacle trajectory of the obstacle from the lane change scenario data based on the target lane change scenario category.

[0108] The relationship determination unit is used to identify an obstacle as a target obstacle when the relationship between the obstacle trajectory and the vehicle's predetermined lane-changing trajectory satisfies a predetermined obstacle discrimination relationship.

[0109] The data determination unit is used to determine the data related to the target obstacle from the lane change scenario data, and use it as the target scenario data.

[0110] According to embodiments of this disclosure, the result determination module includes: a condition determination unit and a result determination unit.

[0111] The condition determination unit is used to determine the predetermined safe lane change conditions that match the target lane change scenario category.

[0112] The result determination unit is used to determine the lane change recognition result based on the target scene data and the predetermined safe lane change conditions.

[0113] According to embodiments of this disclosure, the result determination unit includes: a speed determination subunit, a distance correction subunit, and a result determination subunit.

[0114] The speed determination subunit is used to determine the change in relative distance between the vehicle and the target obstacle within a predetermined time period based on the target scene data.

[0115] The distance correction subunit is used to correct the relative distance change and obtain the corrected distance change.

[0116] The result determination sub-unit is used to determine the lane change identification result based on the corrected distance change and the predetermined safe lane change conditions.

[0117] According to embodiments of this disclosure, the data processing apparatus for autonomous vehicles further includes, after the result determination module, a generation module.

[0118] The generation module is used to generate lane-changing strategies based on the lane-changing recognition results.

[0119] According to embodiments of this disclosure, the lane-changing strategy includes at least one of the following: a strategy of traveling to the initial lane, a strategy of changing lanes according to a predetermined lane-changing trajectory, and a strategy of lane-changing to avoid obstacles.

[0120] According to embodiments of this disclosure, this disclosure also provides an electronic device, a readable storage medium, an autonomous vehicle, and a computer program product.

[0121] According to an embodiment of the present disclosure, an electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform a method as described in the embodiments of the present disclosure.

[0122] According to embodiments of the present disclosure, a non-transitory computer-readable storage medium stores computer instructions, wherein the computer instructions are used to cause a computer to perform methods as described in embodiments of the present disclosure.

[0123] According to embodiments of the present disclosure, a computer program product includes a computer program that, when executed by a processor, implements the methods as described in embodiments of the present disclosure.

[0124] According to an embodiment of this disclosure, an autonomous vehicle is configured with the aforementioned electronic equipment, which, when executed by its processor, can implement the data processing method for autonomous vehicles described in the above embodiments.

[0125] Figure 7 A schematic block diagram of an example electronic device 700 that can be used to implement embodiments 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 may also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0126] like Figure 7 As shown, device 700 includes a computing unit 701, which can perform various appropriate actions and processes based on a computer program stored in read-only memory (ROM) 702 or a computer program loaded from storage unit 708 into random access memory (RAM) 703. RAM 703 may also store various programs and data required for the operation of device 700. The computing unit 701, ROM 702, and RAM 703 are interconnected via bus 704. Input / output (I / O) interface 705 is also connected to bus 704.

[0127] Multiple components in device 700 are connected to I / O interface 705, including: input unit 706, such as keyboard, mouse, etc.; output unit 707, such as various types of monitors, speakers, etc.; storage unit 708, such as disk, optical disk, etc.; and communication unit 709, such as network card, modem, wireless transceiver, etc. Communication unit 709 allows device 700 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0128] The computing unit 701 can be a variety of general-purpose and / or dedicated processing components with processing and computing capabilities. Some examples of the computing unit 701 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, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The computing unit 701 performs the various methods and processes described above, such as data processing methods for autonomous vehicles. For example, in some embodiments, the data processing methods for autonomous vehicles can be implemented as computer software programs tangibly contained in a machine-readable medium, such as storage unit 708. In some embodiments, part or all of the computer program can be loaded and / or installed on device 700 via ROM 702 and / or communication unit 709. When the computer program is loaded into RAM 703 and executed by the computing unit 701, one or more steps of the data processing methods for autonomous vehicles described above can be performed. Alternatively, in other embodiments, the computing unit 701 can be configured to perform data processing methods for autonomous vehicles by any other suitable means (e.g., by means of firmware).

[0129] Various embodiments 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-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0130] The program code used to implement the methods of this disclosure may be written in any combination of one or more programming languages. This program code may be provided to a processor or controller of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, such that when executed by the processor or controller, the program code causes the functions / operations specified in the flowcharts and / or block diagrams to be implemented. The program code may be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0131] In the context of this disclosure, a machine-readable medium can be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, apparatus, or device. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can be, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the foregoing.

[0132] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device for displaying information to the user (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor); and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the computer. Other types of devices can also be used to provide interaction with the user; for example, 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 sound input, voice input, or tactile input).

[0133] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as a data server), or computing systems that include middleware components (e.g., an application server), or computing systems that include frontend components (e.g., a user computer with a graphical user interface or web browser through which a user can interact with embodiments of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., a communication network). Examples of communication networks include local area networks (LANs), wide area networks (WANs), and the Internet.

[0134] Computer systems can include clients and servers. Clients and servers are generally located far apart and typically interact via communication networks. Client-server relationships are created by computer programs running on the respective computers and having a client-server relationship with each other. Servers can be cloud servers, distributed system servers, or servers incorporating blockchain technology.

[0135] It should be understood that the various forms of processes shown above can be used to rearrange, add, or delete steps. For example, the steps described in this disclosure can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution disclosed in this disclosure can be achieved, and this is not limited herein.

[0136] The specific embodiments described above do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

Claims

1. A data processing method for autonomous vehicles, comprising: In response to determining that the vehicle is in the process of changing lanes according to a predetermined lane-changing trajectory, lane-changing scenario data is determined; Based on the lane change scenario data, a target lane change scenario category is determined, wherein the target lane change scenario category is used to indicate the scenario category of the traffic scenario formed by the vehicle and surrounding obstacles during the lane change process; Based on the target lane change scenario category, the obstacle trajectory of the obstacle is determined from the lane change scenario data; If the relationship between the obstacle trajectory of the obstacle and the predetermined lane-changing trajectory of the vehicle satisfies the predetermined obstacle discrimination relationship, the obstacle is designated as the target obstacle. Data related to the target obstacle is determined from the lane change scenario data and used as target scenario data; and Based on the target scene data, a lane change recognition result is determined, wherein the lane change recognition result is used to characterize whether the lane change process is in a safe state.

2. The method according to claim 1, wherein, The process of determining the target lane change scenario category based on the lane change scenario data includes: Determine target template lane change scene data that matches the lane change scene data from multiple template lane change scene data; and Based on the mapping relationship between template lane change scenario data and lane change scenario categories, the target lane change scenario category that matches the target template lane change scenario data is determined.

3. The method according to claim 2, wherein, The step of determining the target template lane change scene data that matches the lane change scene data from multiple template lane change scene data includes: Based on the lane change scenario data, determine the obstacles around the vehicle and the relative positions of the obstacles to the vehicle; and Target template lane change scene data that matches the relative position of the obstacle is determined from the multiple template lane change scene data.

4. The method according to claim 1, wherein, The determination of the lane change recognition result based on the target scene data includes: Determine the predetermined safe lane change conditions that match the target lane change scenario category; and Based on the target scene data and the predetermined safe lane change conditions, the lane change recognition result is determined.

5. The method according to claim 4, wherein, The step of determining the lane change recognition result based on the target scene data and the predetermined safe lane change conditions includes: Based on the target scene data, determine the change in the relative distance between the vehicle and the target obstacle within a predetermined time period; The relative distance change is corrected to obtain the corrected distance change; and The lane change identification result is determined based on the corrected distance change and the predetermined safe lane change conditions.

6. The method according to any one of claims 1 to 5, further comprising, after determining the lane change recognition result based on the target scene data: Based on the lane change recognition results, a lane change strategy is generated. in, The lane-changing strategy includes at least one of the following: Strategies for moving to the initial lane, strategies for changing lanes according to a predetermined lane-changing trajectory, and strategies for lane-changing to avoid obstacles.

7. A data processing device for an autonomous vehicle, comprising: The response module is used to determine lane change scenario data in response to the determination that the vehicle is in the process of changing lanes according to a predetermined lane change trajectory. The category determination module is used to determine the target lane change scenario category based on the lane change scenario data, wherein the target lane change scenario category is used to indicate the scenario category of the traffic scenario formed by the vehicle and surrounding obstacles during the lane change process; The data determination module is used to determine target scenario data from the lane change scenario data based on the target lane change scenario category; and The result determination module is used to determine the lane change recognition result based on the target scene data, wherein the lane change recognition result is used to characterize whether the lane change process is in a safe state; The data determination module includes: The trajectory determination unit is used to determine the obstacle trajectory of the obstacle from the lane change scenario data based on the target lane change scenario category; A relationship determination unit is configured to identify the obstacle as a target obstacle if the relationship between the obstacle trajectory of the obstacle and the predetermined lane-changing trajectory of the vehicle satisfies a predetermined obstacle discrimination relationship; and A data determination unit is used to determine data related to the target obstacle from the lane change scenario data, and use it as the target scenario data.

8. The apparatus according to claim 7, wherein, The category determination module includes: The template determination unit is used to determine, from multiple template lane change scenario data, a target template lane change scenario data that matches the lane change scenario data; and The category determination unit is used to determine the target lane change scenario category that matches the target template lane change scenario data based on the mapping relationship between the template lane change scenario data and the lane change scenario category.

9. The apparatus according to claim 8, wherein, The template determination unit includes: The first determining subunit is configured to determine, based on the lane change scenario data, the obstacles around the vehicle and the relative positions of the obstacles to the vehicle; and The second determining subunit is used to determine the target template lane change scene data that matches the relative position of the obstacle from the plurality of template lane change scene data.

10. The apparatus according to claim 7, wherein, The result determination module includes: A condition determination unit is used to determine predetermined safe lane change conditions that match the target lane change scenario category; and The result determination unit is used to determine the lane change recognition result based on the target scene data and the predetermined safe lane change conditions.

11. The apparatus according to claim 10, wherein, The result determination unit includes: The speed determination subunit is used to determine the change in relative distance between the vehicle and the target obstacle within a predetermined time period based on the target scene data. A distance correction subunit is used to correct the relative distance change to obtain a corrected distance change; and The result determination subunit is used to determine the lane change identification result based on the corrected distance change and the predetermined safe lane change conditions.

12. The apparatus according to any one of claims 7 to 11, further comprising, after the result determination module: The generation module is used to generate a lane-changing strategy based on the lane-changing recognition result. in, The lane-changing strategy includes at least one of the following: Strategies for moving to the initial lane, strategies for changing lanes according to a predetermined lane-changing trajectory, and strategies for lane-changing to avoid obstacles.

13. 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 to enable the at least one processor to perform the method of any one of claims 1 to 6.

14. A non-transitory computer-readable storage medium storing computer instructions, wherein, The computer instructions are used to cause the computer to perform the method according to any one of claims 1 to 6.

15. A computer program product comprising a computer program that, when executed by a processor, implements the method according to any one of claims 1 to 6.

16. An autonomous vehicle, comprising: The electronic device as claimed in claim 13.

Images