Control methods, training methods, vehicles, equipment, and media for autonomous vehicles

Abstract

The present disclosure provides a control method for an autonomous vehicle, a training method for a deep learning model, an apparatus, an autonomous vehicle, an electronic device, a storage medium, and a program product, relating to the field of artificial intelligence technology, particularly autonomous driving, intelligent transportation, high-precision mapping, cloud services, and the Internet of Vehicles. A specific implementation scheme comprises: in response to receiving a lane change instruction, determining a first target lane change merge from multiple lane change merges based on target scene data, the target scene data including data related to the multiple lane change merges; determining a planned lane change path based on the first target lane change merge; and controlling the vehicle to travel according to the planned lane change path.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence technology, particularly autonomous driving, intelligent transportation, high-precision mapping, cloud services, and the Internet of Vehicles. The disclosure also includes a control method for an autonomous vehicle, a training method for a deep learning model, an apparatus, an autonomous vehicle, an electronic device, a storage medium, and a program product. Background Art

[0002] Vehicles operating in autonomous driving mode can free occupants, particularly the driver, from some driving-related responsibilities. When operating in autonomous driving mode, the vehicle can navigate to various locations using onboard sensors, allowing the vehicle to travel with minimal human interaction or, in some cases, without any passengers.

[0003] Lane changes typically involve changing lanes to the corresponding turning lane in response to a turn command, or in response to a command to bypass road construction. However, determining a reasonable lane change path in complex lane change scenarios and controlling the vehicle to perform automatic lane changes is a key aspect of autonomous driving capabilities. Summary of the Invention

[0004] The present disclosure provides a control method for an autonomous driving vehicle, a training method and device for a deep learning model, an autonomous driving vehicle, an electronic device, a storage medium, and a program product.

[0005] According to one aspect of the present disclosure, a control method for an autonomous driving vehicle is provided, comprising: in response to receiving a lane change instruction, determining a first target lane change merge from a plurality of lane change merges based on target scene data, wherein the target scene data includes data related to the plurality of lane change merges; determining a lane change planning path based on the first target lane change merge; and controlling the vehicle to change lanes according to the lane change planning path.

[0006] According to another aspect of the present disclosure, a method for training a deep learning model is provided, comprising: determining training samples, wherein the training samples include sample scenario data and labels, the sample scenario data include data related to multiple sample lane change merges, the labels include positive sample labels and negative sample labels, the positive sample labels are used to indicate a first target sample lane change merge, the first target sample lane change merge includes a successfully merged sample lane change merge among the multiple sample lane change merges, and the negative sample labels are used to indicate a second target sample lane change merge, the second target sample lane change merge includes a sample lane change merge among the multiple sample lane change merges other than the first target sample lane change merge; and training the deep learning model using the training samples to obtain a trained deep learning model.

[0007] According to another aspect of the present disclosure, a control device for an autonomous driving vehicle is provided, comprising: a first determination module for determining, in response to receiving a lane change instruction, a first target lane change merge from a plurality of lane change merges based on target scene data, wherein the target scene data includes data related to the plurality of lane change merges; a second determination module for determining a lane change planning path based on the first target lane change merge; and a driving module for controlling the vehicle to change lanes and drive according to the lane change planning path.

[0008] According to another aspect of the present disclosure, a training device for a deep learning model is provided, including: a sample determination module for obtaining training samples, wherein the training samples include sample scenario data and labels, the sample scenario data include data related to multiple sample lane change mergers, the labels include positive sample labels and negative sample labels, the positive sample labels are used to indicate a first target sample lane change merger, the first target sample lane change merger includes a successfully merged sample lane change merger among multiple sample lane change mergers, and the negative sample labels are used to indicate a second target sample lane change merger, the second target sample lane change merger includes a sample lane change merger among multiple sample lane change mergers other than the first target sample lane change merger; and a training module for training the deep learning model using the training samples to obtain a trained deep learning model.

[0009] According to another aspect of the present 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, and the instructions are executed by the at least one processor to enable the at least one processor to perform a method as disclosed herein.

[0010] According to another 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 the method of the present disclosure.

[0011] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, which implements the method of the present disclosure when executed by a processor.

[0012] According to another aspect of the present disclosure, an autonomous driving vehicle is provided, comprising the electronic device as described in the present disclosure.

[0013] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present disclosure, nor are they intended to limit the scope of the present disclosure. Other features of the present disclosure will become readily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The accompanying drawings are provided to facilitate a better understanding of the present invention and do not constitute a limitation of the present disclosure.

[0015] Figure 1 Schematically illustrates an exemplary system architecture to which the control method and apparatus for an autonomous driving vehicle according to an embodiment of the present disclosure may be applied;

[0016] Figure 2 A diagram schematically illustrates an application scenario of a method for controlling an autonomous driving vehicle according to an embodiment of the present disclosure;

[0017] Figure 3 A flowchart schematically illustrates a method for controlling an autonomous driving vehicle according to an embodiment of the present disclosure;

[0018] Figure 4 A schematic diagram schematically illustrates a scenario of a method for controlling an autonomous driving vehicle according to an embodiment of the present disclosure;

[0019] Figure 5 The following schematically shows a flow chart of a method for controlling an autonomous driving vehicle according to an embodiment of the present disclosure;

[0020] Figure 6 The flowchart of the training method of the deep learning model according to the embodiment of the present disclosure is schematically shown;

[0021] Figure 7 A block diagram schematically illustrates a control device for an autonomous driving vehicle according to an embodiment of the present disclosure;

[0022] Figure 8 A block diagram schematically illustrates a training apparatus for a deep learning model according to an embodiment of the present disclosure; and

[0023] Figure 9 A block diagram of an electronic device suitable for implementing a control method for an autonomous driving vehicle according to an embodiment of the present disclosure is schematically shown. DETAILED DESCRIPTION

[0024] The following description of exemplary embodiments of the present disclosure is made in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding. These details should be considered as merely exemplary. Therefore, those skilled in the art will recognize 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.

[0025] The present disclosure provides a control method for an autonomous driving vehicle, a training method and device for a deep learning model, an autonomous driving vehicle, an electronic device, a storage medium, and a program product.

[0026] According to an embodiment of the present disclosure, a control method for an autonomous driving vehicle is provided, comprising: in response to receiving a lane change instruction, determining a first target lane change merge from a plurality of lane change merges based on target scene data, the target scene data including data related to the plurality of lane change merges; determining a lane change planning path based on the first target lane change merge; and controlling the vehicle to travel according to the lane change planning path.

[0027] In the technical solution disclosed herein, the collection, storage, use, processing, transmission, provision, disclosure and application of user personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0028] In the technical solution disclosed herein, the user's authorization or consent is obtained before obtaining or collecting the user's personal information.

[0029] Figure 1 An exemplary system architecture to which the control method and apparatus for an autonomous driving vehicle according to an embodiment of the present disclosure can be applied is schematically illustrated.

[0030] It should be noted that Figure 1 The examples shown are merely examples of system architectures to which the embodiments of the present disclosure may be applied, to help those skilled in the art understand the technical content of the present disclosure, but do not mean that the embodiments of the present disclosure may not be used in other devices, systems, environments, or scenarios. For example, in another embodiment, an exemplary system architecture to which the control method and apparatus for an autonomous vehicle may be applied may include an onboard terminal of the autonomous vehicle, but the onboard terminal may implement the control method and apparatus for an autonomous vehicle provided by the embodiments of the present disclosure without interacting with a server.

[0031] like Figure 1 As shown, the system architecture 100 according to this embodiment may include an autonomous driving vehicle 101, a network 102, and a server 103. The autonomous driving vehicle 101 may be communicatively connected to one or more servers 103 via the network 102. The network 102 may 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 may be any type of server or server cluster, such as a network or cloud server, an application server, a back-end server, or a combination thereof. The server may 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.

[0032] The autonomous vehicle 101 may refer to a vehicle configured to operate in an autonomous driving mode, but is not limited thereto. The autonomous vehicle may also operate in a manual mode, a fully autonomous driving mode, or a partially autonomous driving mode.

[0033] Autonomous vehicle 101 may include an onboard terminal, a vehicle control module, a wireless communication module, a user interface module, and a sensor module. Autonomous vehicle 101 may also include common components found in conventional vehicles, such as an engine, wheels, a steering wheel, and a transmission. These common components can be controlled by the onboard terminal and the vehicle control module using various communication commands, such as acceleration, deceleration, steering, and braking commands.

[0034] The various modules in the autonomous vehicle 101 can be communicatively coupled to each other via an interconnect, a bus, a network, or a combination thereof. For example, they can be communicatively coupled 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 host computer.

[0035] 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 position of the autonomous vehicle. The IMU unit may sense the position and orientation changes of the autonomous vehicle based on inertial acceleration. The radar unit may represent a system that uses radio signals to sense obstacles in the autonomous vehicle's surroundings. In addition to sensing obstacles, the radar unit may also sense the speed and / or heading of the obstacles. The LIDAR unit may use lasers to sense obstacles in the autonomous vehicle's environment. The LIDAR unit may include, among other components, one or more laser sources, a laser scanner, and one or more detectors. The camera may include one or more devices for capturing images of the autonomous vehicle's surroundings. 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.

[0036] The sensing module may also include other sensors, such as a sonar sensor, an infrared sensor, a steering sensor, a throttle sensor, a brake sensor, and an audio sensor (e.g., a microphone). The audio sensor may be configured to collect sound from the environment surrounding the autonomous vehicle. The steering sensor may be configured to sense the steering angle of the steering wheel, the wheels of the autonomous vehicle, or a combination thereof. The throttle sensor and the brake sensor respectively sense the throttle position and brake position of the autonomous vehicle. In some cases, the throttle sensor and the brake sensor may be integrated into an integrated throttle / brake sensor.

[0037] 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 brake unit. The steering unit is used to adjust the direction or forward direction of the autonomous vehicle. The throttle unit is used to control the speed of the motor or engine, thereby controlling the speed and acceleration of the autonomous vehicle. The brake unit decelerates the autonomous vehicle by providing friction to slow down the wheels or tires of the autonomous vehicle.

[0038] The wireless communication module allows communication between the autonomous vehicle and external modules, such as devices, sensors, other vehicles, etc. For example, the wireless communication module can communicate directly with one or more devices wirelessly, or wirelessly communicate via a communication network, such as communicating with a server via the network. The wireless communication module can use any cellular communication network or wireless local area network (WLAN), such as WiFi, to communicate with another component or module. The user interface module can be part of the peripheral devices implemented in the autonomous vehicle, including, for example, a keyboard, a touch screen display device, a microphone, and a speaker.

[0039] Some or all of the functions of the autonomous vehicle 101 may be controlled or managed by an onboard terminal, particularly 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 routing programs) to receive information from the sensing module, control module, wireless communication module, and / or user interface module, process the received information, and generate instructions for controlling the autonomous vehicle. Alternatively, the onboard terminal may be integrated with the control module.

[0040] For example, a passenger may specify a trip's starting location and destination, for example, via a user interface module. The vehicle terminal then obtains trip-related data. For example, the vehicle terminal may obtain the location and drivable route from an MPOI server, which may be part of the server. The location server provides location services, and the MPOI server provides map services. Alternatively, such locations and maps may be cached locally in the vehicle terminal's permanent storage device.

[0041] As the autonomous vehicle moves along a drivable route, the vehicle terminal can also 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 vehicle terminal. Based on real-time traffic information, location information, and real-time local environmental data detected or sensed by the sensor module, the vehicle terminal can plan an optimal route and control the autonomous vehicle, for example, via the control module, based on the planned optimal route to reach the designated destination safely and efficiently.

[0042] It should be understood that Figure 1The number of autonomous driving vehicles, networks, and servers shown in the figure is merely illustrative. Any number of autonomous driving vehicles, networks, and servers may be used depending on the implementation requirements.

[0043] It should be noted that the sequence numbers of the operations in the following method are only used to indicate the operation for the purpose of description, and should not be regarded as indicating the order in which the operations should be performed. Unless explicitly stated, the method does not need to be performed in the order shown.

[0044] Figure 2 The following schematically shows an application scenario diagram of the control method for an autonomous driving vehicle according to an embodiment of the present disclosure.

[0045] like Figure 2 As shown, when the vehicle ADC201 (i.e., the autonomous driving vehicle, hereinafter referred to as the vehicle) needs to turn, for example, turn left, the on-board terminal mounted on the vehicle ADC201 or the server in communication with the vehicle ADC201 generates a lane change instruction, for example, an instruction for changing lanes from a straight lane to a left turn lane. The on-board terminal may receive the target scene data collected from the sensor module in response to receiving the lane change instruction. The control method for the autonomous driving vehicle provided by the embodiment of the present disclosure is executed based on the target scene data. However, it is not limited to this. The server may also receive the target scene data collected from the sensor module in response to receiving the lane change instruction, and execute the control method for the autonomous driving vehicle provided by the embodiment of the present disclosure based on the target scene data. The following embodiments will be illustrated using the on-board terminal as the execution subject, which will not be repeated here.

[0046] like Figure 2 As shown, the target scene data may include obstacle data about obstacles OBS201, OBS202, OBS203, and OBS204 on the left-turn lane. The target scene data may also include data related to multiple lane change merges, such as data related to lane change merges GAP201, GAP202, and GAP203, and may also include vehicle data, environmental data around the vehicle, and road traffic rules data, etc. The control method for the autonomous driving vehicle provided in the embodiment of the present disclosure can be used to determine a first target lane change merge from multiple lane change merges. Based on the first target lane change merge, a lane change planning path is determined. And the vehicle ADC201 is controlled to change lanes according to the lane change planning path.

[0047] By utilizing the control method for an autonomous driving vehicle provided by the embodiments of the present disclosure, the optional range of lane changes is changed from a lane change junction adjacent to the vehicle on a target lane to multiple lane change junctions on the target lane, depending on the vehicle state and the state of surrounding obstacles. This expands the optional range of lane changes, reduces restrictions on lane changing, and improves the intelligence and flexibility of lane changing.

[0048] Figure 3 A flowchart of a method for controlling an autonomous driving vehicle according to an embodiment of the present disclosure is schematically shown.

[0049] like Figure 3 As shown, the method includes operations S310 to S330.

[0050] In operation S310 , in response to receiving a lane change instruction, a first target lane change merge is determined from a plurality of lane change merges based on target scenario data, wherein the target scenario data includes data related to the plurality of lane change merges.

[0051] In operation S320 , a lane change planning path is determined based on the first target lane change merge entrance.

[0052] In operation S330 , the vehicle is controlled to change lanes according to the planned lane change path.

[0053] According to an embodiment of the present disclosure, in response to receiving a lane change instruction, a lane change task may be completed through multiple lane change phases, which may include a lane change planning phase and a lane change execution phase.

[0054] According to an embodiment of the present disclosure, the lane change planning stage may include: generating a lane change intention or a lane change task in response to receiving a lane change instruction. The lane change execution stage may include: controlling the vehicle to change lanes according to the lane change planning path.

[0055] For example, when the vehicle is traveling straight ahead, the onboard terminal, in response to receiving a lane change command, can enter the lane change planning phase from the straight ahead phase. Based on the target scenario data, the terminal will determine a first target lane change entrance from the target lane and generate a lane change planning path based on the first target lane change entrance. During the lane change execution phase, the terminal will control the vehicle to execute the lane change merging maneuver based on the lane change planning path at the first target lane change entrance.

[0056] According to an embodiment of the present disclosure, the lane change merge may refer to a driving space on the target lane that allows the vehicle to perform a lane change task. The driving space is larger than the movement space of the vehicle during the lane change task.

[0057] According to other embodiments of the present disclosure, in the lane change planning stage, the lane change confluence adjacent to the vehicle on the target lane can be used as the first target lane change confluence according to the predetermined lane change rules. The lane change confluence adjacent to the vehicle on the target lane can be understood as: a lane change confluence that meets the predetermined lane change conditions. Meeting the predetermined lane change conditions can refer to: controlling the vehicle to change lanes according to the lane change planning path, and being able to complete the lane change task within a predetermined time period. The lane change planning path can include not only the lane change planning trajectory, but also a safe driving speed. The predetermined time period can be 8s, but is not limited to this, as long as it is a time period that can ensure a safe lane change. When it is determined that the target scene data does not meet the predetermined lane change conditions, for example, when it is determined that there is no lane change confluence adjacent to the vehicle, the vehicle will remain in the lane change planning stage, waiting for a lane change confluence that meets the predetermined lane change conditions, and cannot move from the lane change planning stage to the lane change execution stage, and thus cannot execute the lane change task.

[0058] According to an embodiment of the present disclosure, during the lane change planning stage, a first target lane change convergence point can be determined from multiple lane change convergence points based on target scenario data. For example, in a traffic scenario where an obstacle on the target lane forms a traffic flow, not only the lane change convergence points adjacent to the vehicle on the target lane can be taken into consideration, but also the forward lane change convergence points of the vehicle on the target lane and the rearward lane change convergence points of the vehicle can be taken into consideration, so as to increase the chances of lane change. For example, when it is determined that there is no lane change convergence point adjacent to the vehicle on the target lane among multiple lane change convergence points, the first target lane change convergence point can be determined from the forward lane change convergence points and the rearward lane change convergence points among the multiple lane change convergence points. This expands the selection range of variable lane routes, extends the opportunities for lane change merging, reduces the restrictions on lane change driving, and improves the intelligence and flexibility of lane change driving.

[0059] According to other embodiments of the present disclosure, the lane change planning path can be adjusted based on the first target lane change confluence. For example, the predetermined lane change conditions specified in the lane change regulations can be adjusted, the safe driving speed can be adjusted, or the predetermined duration can be adjusted. For example, the safe driving speed can be adjusted from 60 km / h to 80 km / h, or the predetermined duration can be adjusted from 8 seconds to 10 seconds, so that a lane change planning path that meets the predetermined conditions can be generated based on the first target lane change confluence, and the vehicle can then be controlled to change lanes according to the lane change planning path, completing the lane change task while meeting the adjusted predetermined lane change conditions.

[0060] According to an embodiment of the present disclosure, after determining the first target lane change merge point, a lane change adjustment phase (prepare lane change task) may be added after the lane change planning phase. For example, the multiple lane change phases may be changed from including a lane change planning phase and a lane change execution phase to including a lane change planning phase, a lane change adjustment phase, and a lane change execution phase.

[0061] According to an embodiment of the present disclosure, the lane change adjustment stage may include adjusting the vehicle's driving speed. For example, if it is determined that the target scene data does not meet the predetermined lane change conditions, the driving speed is adjusted so that the adjusted target scene data meets the predetermined lane change conditions.

[0062] According to an embodiment of the present disclosure, by adjusting the vehicle's driving speed, the relative speed and relative position between the vehicle and the obstacle on the target lane can be adjusted, so that the adjusted target scene data, such as the adjusted target scene data related to the first target lane change entrance, meets the predetermined lane change conditions and can be transferred from the lane change adjustment stage to the lane change generation stage.

[0063] Figure 4 A schematic diagram of a scenario of a control method for an autonomous driving vehicle according to an embodiment of the present disclosure is schematically shown.

[0064] like Figure 4 As shown, in response to receiving a lane change instruction from a straight lane to a left-turn lane, the lane change planning phase is entered, and target scene data is determined. The target scene data can be used to represent: in the target lane, such as the left-turn lane, there are obstacles OBS401, OBS402, and OBS403; there is a first lane change entrance in front of obstacle OBS401; there is a second lane change entrance between obstacles OBS402 and OBS403; and there is a third lane change entrance behind obstacle OBS403.

[0065] The in-vehicle terminal determines, based on the target scene data, the second lane change merge as the first target lane change merge from the first lane change merge, the second lane change merge, and the third lane change merge.

[0066] like Figure 4As shown, the on-board terminal can generate an initial lane change planning path based on the target scene data and determine the required lane change duration. When driving at a safe driving speed according to the initial lane change planning path, and the lane change duration is greater than the predetermined duration, it can be determined that the target scene data does not meet the predetermined lane change conditions. In this case, the on-board terminal can control the vehicle ADC401 to enter the lane change adjustment phase. Adjust the speed of the vehicle ADC401 along the driving direction of the straight lane so that the lane change junction GAP402 becomes the lane change junction adjacent to the vehicle ADC401 on the left turn lane. Then, when it is determined that the adjusted target scene data meets the predetermined lane change conditions, generate a lane change planning path. Enter the lane change execution phase, control the vehicle ADC401 to change lanes according to the lane change planning path, and finally complete the lane change task.

[0067] By utilizing the control method for an autonomous driving vehicle provided by an embodiment of the present disclosure, when it is determined that the target scene data related to the current driving position and the first target lane change merging entrance do not meet the predetermined lane change conditions, a lane change adjustment phase can be set so that the adjusted target scene data meets the predetermined lane change conditions. Furthermore, by setting the lane change adjustment phase, opportunities for lane change merging can be actively created, thereby effectively improving the lane change merging capability, thereby ensuring the safety of the lane change process while improving the intelligence and flexibility in the autonomous driving mode.

[0068] According to an embodiment of the present disclosure, if it is determined that the target scenario data does not meet a predetermined lane change condition, a target acceleration for adjusting the driving speed is determined. If it is determined that the target acceleration meets a predetermined speed adjustment condition, the driving speed is adjusted according to the target acceleration. If it is determined that the target acceleration does not meet the speed adjustment condition, the operation of adjusting the driving speed is stopped.

[0069] According to an embodiment of the present disclosure, the predetermined speed adjustment condition may include a safe driving speed condition, but is not limited thereto, and may also include a physical sensation condition.

[0070] For example, when adjusting the target acceleration to achieve a speed adjustment, the vehicle must accelerate according to the target acceleration, and the adjusted speed must not exceed the safe speed. Alternatively, when decelerating according to the target acceleration, the vehicle must not decelerate excessively and fail to meet the physical sensing conditions, such as emergency braking.

[0071] By utilizing the control method for an autonomous driving vehicle provided by the embodiments of the present disclosure, it is possible to improve the lane changing capability while also improving the safety and comfort of the lane changing process.

[0072] According to an embodiment of the present disclosure, during the lane change adjustment phase, when adjusting driving speed, the sensing module can collect current scene data in real time, and the vehicle terminal receives the current scene data from the sensing module. The current scene data may include the target scene data during the speed adjustment process. The vehicle terminal determines that the current scene data meets the predetermined lane change cancellation conditions. If the current scene data meets the predetermined lane change cancellation conditions, the vehicle terminal can cancel the speed adjustment operation and cancel the lane change.

[0073] According to an embodiment of the present disclosure, satisfying the predetermined lane change cancellation condition may include not satisfying the predetermined lane change condition. For example, current scenario data indicates that the space of the first target lane change merge is smaller than the vehicle's active space during the lane change process, and there are no other lane change merges in the target lane.

[0074] According to an embodiment of the present disclosure, during the lane change adjustment phase, while adjusting the driving speed, the current scene data can be collected in real time through the sensing module, and the on-board terminal receives the current scene data from the sensing module. Based on the current scene data, the on-board terminal determines a second target lane change junction from a plurality of lane change junctions. Based on the first target lane change junction, a first lane change cost value is determined. The first lane change cost value is used to represent: the cost value of changing lanes according to the first target lane change junction. Based on the second target lane change junction, a second lane change cost value is determined. The second lane change cost value is used to represent: the cost value of changing lanes according to the second target lane change junction. Based on the first lane change cost value and the second lane change cost value, a new target lane change junction is determined from the first target lane change junction and the second target lane change junction. Based on the new target lane change junction, the on-board terminal determines an updated lane change planning path. The vehicle is controlled to change lanes according to the updated lane change planning path.

[0075] According to an embodiment of the present disclosure, the first lane-changing cost value or the second lane-changing cost value may include at least one of the following: a physical perception value, a timeliness value, a safety value, and the like.

[0076] According to an embodiment of the present disclosure, the somatosensory value can be used to characterize the comfort level felt by the body. For example, when the vehicle is driving smoothly, the comfort level of the passengers is high, and the somatosensory value is high; on the contrary, if the vehicle brakes suddenly, the comfort level of the passengers is low, and the somatosensory value is low. The timeliness value can be used to characterize driving efficiency. For example, for the same distance, the shorter the driving time, the higher the timeliness value. The safety value can be used to characterize driving safety. For example, when the vehicle is driving, if the risk of the vehicle colliding with surrounding obstacles is low, the safety value is high; on the contrary, if the risk of the vehicle colliding with surrounding obstacles is high, the safety value is low.

[0077] According to an embodiment of the present disclosure, a first lane change planning path is determined based on a first target lane change confluence. A first lane change cost is determined based on the first lane change planning path. For example, a weighted sum of a first sensory value, a first timeliness value, and a first safety value obtained based on the first lane change planning path is performed to obtain the first lane change cost. Similarly, a second lane change planning path is determined based on a second target lane change confluence. A second lane change cost is determined based on the second lane change planning path.

[0078] According to an embodiment of the present disclosure, the first lane change cost value and the second lane change cost value may be compared, the larger value may be taken as the target cost value, and the lane change merging point corresponding to the target cost value may be taken as the new target lane change merging point.

[0079] By using the control method for an autonomous driving vehicle provided by the embodiments of the present disclosure and determining the cost value, the comprehensive performance such as comfort, safety, and lane changing efficiency during the lane changing process can be improved.

[0080] Figure 5 A flow chart of a method for controlling an autonomous driving vehicle according to another embodiment of the present disclosure is schematically shown.

[0081] like Figure 5 As shown, a lane change gap selection model N520 can be used to determine a first target lane change merge 530 from multiple lane change merges based on target scenario data 520. For example, target scenario data 520 associated with multiple lane change merges is input into the lane change gap selection model N520, which outputs a classification result indicating the first target lane change merge.

[0082] like Figure 5 As shown, the feature extraction model N510 and the path planning model N530 can also be used to assist in completing the control method. The feature extraction model N510 can be used to extract feature data that meets the predetermined extraction conditions from the traffic scene data 510 as the target scene data 520. For example, the traffic scene data 510 can be input into the feature extraction model N510 to obtain the target scene data 520. The path planning model N530 can be used to determine the lane change planning path 540. For example, data such as the vehicle's current position 550 and the first target lane change entrance 530 can be input into the path planning model N530 to obtain the lane change planning path 540. Ultimately, the vehicle is controlled to change lanes according to the lane change planning path 540.

[0083] According to an embodiment of the present disclosure, the lane change gap selection model may include a deep learning model such as SVM (Support Vector Machine) and a neural network.

[0084] According to an embodiment of the present disclosure, the feature extraction model may be a screening rule, but is not limited thereto, and may also include deep learning models such as CNN (Convolutional Neural Network) and RNN (Recurrent Neural Network) for feature extraction.

[0085] According to an embodiment of the present disclosure, the path planning model may include a graph search method, a rapid search random tree (RRT) algorithm, and the like.

[0086] According to an embodiment of the present disclosure, traffic scene data may include: time data, vehicle data, obstacle data related to obstacles, environmental data, road traffic regulation data, etc. Feature data that meets predetermined extraction conditions may include at least one of the following: obstacle data related to lane changes, vehicle data, environmental data, and road traffic regulation data.

[0087] According to an embodiment of the present disclosure, data on obstacles related to lane changes may include: state data and attribute data such as the size of the obstacle, the speed of the obstacle, the direction of the obstacle, and the acceleration of the obstacle. Vehicle data may include: state data and attribute data such as the size of the vehicle, the speed of the vehicle, the direction of the vehicle, and the acceleration of the vehicle. Environmental data may include: objective driving environment data such as weather, visibility, road muddiness, road congestion, and road construction conditions. Road traffic rule data may include: subjective driving rule data such as speed limit rules, no reversing rules, and no lane change across solid lines.

[0088] According to an embodiment of the present disclosure, taking vehicle data as an example, the vehicle data in traffic scene data may include the vehicle's license plate, annual inspection data, vehicle size, and vehicle status data. After processing by the feature extraction model, the vehicle data in the target scene data may include vehicle status data and vehicle size, etc.

[0089] By utilizing the control method for an autonomous driving vehicle provided by the embodiments of the present disclosure, target scene data can be extracted from a large amount of traffic scene data through feature extraction means, so that the target scene data is streamlined data, thereby reducing the amount of data processing and improving data processing efficiency.

[0090] Figure 6 A flowchart of a deep learning model training method according to an embodiment of the present disclosure is schematically shown.

[0091] like Figure 6 As shown, the method includes operations S610 to S620.

[0092] In operation S610, training samples are determined. The training samples include sample scene data and labels. The sample scene data includes data related to multiple sample lane change merges. The labels include positive sample labels and negative sample labels. The positive sample labels are used to indicate a first target sample lane change merge, which includes a sample lane change merge that has successfully merged into the multiple sample lane change merges. The negative sample labels are used to indicate a second target sample lane change merge, which includes a sample lane change merge that has successfully merged into the multiple sample lane change merges.

[0093] In operation S620 , a deep learning model is trained using the training samples to obtain a trained deep learning model.

[0094] According to embodiments of the present disclosure, a trained deep learning model can be used as a lane change gap selection model, and the determination of the first target lane change merge point is treated as a classification problem. By adding the first target sample lane change merge point and the second target sample lane change merge point to the training samples, the deep learning model learns the feature data of not only the successfully selected sample lane change merge points during training, but also the feature data of the unselected sample lane change merge points. This ensures that the trained deep learning model has high accuracy and robustness in lane change merge point selection.

[0095] According to other embodiments of the present disclosure, a target sample lane change merge entrance may be determined from a plurality of sample lane change merge entrances according to corresponding lane change merge entrance selection rules, and the effect may be verified through simulation.

[0096] According to an embodiment of the present disclosure, compared with determining the first target lane change merge entrance by using a selection rule, determining the first target lane change merge entrance by using a lane change gap selection model for intelligent determination can make the determination process short, efficient, and intelligent.

[0097] According to an embodiment of the present disclosure, with respect to operation S610, determining the training sample may include: acquiring initial sample scene data, and extracting feature data that meets a predetermined extraction condition from the initial sample scene data as the sample scene data.

[0098] According to an embodiment of the present disclosure, the initial sample scenario data may include: closed-loop data, such as data on a vehicle's successful lane change; open-loop data, such as data on a vehicle's successful lane change controlled by a human driver; and data on other vehicles' successful lane changes collected by the vehicle.

[0099] According to an embodiment of the present disclosure, the feature data satisfying the predetermined extraction condition includes at least one of the following: data of obstacles related to lane change, vehicle data, environment data, and road traffic regulation data.

[0100] By using the training method of the deep learning model provided by the embodiment of the present disclosure, sample scene data can be extracted from a large amount of initial sample scene data through feature extraction means, so that the sample scene data is streamlined data, thereby reducing the data processing volume and improving the training efficiency of the deep learning model.

[0101] According to embodiments of the present disclosure, the process operation code of the autonomous vehicle control method can call process operation code related to the deep learning model training method. For example, the operation code for extracting feature data that meets predetermined extraction conditions from initial sample scene data as sample scene data is consistent with the operation code for extracting feature data that meets predetermined extraction conditions from traffic scene data as target scene data. This approach ensures consistency between the training and application processes of the lane change gap selection model.

[0102] Figure 7 A block diagram of a control device for an autonomous driving vehicle according to an embodiment of the present disclosure is schematically shown.

[0103] like Figure 7 As shown, the control device 700 of the autonomous driving vehicle includes: a first determination module 710, a second determination module 720, and a driving module 730.

[0104] The first determination module 710 is configured to determine, in response to receiving a lane change instruction, a first target lane change merge entrance from a plurality of lane change merge entrances based on target scene data, wherein the target scene data includes data related to the plurality of lane change merge entrances.

[0105] The second determining module 720 is configured to determine a lane change planning path based on the first target lane change merge entrance.

[0106] The driving module 730 is used to control the vehicle to change lanes according to the lane change planning path.

[0107] According to an embodiment of the present disclosure, the control device of the autonomous driving vehicle further includes, before the first determination module: an extraction module.

[0108] The extraction module is used to extract feature data that meets predetermined extraction conditions from the traffic scene data as target scene data.

[0109] According to an embodiment of the present disclosure, the control device of the autonomous driving vehicle further includes, before the second determination module: an adjustment module.

[0110] The adjustment module is used to adjust the driving speed when it is determined that the target scene data does not meet the predetermined lane change condition, so that the adjusted lane change scene data meets the predetermined lane change condition.

[0111] According to an embodiment of the present disclosure, the control device of the autonomous driving vehicle further includes, when it is determined that the target scene data does not meet the predetermined lane change condition, adjusting the driving speed: a third determination module and a cancellation module.

[0112] The third determining module is configured to determine current scene data, wherein the current scene data includes target scene data during the process of adjusting the driving speed.

[0113] The cancellation module is used to cancel the operation of adjusting the driving speed and cancel the lane change when it is determined that the current scene data meets the predetermined lane change cancellation conditions.

[0114] According to an embodiment of the present disclosure, the control device of the autonomous driving vehicle also includes, when it is determined that the target scene data does not meet the predetermined lane change conditions, adjusting the driving speed: a fourth determination module, a fifth determination module, a sixth determination module, and an update module.

[0115] The fourth determining module is configured to determine a second target lane change merging entrance from a plurality of lane change merging entrances based on current scene data.

[0116] The fifth determining module is configured to determine a first lane change cost based on the first target lane change merge. The first lane change cost is configured to represent a cost of changing lanes according to the first target lane change merge.

[0117] The sixth determining module is configured to determine a second lane change cost based on the second target lane change merge point. The second lane change cost is configured to represent a cost of changing lanes according to the second target lane change merge point.

[0118] An updating module is configured to determine a new target lane change merge from the first target lane change merge and the second target lane change merge based on the first lane change cost value and the second lane change cost value, so as to determine an updated lane change planning path based on the new target lane change merge.

[0119] According to an embodiment of the present disclosure, the predetermined lane change condition includes: completing the lane change at a safe driving speed within a predetermined time period.

[0120] According to an embodiment of the present disclosure, the feature data satisfying the predetermined extraction condition includes at least one of the following: data of obstacles related to lane change, vehicle data, environment data, and road traffic regulation data.

[0121] According to an embodiment of the present disclosure, the adjustment module includes an acceleration adjustment unit and a speed adjustment unit.

[0122] The acceleration adjustment unit is used to determine a target acceleration for adjusting the driving speed when it is determined that the target scene data does not meet the predetermined lane change condition.

[0123] The speed adjustment unit is used to adjust the driving speed according to the target driving degree when it is determined that the target acceleration meets the predetermined speed adjustment condition.

[0124] Figure 8 A block diagram of a deep learning model training device according to an embodiment of the present disclosure is schematically shown.

[0125] like Figure 8 As shown, the training device 800 for the deep learning model includes: a sample determination module 810 and a training module 820.

[0126] The sample determination module 810 is used to obtain training samples, wherein the training samples include sample scenario data and labels, the sample scenario data includes data related to multiple sample lane change merges, the labels include positive sample labels and negative sample labels, the positive sample labels are used to indicate a first target sample lane change merge, the first target sample lane change merge includes a successfully merged sample lane change merge from the multiple sample lane change merges, and the negative sample labels are used to indicate a second target sample lane change merge, the second target sample lane change merge includes a sample lane change merge from the multiple sample lane change merges except the first target sample lane change merge.

[0127] The training module 820 is used to train the deep learning model using the training samples to obtain a trained deep learning model.

[0128] According to an embodiment of the present disclosure, the sample determination module comprises: a data acquisition unit and a data extraction unit.

[0129] The data acquisition unit is used to acquire initial sample scene data.

[0130] The data extraction unit is used to extract feature data that meets a predetermined extraction condition from the initial sample scene data as sample scene data.

[0131] According to an embodiment of the present disclosure, the feature data satisfying the predetermined extraction condition includes at least one of the following: obstacle data related to lane change, vehicle data, environment data, and road traffic regulation data.

[0132] According to an embodiment of the present disclosure, the present disclosure also provides an electronic device, a readable storage medium, an autonomous driving vehicle, and a computer program product.

[0133] 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 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 execute a method as in the embodiment of the present disclosure.

[0134] According to an embodiment 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 a method according to an embodiment of the present disclosure.

[0135] According to an embodiment of the present disclosure, a computer program product includes a computer program. When the computer program is executed by a processor, the method according to the embodiment of the present disclosure is implemented.

[0136] According to an embodiment of the present disclosure, an autonomous driving vehicle is configured with the above-mentioned electronic device, and the configured electronic device can implement the control method of the autonomous driving vehicle described in the above embodiment when its processor executes it.

[0137] Figure 9 A schematic block diagram of an example electronic device 900 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 can also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smartphones, wearable devices, and other similar computing devices. The components shown herein, their connections and relationships, and their functions are provided as examples only and are not intended to limit the implementation of the present disclosure described and / or claimed herein.

[0138] like Figure 9 As shown, the device 900 includes a computing unit 901, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 902 or a computer program loaded from a storage unit 908 into a random access memory (RAM) 903. Various programs and data required for the operation of the device 900 can also be stored in the RAM 903. The computing unit 901, the ROM 902, and the RAM 903 are connected to each other via a bus 904. An input / output (I / O) interface 905 is also connected to the bus 904.

[0139] Various components in the device 900 are connected to the I / O interface 905, including an input unit 906, such as a keyboard, a mouse, etc.; an output unit 907, such as various types of displays, speakers, etc.; a storage unit 908, such as a magnetic disk, an optical disk, etc.; and a communication unit 909, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 909 allows the device 900 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0140] The computing unit 901 can be a variety of general-purpose and / or specialized processing components with processing and computing capabilities. Some examples of the computing unit 901 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 that run machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 901 performs the various methods and processes described above, such as the control method of an autonomous vehicle. For example, in some embodiments, the control method of an autonomous vehicle can be implemented as a computer software program that is tangibly contained in a machine-readable medium, such as the storage unit 908. In some embodiments, part or all of the computer program can be loaded and / or installed on the device 900 via the ROM 902 and / or the communication unit 909. When the computer program is loaded into the RAM 903 and executed by the computing unit 901, one or more steps of the control method of the autonomous vehicle described above can be performed. Alternatively, in other embodiments, the computing unit 901 can be configured to perform the control method of the autonomous vehicle by any other appropriate means (e.g., by means of firmware).

[0141] Various embodiments of the systems and techniques described above 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), system-on-chip systems (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include being implemented in one or more computer programs that are executable and / or interpreted on a programmable system that includes 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.

[0142] The program code for implementing the method of the present disclosure can be written in any combination of one or more programming languages. These program codes can be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device so that when the program code is executed by the processor or controller, the functions / operations specified in the flow chart and / or block diagram are implemented. The program code can be executed entirely on the machine, partially on the machine, as a stand-alone software package, partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0143] In the context of the present disclosure, a machine-readable medium can be a tangible medium that can contain or store a program for use by or in conjunction with an instruction execution system, device or equipment. A machine-readable medium can be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium can 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 can 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.

[0144] 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).

[0145] The systems and techniques described herein can 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 having 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 can 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.

[0146] A computer system may include a client and a server. The client and server are generally remote from each other and typically interact through a communication network. The client-server relationship arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server may be a cloud server, a server in a distributed system, or a server integrated with a blockchain.

[0147] It should be understood that the various forms of the processes shown above can be used to reorder, add, or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially, or in a different order, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved. This is not a limitation herein.

[0148] The above specific embodiments do not constitute a limitation on the scope of protection of this disclosure. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may be made based on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this disclosure shall be included within the scope of protection of this disclosure.

Claims

1. A method for controlling an autonomous vehicle, comprising: In response to receiving a lane change instruction, determining a first target lane change merge from a plurality of lane change merges based on target scenario data using a lane change merge selection model, wherein the target scenario data includes data related to the plurality of lane change merges, and the lane change merge refers to a driving space in a target lane of the lane change that allows the vehicle to perform a lane change task; Determining a lane change planning path based on the first target lane change merge entrance; and Controlling the vehicle to change lanes according to the lane change planning path; The lane change entrance selection model is trained using the following method: Using the training samples to train a deep learning model to obtain the lane change merging entrance selection model; The training samples include sample scene data and labels, the sample scene data includes data related to multiple sample lane change merges, the labels include positive sample labels and negative sample labels, the positive sample labels are used to indicate a first target sample lane change merge, the first target sample lane change merge includes a successfully merged sample lane change merge among the multiple sample lane change merges, and the negative sample labels are used to indicate a second target sample lane change merge, the second target sample lane change merge includes a sample lane change merge among the multiple sample lane change merges except the first target sample lane change merge.

2. The method according to claim 1, further comprising, before determining the first target lane change merge entrance from the plurality of lane change merge entrances based on the target scenario data: Feature data that meets a predetermined extraction condition is extracted from the traffic scene data as the target scene data.

3. The method according to claim 1, further comprising, before determining the lane change planning path based on the first target lane change merge: When it is determined that the target scene data does not satisfy the predetermined lane change condition, the driving speed is adjusted so that the adjusted target scene data satisfies the predetermined lane change condition.

4. The method according to claim 3, further comprising, in the case of adjusting the driving speed when it is determined that the target scene data does not meet the predetermined lane change condition: Determine the current scene data, where The current scene data includes target scene data during the process of adjusting the driving speed; as well as In the case where it is determined that the current scene data satisfies a predetermined lane change cancellation condition, the operation of adjusting the driving speed is canceled, and the lane change is canceled.

5. The method according to claim 4, further comprising, in the case of adjusting the driving speed when it is determined that the target scene data does not meet the predetermined lane change condition: determining a second target lane change merging entrance from a plurality of lane change merging entrances based on the current scene data; determining a first lane change cost based on the first target lane change merge, wherein the first lane change cost is used to represent: a cost of changing lanes according to the first target lane change merge; determining a second lane change cost based on the second target lane change merge, wherein the second lane change cost is used to represent: a cost of changing lanes according to the second target lane change merge; and Based on the first lane change cost value and the second lane change cost value, a new target lane change merge is determined from the first target lane change merge and the second target lane change merge, so as to determine an updated lane change planning path based on the new target lane change merge.

6. The method according to claim 3, wherein: The predetermined lane change condition includes: completing the lane change at a safe driving speed within a predetermined time period.

7. The method according to claim 2, wherein: The feature data that meets the predetermined extraction conditions includes at least one of the following: Data on obstacles related to lane changes, vehicle data, environmental data, and road traffic regulations data.

8. The method according to claim 3, wherein: When it is determined that the target scene data does not meet the predetermined lane change condition, adjusting the driving speed includes: determining a target acceleration for adjusting a driving speed when it is determined that the target scene data does not satisfy a predetermined lane change condition; When it is determined that the target acceleration satisfies a predetermined speed adjustment condition, the driving speed is adjusted according to the target acceleration.

9. The method according to claim 1, further comprising: Determining the training sample includes: Obtaining initial sample scene data; and Feature data that meets a predetermined extraction condition is extracted from the initial sample scene data as the sample scene data.

10. The method according to claim 9, wherein: The feature data that meets the predetermined extraction conditions includes at least one of the following: Obstacle data, vehicle data, environmental data, and road traffic regulation data related to lane changes.

11. A control device for an autonomous driving vehicle, comprising: a first determining module configured to, in response to receiving a lane change instruction, determine a first target lane change merge from a plurality of lane change merges using a lane change merge selection model based on target scenario data, wherein the target scenario data includes data related to the plurality of lane change merges, and the lane change merge refers to a driving space on a target lane of the lane change that allows the vehicle to perform a lane change task; a second determining module, configured to determine a lane change planning path based on the first target lane change merge entrance; and A driving module, used to control the vehicle to change lanes according to the lane change planning path; The lane change entrance selection model is trained using the following method: Using the training samples to train a deep learning model to obtain the lane change merging entrance selection model; The training samples include sample scene data and labels, the sample scene data includes data related to multiple sample lane change merges, the labels include positive sample labels and negative sample labels, the positive sample labels are used to indicate a first target sample lane change merge, the first target sample lane change merge includes a successfully merged sample lane change merge among the multiple sample lane change merges, and the negative sample labels are used to indicate a second target sample lane change merge, the second target sample lane change merge includes a sample lane change merge among the multiple sample lane change merges except the first target sample lane change merge.

12. The apparatus according to claim 11, further comprising, before the first determining module: The extraction module is used to extract feature data that meets predetermined extraction conditions from the traffic scene data as the target scene data.

13. The apparatus according to claim 11, further comprising, before the second determining module: The adjustment module is used to adjust the driving speed when it is determined that the target scene data does not meet the predetermined lane change condition, so that the adjusted target scene data meets the predetermined lane change condition.

14. The apparatus according to claim 13, further comprising, when determining that the target scene data does not satisfy the predetermined lane change condition, adjusting the driving speed: The third determining module is used to determine the current scene data, wherein: The current scene data includes target scene data during the process of adjusting the driving speed; as well as The cancellation module is used to cancel the operation of adjusting the driving speed and cancel the lane change when it is determined that the current scene data meets the predetermined lane change cancellation condition.

15. The apparatus according to claim 14, further comprising, in the case of adjusting the driving speed when it is determined that the target scene data does not meet the predetermined lane change condition: a fourth determining module, configured to determine a second target lane change merging entrance from a plurality of lane change merging entrances based on the current scene data; a fifth determining module, configured to determine a first lane change cost based on the first target lane change merge, wherein the first lane change cost is used to represent a cost of changing lanes according to the first target lane change merge; a sixth determining module, configured to determine a second lane change cost based on the second target lane change merge, wherein the second lane change cost is used to represent a cost of changing lanes according to the second target lane change merge; and An updating module is configured to determine a new target lane change merge from the first target lane change merge and the second target lane change merge based on the first lane change cost value and the second lane change cost value, so as to determine an updated lane change planning path based on the new target lane change merge.

16. The device according to claim 13, wherein The predetermined lane change condition includes: completing the lane change at a safe driving speed within a predetermined time period.

17. The device according to claim 12, wherein The feature data that meets the predetermined extraction conditions includes at least one of the following: Data on obstacles related to lane changes, vehicle data, environmental data, and road traffic regulations data.

18. The device according to claim 13, wherein The adjustment module includes: an acceleration adjustment unit, configured to determine a target acceleration for adjusting a driving speed if it is determined that the target scene data does not satisfy a predetermined lane change condition; The speed adjustment unit is configured to adjust the driving speed according to the target acceleration when it is determined that the target acceleration satisfies a predetermined speed adjustment condition.

19. The apparatus according to claim 11, further comprising: Sample determination module, including: a data acquisition unit, configured to acquire initial sample scene data; and The data extraction unit is configured to extract feature data satisfying a predetermined extraction condition from the initial sample scene data as the sample scene data.

20. The device according to claim 19, wherein The feature data that meets the predetermined extraction conditions includes at least one of the following: Obstacle data, vehicle data, environmental data, and road traffic regulation data related to lane changes.

21. 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 10.

22. 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 to 10.

23. 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 10.

24. An autonomous driving vehicle comprising: The electronic device as claimed in claim 21.

Images