Calibration method and device for autonomous driving vehicle

Abstract

A method for calibrating an autonomous vehicle includes: obtaining design trajectory information, which is information in a vehicle coordinate system, and converting the design trajectory information into information in a world coordinate system; generating a planned trajectory for the vehicle based on the vehicle's current position, the planned trajectory comprising a collection trajectory and a starting trajectory; the collection trajectory corresponds to the designed driving trajectory indicated by the design trajectory information, with the starting trajectory extending from the vehicle's current position to the starting point of the collection trajectory; controlling the vehicle to automatically drive along the planned trajectory, and commencing driving data collection when the vehicle reaches the starting point of the collection trajectory; and using the driving data to calibrate the vehicle's calibration objects. This method enables high-quality and rapid automatic collection of driving data, for example, improving the calibration accuracy of calibration objects such as cameras and radars.

Description

Technical Field

[0001] The present application relates to the field of autonomous vehicles (AV), and in particular to a calibration method and device for an autonomous vehicle. Background Art

[0002] Currently, autonomous driving technology is attracting much attention. ADAS (Advanced Driving Assistance System) is a necessary configuration for achieving full or partial autonomous driving of vehicles. It involves many subsystems such as perception fusion, planning control, and power and chassis actuators. The algorithm model of each subsystem contains a large number of ECU (Electronic Control Unit) control parameters that need to be calibrated. The advanced driving assistance system also has an ECU on-board diagnostic function for identifying faulty components, and the diagnostic parameters contained in the above function also need to be calibrated. The vehicle calibration process, including the process of optimizing ECU parameters and optimizing the parameters of the algorithm model, is crucial to the performance of the entire vehicle. It can be said that the calibration accuracy is directly related to whether the autonomous driving function can operate normally and accurately.

[0003] In order to obtain high-precision calibration results, it is necessary to collect high-quality driving data for calibrating various parameters. In addition, in order to meet the scale of vehicle mass production, it is also necessary to quickly collect driving data to achieve efficient calibration. In the existing technology, it is necessary to manually drive the vehicle to collect driving data in a specific static workstation / or dynamic calibration channel. When driving manually, it is difficult to accurately achieve driving according to the required trajectory and speed, resulting in low quality of collected data. Moreover, when manually driving a vehicle to collect data, it may be necessary to re-collect data due to the low quality of the collected data, affecting the speed of data collection. Moreover, manual driving is easily restricted by external environmental conditions and physical conditions, which will also affect the speed of data collection.

[0004] Based on the above, a technology is needed that can automatically collect driving data with high quality and speed, so as to perform calibration with high precision and efficiency. Summary of the Invention

[0005] The present application provides a calibration method and apparatus for an autonomous driving vehicle that can automatically collect driving data with high quality and speed.

[0006] In a first aspect, a calibration method for an autonomous driving vehicle is provided, the calibration method comprising: obtaining first trajectory information; obtaining vehicle position information; generating a planned trajectory based on the first trajectory information and the position information; and starting to collect driving data when the vehicle automatically drives to a first position according to the planned trajectory, the first position corresponding to a preset position on the first trajectory indicated by the first trajectory information. The generated planned trajectory includes a collection trajectory and a starting trajectory. The collection trajectory corresponds to the first trajectory designed according to the calibration requirements and is a trajectory for collecting driving data. The starting trajectory extends from the position indicated by the vehicle position information (the initial position of the vehicle) to the starting point of the collection trajectory.

[0007] The first trajectory information can be obtained from a memory within the vehicle or from an external device in communication with the vehicle. The first trajectory information can be the coordinate information of multiple trajectory points on the first trajectory in the vehicle coordinate system or the coordinate information of the multiple trajectory points in the world coordinate system. The shape of the first trajectory can be a curve, a straight line, or a combination of curves and straight lines. The vehicle's position information can be obtained, for example, using a positioning function provided by the vehicle.

[0008] By adopting the calibration method of the first aspect, a planned trajectory is generated based on the first trajectory information, and driving data is collected when the vehicle automatically drives along the pre-designed trajectory. This can realize unmanned operation of the data collection process and improve the efficiency of data collection. Moreover, compared with manual driving, the vehicle can be accurately driven along the desired trajectory. Therefore, when there are special requirements for the driving trajectory when collecting data, the collection quality of driving data can be improved.

[0009] As a possible implementation of the first aspect, the first trajectory information is information in a vehicle coordinate system; the first trajectory information is converted into second trajectory information in a world coordinate system; and a planned trajectory is generated based on the second trajectory information and the position information.

[0010] The second trajectory information includes, for example, the coordinates of each trajectory point on the first trajectory in the world coordinate system. Depending on the data collection site, the actual trajectory of the vehicle when collecting data will inevitably be different. If trajectory information is designed and pre-stored for each site, this will increase the workload during design. Using the above method, the same first trajectory information can be mapped to data collection sites located in different locations through coordinate conversion, without having to design the first trajectory information separately for different data collection sites, thereby reducing the design workload.

[0011] As a possible implementation of the first aspect, first coordinate information is obtained, where the first coordinate information indicates coordinates of the preset position in the world coordinate system; and based on the first coordinate information, the first trajectory information is converted into second trajectory information in the world coordinate system. The first coordinate information can be obtained from a memory within the vehicle or from an external device communicatively connected to the vehicle.

[0012] By adopting this method, when data collection is performed at multiple data collection sites located at different locations, the same first trajectory information can be automatically mapped to data collection sites at different locations by changing the first coordinate information. Therefore, data collection sites at different locations can be handled with simple processing.

[0013] As a possible implementation manner of the first aspect, the first position corresponds to a starting point of the first trajectory.

[0014] As a possible implementation of the first aspect, the vehicle is caused to automatically travel according to the planned trajectory from the position indicated by the position information to a position corresponding to the starting point of the first trajectory.

[0015] In this way, the vehicle automatically drives from the initial position to the position corresponding to the starting point of the first trajectory according to the planned trajectory, that is, automatically drives to the starting point of the collection trajectory. Therefore, when there are special requirements such as requiring the vehicle to travel at a specified speed on the collection trajectory when collecting driving data, by setting a preliminary distance from the initial position to the starting point of the collection trajectory, it is possible to ensure that the vehicle reaches a certain speed on the collection trajectory.

[0016] As a possible implementation of the first aspect, the vehicle body coordinate system includes a rectangular coordinate system defined by SAE, a rectangular coordinate system defined by ISO, or a rectangular coordinate system defined based on an IMU.

[0017] As a possible implementation of the first aspect, the driving data is used to calibrate a calibration object possessed by the vehicle; the calibration object includes one or more of a camera, radar, ECU parameters, or parameters of an ADAS algorithm model; the driving data includes one or more of the following data: data obtained by photographing a target object by a camera, data obtained by measuring the target object by a radar, the vehicle's wheel speed, yaw rate, and steering wheel angle, wherein the target object is set at a specified location. The camera may be one or more. The radar may include a lidar, a millimeter-wave radar, an ultrasonic radar, and the like.

[0018] This approach improves the quality of driving data collection, thereby improving the calibration quality of the calibration object. In particular, the improved quality of camera and radar data improves the calibration quality of both radar and camera calibration. This is because camera and radar calibration require strict vehicle trajectory. With manual driving, the actual trajectory can deviate significantly from the desired trajectory. Autonomous driving, on the other hand, precisely steers the vehicle along the desired trajectory, improving the quality of the collected data and, consequently, the calibration quality.

[0019] In a second aspect, a calibration device for an autonomous driving vehicle is provided, the calibration device comprising an acquisition module and a processing module, wherein the acquisition module is used to acquire first trajectory information; the acquisition module is also used to acquire vehicle position information; the processing module is used to generate a planned trajectory based on the first trajectory information and the position information; the processing module is also used to start collecting driving data when the vehicle automatically drives to a first position according to the planned trajectory, and the first position corresponds to a preset position on the first trajectory indicated by the first trajectory information. The generated planned trajectory includes a collection trajectory and a starting trajectory. The collection trajectory corresponds to the first trajectory designed according to the calibration requirements, and is a trajectory for collecting driving data. The starting trajectory extends from the position indicated by the vehicle's position information (the vehicle's initial position) to the starting point of the collection trajectory.

[0020] By adopting the calibration device of the second aspect, a planned trajectory is generated according to the first trajectory information, and driving data is collected when the vehicle automatically drives according to the pre-designed trajectory, unmanned operation of the data collection process can be realized, the efficiency of data collection can be improved, and compared with manual driving, the vehicle can be accurately driven according to the desired trajectory. Therefore, when there are special requirements for the driving trajectory when collecting data, the collection quality of driving data can be improved.

[0021] As a possible implementation of the second aspect, the first trajectory information is information in a vehicle coordinate system; the processing module is further used to convert the first trajectory information into second trajectory information in a world coordinate system; the processing module is further used to generate a planned trajectory based on the second trajectory information and the position information.

[0022] In this way, the same first trajectory information can be mapped to data collection sites at different locations through coordinate conversion without redesigning the first trajectory information for the data collection sites at different locations. Therefore, it is possible to cope with data collection sites at different locations.

[0023] As a possible implementation method of the second aspect, the acquisition module is further used to obtain first coordinate information, which indicates the coordinates of the preset position in the world coordinate system; the processing module is further used to convert the first trajectory information into second trajectory information in the world coordinate system based on the first coordinate information.

[0024] By adopting this method, when data collection is performed at multiple data collection sites located at different locations, the same first trajectory information can be automatically mapped to data collection sites at different locations by changing the first coordinate information. Therefore, data collection sites at different locations can be handled with simple processing.

[0025] As a possible implementation manner of the second aspect, the first position corresponds to a starting point of the first trajectory.

[0026] As a possible implementation of the second aspect, the processing module is further configured to enable the vehicle to automatically travel from the position indicated by the position information to a position corresponding to the starting point of the first trajectory according to the planned trajectory.

[0027] In this way, the vehicle automatically drives from the initial position to the position corresponding to the starting point of the first trajectory according to the planned trajectory, that is, automatically drives to the starting point of the collection trajectory. Therefore, when there are special requirements such as requiring the vehicle to travel at a specified speed on the collection trajectory when collecting driving data, by setting a preliminary distance from the initial position to the starting point of the collection trajectory, it is possible to ensure that the vehicle reaches a certain speed on the collection trajectory.

[0028] As a possible implementation manner of the second aspect, the vehicle body coordinate system includes a rectangular coordinate system defined by SAE, a rectangular coordinate system defined by ISO, or a rectangular coordinate system defined based on an IMU.

[0029] As a possible implementation of the second aspect, the driving data is used to calibrate a calibration object of the vehicle; the calibration object includes one or more of a camera, a radar, an ECU parameter, or parameters of an ADAS algorithm model; the driving data includes one or more of the following data: data obtained by photographing the target object by a camera, data obtained by measuring the target object by a radar, the vehicle's wheel speed, yaw rate, and steering wheel angle, wherein the target object is set at a specified position.

[0030] By adopting this method, the collection quality of driving data can be improved, and thus the calibration quality of the calibration object can be improved.

[0031] In a third aspect, an electronic device is provided, which includes a processor and an interface circuit, wherein the processor is coupled to a memory through the interface circuit, and the processor is used to execute program code in the memory so that the processor executes the technical solution provided by the first aspect or any possible implementation method.

[0032] In a fourth aspect, a computer storage medium is provided, which includes computer instructions. When the computer instructions are executed on an electronic device, the electronic device executes the technical solution provided by the first aspect or any possible implementation method.

[0033] In a fifth aspect, a computer program product is provided. When the computer program product is run on a computer, the computer is enabled to execute the technical solution provided by the first aspect or any possible implementation method.

[0034] The technical details and technical effects of any aspect from the third to the fifth aspect and its possible implementation methods can be referred to the relevant descriptions in the first aspect, the second aspect and its possible implementation methods, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] The following further illustrates the various features of the present application and the relationships between the various features with reference to the accompanying drawings. The accompanying drawings are all exemplary, and some features are not shown in actual proportion. In addition, some drawings may omit features that are customary in the field to which the present application relates and are not necessary for the present application, or additional features that are not necessary for the present application may be shown. The combination of the various features shown in the accompanying drawings is not intended to limit the present application. In addition, throughout this specification, the same figure numbers refer to the same content. The specific description of the drawings is as follows:

[0036] Figure 1 is a functional structure diagram of an autonomous driving vehicle according to an embodiment of the present application;

[0037] Figure 2 It is a schematic diagram of the calibration implementation process of the advanced driver assistance system;

[0038] Figure 3 is a schematic diagram of a calibration site according to an embodiment of the present application;

[0039] Figure 4 Schematic diagram of the principle of VIL / MOP processing in an embodiment of the present application;

[0040] Figure 5 is a schematic diagram of a coordinate conversion method according to an embodiment of the present application;

[0041] Figure 6 This is a flow chart of a calibration method for an autonomous driving vehicle provided in an embodiment of the present application;

[0042] Figure 7 is a schematic diagram of another calibration site according to an embodiment of the present application;

[0043] Figure 8 is a schematic diagram showing a trajectory tracking process according to an embodiment of the present application;

[0044] Figure 9 This is a schematic structural diagram of a calibration device for an autonomous driving vehicle provided in an embodiment of the present application;

[0045] Figure 10 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0046] Below, the technical solution of this application will be described with reference to the accompanying drawings.

[0047] First, the definitions of autonomous driving and autonomous driving vehicles in this application are explained. Autonomous driving refers to the ability of a vehicle to automatically perform driving tasks such as path planning, behavioral decision-making, and motion planning (speed and trajectory planning). Autonomous driving includes five levels: L1, L2, L3, L4, and L5. Level L1: Assisted driving, the vehicle provides driving for one of the steering wheel and acceleration and deceleration operations, and the human driver is responsible for other driving actions. Level L2: Partial autonomous driving, the vehicle provides driving for multiple operations of the steering wheel and acceleration and deceleration, and the human driver is responsible for other driving actions. Level L3: Conditional autonomous driving, the vehicle completes most of the driving operations, and the human driver needs to concentrate in case of emergency. Level L4: Highly autonomous driving, the vehicle completes all driving operations, the human driver does not need to concentrate, but the road and environmental conditions are limited. Level L5: Fully autonomous driving, the vehicle completes all driving operations, the human driver does not need to concentrate, and there are no restrictions on roads and environments. The autonomous driving vehicle in this application refers to a vehicle that can achieve autonomous driving of level L2 and above.

[0048] Figure 1 FIG. 1 is a functional structure diagram of vehicle 1 as an autonomous driving vehicle. Figure 1 As shown, the vehicle 1 includes a control device 10 , a radar 20 , a camera 30 , a communication device 40 , a GNSS (Global Navigation Satellite System) 50 , an IMU (Inertial Measurement Unit) 60 , a power system 70 , a steering system 80 , and a braking system 90 .

[0049] The camera 20 and the radar 30 are used to sense the surrounding environment of the vehicle 1 and output the sensed information to the control device 10. The radar 20 may include a laser radar, a millimeter-wave radar, an ultrasonic radar, etc. There may be one or more cameras 30. The communication device 40 is used to wirelessly communicate with external devices such as base stations and management platforms. The power system 70 includes a drive ECU (not shown) and a drive source (not shown). The drive ECU can control the drive source according to instructions sent from the control device 10, thereby controlling the driving force. The steering system 80 includes a steering ECU (not shown), namely an EPS (Electric Power Steering) ECU, and an EPS motor (not shown). The steering ECU can control the EPS motor according to instructions sent from the control device 10, thereby controlling the direction of the wheels. The braking system 90 includes a brake ECU (not shown) and a brake mechanism (not shown). The brake ECU can control the brake mechanism according to instructions sent from the control device 10, thereby controlling the braking force.

[0050] The control device 10 can be implemented by, for example, one ECU or a combination of multiple ECUs. The ECU is a computing device comprising a processor, a memory, and a communication interface connected via an internal bus. The memory stores program instructions that, when executed by the processor, function as corresponding functional modules. These functional modules include a path planning module 12, a behavior decision module 13, a prediction module 14, a motion planning module 15, a motion control module 17, and a positioning module 18. That is, the vehicle control device 10 implements these functional modules by executing a program (software) by a processor. However, the vehicle control device 10 can also implement all or part of these functional modules through hardware such as LSI (Large Scale Integration) and ASIC (Application Specific Integrated Circuit), or can also implement all or part of these functional modules through a combination of software and hardware. Optionally, a high-precision map (HD Map) 11 is also stored in the control device 10. Optionally, the control device 10 also has an acquisition and calibration module 16.

[0051] The path planning module 12 is used to plan the driving path of the vehicle 1 based on the high-precision map 11 or the perception information of the camera 20 and the radar 30. The behavior decision module 13 is used to implement human-like driving decisions, such as driving, following, turning, changing lanes, and parking. The prediction module 14 is used to predict the movement trajectory and intentions of road traffic participants, such as other vehicles and pedestrians. The motion planning module 15 is used to plan the movement behavior of the vehicle 1, including the driving trajectory and driving speed. The acquisition and calibration module 16 is used to obtain the collected driving data and calibrate the on-board equipment such as cameras and radars, ECU parameters, and parameters in the ADAS algorithm model. The motion control module 17 is used to generate control instructions for sending to the power system 70, steering system 80, and braking system 90 based on the planning results of the motion planning module 15. The positioning module 18 can locate the current position of the vehicle 1 by fusing GNSS information and IMU information.

[0052] exist Figure 1 The autonomous driving vehicle shown is equipped with an advanced driver assistance system for realizing the autonomous driving function. The advanced driver assistance system contains a large number of parameters that need to be calibrated. Figure 2 Figure 1 is a schematic diagram of the calibration implementation process of the advanced driver assistance system configured in an autonomous vehicle. Figure 2As shown in the figure, the calibration implementation process for an autonomous vehicle's advanced driver assistance system (ADAS) primarily involves calibration of subsystem parameters at the execution, perception, and functional layers. The execution layer involves calibration of the powertrain, braking, steering, four-wheel alignment parameters, and suspension systems. The perception layer involves calibration of GNSS and INS (Initial Navigation System), camera, lidar, millimeter-wave radar, and ultrasonic radar. GNSS includes GPS (Global Positioning System), GLONASS (Global Navigation Satellite System), Galileo (Galileo Navigation Satellite System), and BDS (Beidou Navigation Satellite System). The functional layer involves calibration of the vehicle's longitudinal and lateral control modules, ADAS basic functions, and ADAS driving style. Longitudinal control primarily involves speed control, achieved through control of the brakes, throttle, and gear position. Lateral control is mainly used to control the heading, by changing the steering wheel torque or angle, etc., to make the vehicle move in the desired direction. Basic ADAS functions include ACC (Adaptive Cruising System), LCC (Lane Center Control), ALC (Auto Lane Change), etc. Driving style refers to the way of driving or habitual driving method, which includes the choice of driving speed, the choice of driving distance, etc. Driving styles include aggressive, steady, cautious, etc.

[0053] In order to carry out calibration, it is necessary to collect relevant driving data. The collection of driving data can be carried out in a designated calibration station, calibration channel or calibration site. Figure 3 This is a schematic diagram of a calibration site in an embodiment of the present application. Figure 3 The calibration site is used, for example, to calibrate sensing devices such as cameras and radars installed on the vehicle 1. Figure 3As shown, a calibration site with a length of L and a width of B is provided with multiple calibration plates 2 on both sides, with a spacing of d between each plate. The camera and radar mounted on vehicle 1 sense the calibration plates 2, collecting camera and radar perception data as driving data. The camera and radar parameters are calibrated based on this driving data. The camera calibration method can, for example, use the Zhang Zhengyou algorithm. Camera parameters include, for example, intrinsic parameters, extrinsic parameters, and distortion parameters. Radar parameters include, for example, rotation and translation parameters. Joint calibration of the camera and radar is also possible.

[0054] The length L, width B, and interval b can be set freely. The shape of the calibration site is not limited to Figure 3 The straight line in the figure can also be a curve shape according to the specific calibration requirements. The setting method of the calibration plate 2 is not limited to Figure 3 In the above method, for example, the distance between each two calibration plates 2 can be set to be different. The calibration plate 2 can be, for example, an AprilTag (a visual positioning marker) or a checkerboard calibration plate. The AprilTag calibration plate can be Tag16h5, Tag25h9, Tag36h11, etc.

[0055] For Figure 3 The process of collecting driving data in the calibration site shown usually has specific requirements, mainly including requirements for the vehicle's driving trajectory and driving speed when collecting data. For example, the vehicle is usually required to travel according to the collection trajectory R at a designed speed. In the case of manual driving, it is difficult to accurately make the vehicle travel according to the collection trajectory R at a designed speed. Therefore, the quality of the collected driving data is not high, and the collection speed is slow, resulting in poor calibration quality and low calibration efficiency. To this end, the present application proposes a calibration method for an autonomous driving vehicle based on VIL (Vehicle inLoop) / MOP (MotionPlanning) processing, which collects driving data in an automated manner with high quality and speed. VIL is to embed a complete vehicle system into a simulation loop for simulation testing, which can also be understood as a virtual-real combination method that combines simulation testing and real vehicle testing. In the present application, the VIL / MOP processing combining VIL and MOP is used to control the vehicle 1 to automatically travel as required in the calibration site to achieve automatic collection of driving data.

[0056] Using the autonomous vehicle calibration method provided herein, the motion planning module 15 of the control device 10 of the vehicle 1 obtains pre-stored design trajectory information, which indicates the vehicle's designed driving trajectory. This pre-stored design trajectory information includes coordinate information of multiple trajectory points on the designed driving trajectory in the vehicle coordinate system. The motion planning module 15 obtains pre-stored reference point information, which includes the world coordinates of at least one reference point. The reference point is a point on the designed driving trajectory. The reference point information may also include the vehicle's designed heading angle at the reference point. Based on the reference point information, the motion planning module 15 converts the coordinates of the multiple trajectory points on the designed driving trajectory into world coordinates through coordinate transformation, thereby obtaining a driving trajectory of the vehicle within the calibration site for collecting driving data (hereinafter referred to as the "collection trajectory"). Then, based on the positioning information of the vehicle 1, the motion planning module 15 plans the planned trajectory of the vehicle 1 within the calibration site. The planned trajectory includes a collection trajectory and a starting trajectory, which is used to automatically drive the vehicle 1 from its current position to the starting point of the collection trajectory. When the vehicle 1 travels along the planned trajectory to the start collection position on the collection trajectory, the collection and calibration module 16 starts to collect driving data, and the driving data is used to calibrate the calibration object possessed by the vehicle. The start collection position corresponds to a pre-set position on the designed driving trajectory. The start collection position may, for example, correspond to the starting point of the designed driving trajectory. That is, the start collection position may, for example, be the starting point of the collection trajectory. The calibration objects include devices at the perception layer such as cameras and radars, as well as devices at the execution layer such as braking systems, steering systems, and power systems, and basic ADAS functions at the functional layer. When the calibration object is a camera, the driving data is, for example, the camera's detection of a target object (for example, Figure 3 When the calibration object is a radar, the driving data is, for example, raw data obtained by the radar sensing the target object.

[0057] Below, we will refer to Figures 4 to 6 , the calibration method of the autonomous driving vehicle in the embodiment of the present application is described in detail.

[0058] Figure 4 Schematic diagram of the principle of VIL / MOP processing in the embodiment of the present application. Figure 4 As shown, first, the pre-stored MOP file is loaded into the MOP injection node to initialize the MOP injection node. In this embodiment, the MOP injection node is the motion planning module 15 of the control device 10. In some embodiments, a dedicated functional module can also be provided in the control device 10 to implement the functions of the MOP injection node. The MOP file is stored in, for example, a memory provided by the control device 10, but is not limited thereto. The MOP file includes, for example, design trajectory information and design speed information.

[0059] The design trajectory information is information about the design driving trajectory of the vehicle 1 designed according to the calibration requirements. In this embodiment, the design trajectory information is a formula or a point set in the vehicle body coordinate system. That is, the position of the point on the design driving trajectory is defined by the coordinates in the vehicle body coordinate system. The vehicle body coordinate system is used to describe the relative position relationship between the objects around the vehicle and the vehicle itself. The vehicle body coordinate system can be used to describe the posture of the vehicle body. In this embodiment, the vehicle body coordinate system adopts the rectangular coordinate system defined by SAE (Society of Automotive Engineers). In addition, in some embodiments, the rectangular coordinate system defined by ISO (International Organization for Standardization) or the rectangular coordinate system defined based on IMU can also be used. The design speed information is information about the design driving speed of the vehicle 1 on the design driving trajectory.

[0060] The designed driving trajectory and the designed driving speed can be freely designed according to the calibration needs. The designed driving trajectory can be a curve shape, a straight line shape, or a combination of a straight line and a curve shape. The designed driving speed can be that the vehicle 1 maintains a constant speed on the designed driving trajectory, or different driving speeds can be designed for different parts of the designed driving trajectory. In addition to being obtained through forward design, the designed driving trajectory and design driving speed information in the MOP file can also be obtained through manual teaching. The manual teaching method refers to manually driving the vehicle in the calibration site to demonstrate the trajectory and speed when collecting data, and recording the driving trajectory and driving speed at this time as the designed driving trajectory and design driving speed.

[0061] After loading the MOP file, in order to map the designed driving trajectory to the calibration site, the motion planning module 15, which serves as the MOP injection node, converts the coordinates of all points on the designed driving trajectory into world coordinates based on the pre-stored reference point information. In this embodiment, the reference point information includes the world coordinates of the reference point and the designed heading angle of the vehicle 1 at the reference point. The designed heading angle can indicate the angle between the velocity of the vehicle's center of mass (i.e., the vehicle's driving direction) and the coordinate axis of the world coordinate system in the world coordinate system. That is, the angle between the vehicle coordinate system and the world coordinate system can be determined based on the above-mentioned designed heading angle. The above-mentioned designed heading angle is designed based on the calibration site. In this embodiment, the reference point includes the starting point of the designed driving trajectory. In some embodiments, the reference point may not include the starting point of the designed driving trajectory, but include at least one point other than the starting point on the designed driving trajectory. In some embodiments, the reference point information may not include the designed heading angle, but include the world coordinates of two points on the designed driving trajectory, and the angle between the vehicle coordinate system and the world coordinate system is determined based on the world coordinates of the two points.

[0062] In this embodiment, the world coordinate system adopts the UTM (Universal Transverse Mercator Grid System) coordinate system. In some embodiments, the WGS-84 (World Geodetic System-1984 Coordinate System) coordinate system may also be adopted.

[0063] Figure 5 Schematic diagram of the coordinate conversion method of the embodiment of the present application. Figure 5 As shown, the coordinates of the reference point O1 in the world coordinate system are (x0, y0), the coordinates of the track point A on the designed driving trajectory in the vehicle coordinate system are (x, y), and when the angle between the vehicle coordinate system and the world coordinate system is α, the coordinates of the track point A in the world coordinate system (x′, y′) can be calculated according to the following formula.

[0064] x′=cos(α)*x+sin(α)*y+x0

[0065] y′=cos(α)*y-sin(α)*x+y0

[0066] The motion planning module 15, which serves as an MOP injection node, obtains the current position information of the vehicle from the positioning module 18, which serves as a positioning node, and plans the planned trajectory of the vehicle 1 within the calibration site based on the current position of the vehicle and the designed driving trajectory. The planned trajectory includes a collection trajectory corresponding to the designed driving trajectory, and a starting trajectory for automatically driving the vehicle 1 from the current position to the starting point of the collection trajectory. A collection start position and a collection end position are set on the collection trajectory. The collection start position is the position where the collection of driving data starts. The collection end position is the position where the collection of driving data ends. In this embodiment, the collection start position corresponds to the starting point of the designed driving trajectory, and the collection end position corresponds to the end point of the designed driving trajectory. Regarding the collection start position and the collection end position, it can be pre-set in the designed trajectory information which point on the designed driving trajectory is the collection start point or collection end point corresponding to the collection start position or collection end position; or it can be pre-specified in the designed trajectory information, and the starting point and end point of the designed driving trajectory can be directly assumed to correspond to the collection start position or collection end position.

[0067] Motion planning module 15 plans the speed and acceleration of vehicle 1 along the planned trajectory based on the design speed information. To ensure the quality of the collected driving data, the planned speed of vehicle 1 along the collected trajectory must strictly comply with the design speed information. There are no strict requirements for the planned speed of vehicle 1 on the starting trajectory—that is, the planned speed from vehicle 1's current position to the starting point of the collected trajectory. As long as vehicle 1 meets the design speed information upon reaching the starting point of the collected trajectory, it is sufficient.

[0068] After the motion planning module 15 completes the planning of the trajectory and speed, the motion control module 17, which serves as the control node, controls the motion behavior of the vehicle 1 according to the planning results, so that the vehicle 1 automatically travels according to the planned trajectory and speed. The motion control module 17 also controls the motion behavior of the vehicle 1 based on the chassis information of the vehicle 1 obtained. The chassis information includes, for example, information such as wheel speed, turning angle, and yaw rate. As described above, in the embodiment of the present application, the positioning and control node is, for example, the positioning module 18 and the motion control module 17 of the control device 10. In some embodiments, the positioning and control node may also be a module with related functions of a mobile data center (MDC) serving as an autonomous driving controller.

[0069] While vehicle 1 is autonomously traveling along a planned trajectory and speed, positioning module 18 acquires information from GNSS 50 and IMU 60, determines the current location of vehicle 1 based on the acquired information, and provides this current location information to motion planning module 15. Based on this current location information, motion planning module 15 can make real-time adjustments to the trajectory and speed of vehicle 1 while vehicle 1 is autonomously traveling.

[0070] Figure 6 This is a flow chart of the automatic driving vehicle calibration method based on VIL / MOP processing provided by an embodiment of the present application. Vehicle 1 can be driven by the driver to the initial position of the calibration site, or directly transported to the initial position of the calibration site after completing assembly on the production assembly line. After the driver or staff turns on the automatic driving switch of vehicle 1 and starts the application with calibration function, the control device 10 starts to execute Figure 6 As shown in the method. Figure 6 As shown, the method includes steps S210 to S270. Figure 3 The processing of steps S210 to S270 is described in detail for the scenario.

[0071] S210: Obtaining designed trajectory information and designed speed information. As described above, the designed trajectory information and designed speed information are contained in a pre-stored MOP file. The designed trajectory information includes coordinate information of multiple trajectory points on the designed driving trajectory in the vehicle coordinate system. The MOP file can be pre-stored in a memory within vehicle 1 or obtained from an external device in communication with vehicle 1. Figure 3 In the figure, vehicle 1 is at the initial position Po of the calibration site, and the design trajectory information and design speed information are obtained by obtaining the MOP file.

[0072] S220: Perform coordinate conversion based on the world coordinates of the reference point. Figure 5 The coordinate conversion method converts the coordinates of all track points on the designed driving track into world coordinates. The world coordinates of the reference point can be pre-stored in a memory inside the vehicle 1 or obtained from an external device that is communicatively connected to the vehicle 1.

[0073] Figure 3 In , according to the world coordinates of the starting point Ps obtained, the coordinate transformation of the design trajectory information is performed to obtain the acquisition trajectory R. The acquisition start position is the starting point Ps of the acquisition trajectory R, and the acquisition end position is the end point Pe of the acquisition trajectory R.

[0074] S230: The MOP route is set based on the current position information. Specifically, a planned trajectory is generated based on the current position of vehicle 1, and a planned speed along the planned trajectory is generated based on the set speed information. As described above, the generated planned trajectory includes a collected trajectory corresponding to the designed driving trajectory and a starting trajectory from the current position of vehicle 1 to the starting point of the collected trajectory.

[0075] Figure 3 In the initial stage, a MOP route is set from the initial position Po to the collection start position Ps, and then from the collection start position Ps along the collection trajectory R to the collection end position Pe. The speed along the collection trajectory R is planned according to the design speed information obtained in S210. In addition, after the vehicle 1 begins autonomous driving along the MOP route in the initial stage, the trajectory and speed to reach the end point of the MOP route can be adjusted in real time based on changes in the current position of the vehicle during driving.

[0076] The initial position Po is different from the collection start position Ps because a certain preliminary distance ensures that vehicle 1 reaches a certain speed at the collection start position Ps. This allows for special requirements, such as requiring vehicle 1 to maintain a constant speed while collecting driving data, to be met. Furthermore, since the initial position Po is not located on the collection trajectory R, driving data collection has not yet begun at this position. Therefore, the positional accuracy of vehicle 1 at this time does not affect the quality of driving data collection. Therefore, during the initial stage of vehicle 1 positioning, it is sufficient to place vehicle 1 within a certain range centered on the initial position Po, rather than requiring it to be positioned at the initial position Po. Vehicle 1 can automatically travel from the initial position Po or a position near it to the collection start position Ps.

[0077] S240: Issue control instructions for automatically driving the vehicle along the MOP route. Based on the set MOP route, control instructions are generated for transmission to the powertrain 70, steering system 80, braking system 90, and other components of vehicle 1. The powertrain 70, steering system 80, braking system 90, and other components execute the control instructions, causing vehicle 1 to automatically drive along the MOP route.

[0078] S250: Determine whether the current position of vehicle 1 is the collection start position. During the autonomous driving process, the current position of vehicle 1 is obtained based on IMU and GNSS information to determine whether vehicle 1 has reached the collection start position Ps. If so, execute S260; otherwise, execute S270.

[0079] S260: Start collecting driving data. Driving data includes, for example, images captured by the camera on the calibration plate 2, radar raw data obtained by the radar sensing the calibration plate 2, and the like. The acquired driving data can be used to calibrate the camera, radar, and other calibration objects online, and directly output the calibration results, but is not limited to this. For example, the acquired driving data can also be stored and calibrated later. Regarding the calibration results, in addition to being stored in the memory inside the vehicle 1, the calibration results can also be uploaded to the management platform through a communication connection with an external management platform, and the management platform can manage the information of multiple vehicles in a unified manner. In some embodiments, the processing in this step can also be replaced by starting the calibration mode.

[0080] S270: Determine whether the vehicle has reached the endpoint or has been taken over by the driver. If so, the process ends; otherwise, the process returns to S230. The endpoint here can be, for example, the acquisition end position Pe on the acquisition trajectory R. When the vehicle reaches the acquisition end position Pe or the driver has taken over, the process ends, which can also be understood as the end of driving data collection or the end of calibration mode. In some embodiments, before the process ends, it can determine whether the calibration was successful and record the calibration success / failure result.

[0081] The calibration method of the autonomous driving vehicle of the embodiment of the present application collects driving data while the vehicle 1 automatically drives from the collection start position Ps to the collection end position Pe according to a pre-designed driving trajectory and driving speed. Compared with manual driving, the vehicle can be accurately tracked and controlled in the lateral and longitudinal directions, thereby improving the quality of the collected driving data and thus improving the calibration accuracy. Moreover, due to the high quality of the collected driving data, compared with the manual driving of the prior art, the data required for calibration can be collected using a shorter designed driving trajectory. Specifically, for example, Figure 3 In this scenario, the existing technology requires a designed driving trajectory of about 70 meters. However, using the method of the present application, the calibration of the camera and radar can be completed using a designed driving trajectory of about 50 meters, which is actually equivalent to improving the data acquisition speed.

[0082] The calibration method for autonomous driving vehicles according to the embodiment of the present application can realize unmanned operation of the entire calibration process and realize all-weather data collection operations, thereby reducing the disturbance caused by human driving and improving the calibration success rate while increasing the data collection speed to better meet the scale requirements of vehicle mass production.

[0083] The calibration method of the autonomous driving vehicle in the embodiment of the present application is described above, but the embodiment of the present application is not limited thereto. For example, the pre-stored design trajectory information may also be the coordinate information of the points on the designed driving trajectory in the world coordinate system. In this case, the coordinate conversion process can be omitted. However, in the case where the pre-stored design trajectory information is the coordinate information in the vehicle body coordinate system, when data is collected at multiple identical calibration sites located in different locations, by changing the reference point information, the same designed driving trajectory can be automatically mapped to calibration sites in different locations without having to design MOP files for each calibration site separately, thereby reducing the design workload. The collection start position may also not correspond to the starting point of the designed driving trajectory, but to other points on the designed driving trajectory. The collection end position may also not correspond to the end point of the designed driving trajectory, but to other points on the designed driving trajectory.

[0084] Figure 3 The example in which the collected trajectory R is a straight line when collecting driving data for calibrating cameras and radars is schematically listed in FIG. 1 is a linear example. However, in some embodiments, such as Figure 7 As shown, the collection trajectory R can also be in a curved shape. The shape of the collection trajectory R can be designed according to specific calibration requirements. For example, when collecting driving data for calibrating the steering system of the execution layer, the collection trajectory R can be in a curved shape.

[0085] In some embodiments, in addition to collecting driving data from cameras, radars, etc. used to calibrate the perception layer, GNSS data, INS data, vehicle 1's wheel speed, yaw rate, steering wheel angle, and other driving data can also be collected simultaneously and stored centrally. All collected data are timestamped. When calibrating the perception layer or functional layer later, interpolation compensation and other processing can be performed on data with different sampling frequencies based on the timestamp to ensure time synchronization of various data. In this way, efficient collection of integrated comprehensive data can be achieved.

[0086] In some embodiments, the trajectory tracking process of the vehicle 1 can also be visualized and displayed on the display screen of the vehicle display device or the management platform or the mobile terminal held by the calibration engineer. Figure 8 As shown, the planned trajectory shown by the thick solid line and the current position, direction and other information of the vehicle 1 are displayed on the display screen to determine whether the vehicle 1 deviates from the planned trajectory. Figure 8 As shown, virtual lane lines shown by thin solid lines, virtual lane center lines shown by dotted lines, etc. can also be displayed.

[0087] Figure 9 This is a schematic diagram of the structure of the calibration device for an autonomous vehicle provided in an embodiment of the present application. The calibration device can be a vehicle-mounted terminal, or a chip or chip system inside the vehicle-mounted terminal, and can be implemented with reference to Figure 1-8 The calibration method of the autonomous driving vehicle and various optional embodiments are described. Figure 9 As shown, the calibration device 1000 has an acquisition module 1100 and a processing module 1200 .

[0088] Acquisition module 1100 is configured to acquire first trajectory information. Acquisition module 1100 is also configured to acquire vehicle location information. Processing module 1200 is configured to generate a planned trajectory based on the first trajectory information acquired by acquisition module 1100 and the vehicle location information. Processing module 1200 is further configured to begin collecting driving data when the vehicle automatically drives to a first position along the generated planned trajectory. The first position corresponds to a preset position on the first trajectory indicated by the first trajectory information.

[0089] If the first trajectory information is in a vehicle coordinate system, the processing module 1200 is further configured to convert the first trajectory information into second trajectory information in a world coordinate system and generate a planned trajectory based on the second trajectory information and the vehicle's position information. In this case, the acquisition module 1100 may acquire first coordinate information indicating the coordinates of the preset position in the world coordinate system. The processing module 1200 converts the first trajectory information into second trajectory information in the world coordinate system based on the first coordinate information acquired by the acquisition module 1100.

[0090] It should be understood that the calibration device in the embodiment of the present application can be implemented by software, for example, a computer program or instruction with the above functions. The corresponding computer program or instruction can be stored in the memory inside the vehicle terminal, and the processor reads the corresponding computer program or instruction in the memory to implement the above functions. Alternatively, the calibration device in the embodiment of the present application can also be implemented by hardware. The processing module 1200 is a processor, and the acquisition module 1100 is a transceiver circuit or an interface circuit. Alternatively, the calibration device in the embodiment of the present application can also be implemented by a combination of a processor and a software module.

[0091] It should be understood that the relevant design details and technical effects of the calibration device can be referred to Figure 1-8 The description of the method shown will not be repeated here.

[0092] Figure 10 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device can be used as a calibration device for an autonomous driving vehicle to perform reference Figures 1-8 The electronic device may be a vehicle-mounted terminal, or a chip or chip system inside the vehicle-mounted terminal. Figure 10 As shown, the electronic device 1600 includes: a processor 1610, and an interface circuit 1620 coupled to the processor 1610. It should be understood that although Figure 10 Only one processor and one interface circuit are shown in FIG. 1 , but the electronic device 1600 may include other numbers of processors and interface circuits.

[0093] The interface circuit 1620 is used to communicate with other components of the terminal, such as a memory or another processor. The processor 1610 is used to exchange signals with other components through the interface circuit 1620. The interface circuit 1620 may be an input / output interface of the processor 1610.

[0094] For example, the processor 1610 reads the computer program or instructions in the memory coupled thereto through the interface circuit 1620, and decodes and executes these computer programs or instructions. It should be understood that these computer programs or instructions may include the above-mentioned terminal function program, and may also include the above-mentioned function program of the calibration device applied in the terminal. When the corresponding function program is decoded and executed by the processor 1610, the vehicle-mounted terminal or the calibration device in the vehicle-mounted terminal can implement the solution in the calibration method of the autonomous driving vehicle provided in the embodiment of the present application.

[0095] Optionally, these terminal function programs are stored in a memory outside the electronic device 1600. When the terminal function programs are decoded and executed by the processor 1600, part or all of the contents of the terminal function programs are temporarily stored in the memory.

[0096] Optionally, these terminal function programs are stored in a memory inside the electronic device 1600. When the terminal function programs are stored in the memory inside the electronic device 1600, the electronic device 1600 may be provided in a terminal according to an embodiment of the present invention.

[0097] Optionally, part of the contents of these terminal function programs are stored in a memory outside the electronic device 1800 , and other part of the contents of these terminal function programs are stored in a memory inside the electronic device 1800 .

[0098] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0099] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0100] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of the units may be selected according to actual needs to achieve the objectives of the embodiments of the present application.

[0101] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0102] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk.

[0103] An embodiment of the present application further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, it is used to execute at least one of the solutions described in the above embodiments.

[0104] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable media.Computer-readable media can be computer-readable signal media or computer-readable storage media.Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or components, or any combination thereof.More specific examples (non-exhaustive list) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM, Electrical Programmable Read Only Memory or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.In this document, computer-readable storage media can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0105] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0106] The program code contained on the computer-readable medium can be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF (Radio Frequency), etc., or any suitable combination of the above.

[0107] The computer program code for performing the operations of the present application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0108] It should be understood that in the various embodiments of the present application, unless otherwise specified or there is any logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0109] In addition, the terms "first," "second," "third," and the like in the specification and claims are used only to distinguish similar objects and do not represent a specific ordering of the objects. Specific orders or precedences can be interchanged where permitted. The reference numbers representing steps, such as S110, S120, etc., do not necessarily indicate that the steps will be performed accordingly. The order of the steps before and after can be interchanged or performed simultaneously where permitted. The expression "above" regarding quantities and numerical values should be interpreted as including the number itself. The term "comprising" used in the specification and claims should not be interpreted as being limited to the contents listed thereafter; it does not exclude the presence of other elements or steps.

Claims

1. A calibration method for an autonomous driving vehicle, characterized in that: include: Acquiring first trajectory information, where the first trajectory information is acquired from a memory inside the vehicle or from an external device communicatively connected to the vehicle; Obtaining location information of the vehicle; generating a planned trajectory according to the first trajectory information and the position information; When the vehicle automatically drives to a first position according to the planned trajectory, driving data is collected, and the driving data is used to calibrate a calibration object of the vehicle. The first position corresponds to a preset position on the first trajectory indicated by the first trajectory information.

2. The calibration method according to claim 1, characterized in that: The first trajectory information is information in a vehicle coordinate system; Converting the first trajectory information into second trajectory information in a world coordinate system; A planned trajectory is generated according to the second trajectory information and the position information.

3. The calibration method according to claim 2, characterized in that: Acquire first coordinate information, where the first coordinate information indicates the coordinates of the preset position in the world coordinate system; The first trajectory information is converted into second trajectory information in the world coordinate system according to the first coordinate information.

4. The calibration method according to any one of claims 1 to 3, characterized in that: The first position corresponds to a starting point of the first trajectory.

5. The calibration method according to claim 4, characterized in that: Also includes: The vehicle is caused to automatically travel from the position indicated by the position information to the first position according to the planned trajectory.

6. The calibration method according to claim 2 or 3, characterized in that: The vehicle body coordinate system includes a rectangular coordinate system defined by SAE, a rectangular coordinate system defined by ISO, or a rectangular coordinate system defined based on IMU.

7. The calibration method according to any one of claims 1 to 3, characterized in that: The calibration object includes one or more parameters of a camera, radar, ECU or ADAS algorithm model; The driving data includes one or more of the following data: data obtained by the camera photographing the target object, data obtained by the radar measuring the target object, the wheel speed, yaw rate, and steering wheel angle of the vehicle, wherein the target object is set at a specified position.

8. A calibration device for an autonomous driving vehicle, characterized in that: It includes an acquisition module and a processing module, wherein: The acquisition module is configured to acquire first trajectory information, where the first trajectory information is acquired from a memory inside the vehicle or from an external device communicatively connected to the vehicle; The acquisition module is further used to obtain the location information of the vehicle; The processing module is configured to generate a planned trajectory based on the first trajectory information and the position information; The processing module is further configured to start collecting driving data when the vehicle automatically drives to a first position according to the planned trajectory, wherein the driving data is used to calibrate a calibration object possessed by the vehicle, and the first position corresponds to a preset position on the first trajectory indicated by the first trajectory information.

9. The calibration device according to claim 8, characterized in that: The first trajectory information is information in a vehicle coordinate system; The processing module is further configured to convert the first trajectory information into second trajectory information in a world coordinate system; The processing module is further configured to generate a planned trajectory according to the second trajectory information and the position information.

10. The calibration device according to claim 9, characterized in that: The acquisition module is further configured to acquire first coordinate information, where the first coordinate information indicates the coordinates of the preset position in the world coordinate system; The processing module is further configured to convert the first trajectory information into second trajectory information in the world coordinate system according to the first coordinate information.

11. The calibration device according to any one of claims 8 to 10, characterized in that: The first position corresponds to a starting point of the first trajectory.

12. The calibration device according to claim 11, characterized in that: The processing module is further configured to enable the vehicle to automatically travel from the position indicated by the position information to the first position according to the planned trajectory.

13. The calibration device according to claim 9 or 10, characterized in that: The vehicle body coordinate system includes a rectangular coordinate system defined by SAE, a rectangular coordinate system defined by ISO, or a rectangular coordinate system defined based on IMU.

14. The calibration device according to any one of claims 8 to 10, characterized in that: The calibration object includes one or more parameters of a camera, radar, ECU or ADAS algorithm model; The driving data includes one or more of the following data: data obtained by the camera photographing the target object, data obtained by the radar measuring the target object, the wheel speed, yaw rate, and steering wheel angle of the vehicle, wherein the target object is set at a specified position.

15. An electronic device, characterized in that: The device comprises a processor and an interface circuit, wherein the processor is coupled to a memory via the interface circuit, and the processor is configured to execute a program code in the memory, so that the processor executes the calibration method according to any one of claims 1 to 7.

16. A computer storage medium, characterized in that The method comprises computer instructions, which, when executed on an electronic device, enable the electronic device to execute the calibration method according to any one of claims 1 to 7.

17. A computer program product, characterized in that When the computer program product is run on a computer, the computer is enabled to execute the calibration method according to any one of claims 1 to 7.

Images