Automatic driving vehicle control device and method based on safety officer training

Abstract

The invention belongs to the technical field of automatic driving vehicles, and particularly relates to an automatic driving vehicle control device and method based on safety officer training. The invention provides a training device based on a drive-by-wire vehicle, a low-torque motor, an integrated navigation system and an electronic map, and aims to solve the problems that existing automatic driving safety officer training depends on operation of a driving robot, the scene is single, and complex working conditions cannot be dynamically simulated. According to the technical scheme, the method comprises the steps that a low-torque motor simulates the holding operation of a driver, an INS / GPS integrated navigation system conducts real-time positioning compensation, a bus tool executes a drive-by-wire instruction, and a control system combines an electronic map and a training scheme to generate path planning. The device can simulate mileage of more than 1000 kilometers, complex weather and emergency scenes, and is used for training emergency response capability and vehicle control skills of safety officers.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle driving training, and more specifically to an automatic driving vehicle control device and method based on safety officer training. Background Art

[0002] At present, the training of autonomous driving safety officers mainly relies on installing a full set of driving robots and replaying the route through "driving memory", that is, simulating an autonomous driving vehicle. Then, in the program of the driving robot, the safety officer is trained by turning the steering wheel sharply on a certain section of the road. Robot training has problems such as high cost, limited venues, and difficulty in reproducing extreme scenes, and it is impossible to accurately quantify the safety officer's operating behavior. Although the use of traditional simulators can reduce costs, there are generally defects such as static scenes, poor real-time interaction, and lack of physical feedback, which makes the training effect disconnected from the actual driving scene. The shortcomings of the above existing technologies are specifically reflected in: (1) The simulation of the steering wheel holding state is not realistic and cannot meet the requirements of alarm threshold and driving intention recognition at the same time; (2) The path tracking accuracy is limited by a single navigation system and is easily affected by GPS signal occlusion; (3) The training plan lacks a dynamic adjustment mechanism, making it difficult to optimize the training content according to the performance of the safety officer; (4) The safety protection strategy is simple and does not achieve graded braking and risk adaptive control.

[0003] The root cause of the above problems lies in the lack of a closed-loop control architecture that coordinates multiple systems and in-depth modeling of vehicle dynamics in complex scenarios. In addition, traditional training methods do not fully utilize the flexibility of wire control technology, making it difficult to balance training efficiency and safety. Summary of the invention

[0004] An object of the present invention is to provide an autonomous driving vehicle control device and method based on safety officer training, which utilizes existing vehicles to build a low-cost training system and ensures precise path control.

[0005] In order to achieve these purposes and other advantages of the present invention, according to one aspect of the present invention, the present invention provides an automatic driving vehicle control device based on safety officer training, comprising: Autonomous driving vehicles, equipped with autopilot and drive-by-wire systems; A low-torque motor is installed on the steering wheel and is used to periodically output torque to simulate the driver's grip operation; INS / GPS combined navigation system, real-time output of vehicle position fusion data; Bus tool, which sends steering, throttle and brake commands to the wire control system based on the wire control protocol; Control system, including: The electronic site map system divides the training site roads into multiple links. Each link contains ID, longitude and latitude information, direction attributes and nodes, and establishes the road network topology relationship. Training program data for generating vehicle control commands; The control system controls the vehicle to travel along a predetermined path through a bus tool according to the site map data and the training program.

[0006] Preferably, the output cycle of the low-torque motor is greater than the reminder cycle of the vehicle steering wheel holding alarm, and the output torque is greater than the steering wheel holding sensing threshold, but less than the torque threshold for exiting the automatic driving function.

[0007] Preferably, the position data of the INS / GPS combined navigation system is matched with the Link in the site map, and dynamic compensation is performed by calculating the vertical distance between the vehicle position and the Link to ensure the path tracking accuracy.

[0008] Preferably, the vertical distance is calculated as follows: Convert the starting point, end point and vehicle position of the Link into a plane rectangular coordinate system; Calculate the vertical distance from the vehicle to the Link segment using the vector operation formula; When the vertical distance exceeds the threshold, a compensation amount is generated according to the deviation direction, and the vehicle direction is adjusted to return to the Link center line.

[0009] Preferably, the INS / GPS integrated navigation system includes an error correction module for: When GPS signals are available, the INS integral error is corrected by Kalman filtering to make the position error ≤ ±0.1 m; When the GPS signal is lost, it switches to INS standalone mode and suppresses the error through zero-speed correction to make the position error ≤±0.5 meters.

[0010] Preferably, the error correction module outputs position data at 0.01 second intervals in INS standalone mode and fuses it with GPS data after GPS recovery to avoid position jumps.

[0011] Preferably, the training program data includes: The preset training mileage is ≥ 1000 kilometers; Thresholds for the number of steering operations at different angles; Complex scenario simulation module, supporting severe weather, night driving and emergency traffic scenarios; Monitor the safety officer's response and vehicle status in real time, and adjust the training content dynamically.

[0012] Preferably, a safety strategy module is also included, for triggering a graded braking instruction according to the risk level when the vehicle is predicted to touch the boundary of the site.

[0013] Preferably, the security policy module: There are three levels of risk, corresponding to sound and light warning, progressive braking and emergency braking; Generates adaptive braking curve based on vehicle dynamics model, limiting lateral acceleration to ≤ 0.3g; Uses CAN bus and Ethernet redundant communication and triggers local autonomous braking when command is lost; Dynamically adjust the risk assessment threshold based on the safety officer’s historical response time.

[0014] The present invention also provides a control method for an automatic driving vehicle control device based on safety officer training, comprising the following steps: Digitize the training site roads into an electronic map containing links and topological relationships; Generate vehicle control parameters according to the training plan; Applying periodic torque to the steering wheel via a low torque motor; Acquire INS / GPS posture data in real time and match it with electronic maps; Send control-by-wire commands through the bus tool to control the vehicle to execute the training path.

[0015] The present invention includes at least the following beneficial effects: the present invention provides an automatic driving vehicle control device and method based on safety officer training, the device is directly connected to the bus tool through the wire control system, and no additional modification of the vehicle actuator is required; a low-torque motor is used to replace the manual grip of the steering wheel to avoid the triggering of the vehicle alarm function and reduce the cost of manual intervention; the electronic site map system abstracts the physical road into a Link topology structure to provide a digital basis for path planning; combined with the fusion positioning data of INS / GPS, the real-time matching of the vehicle position and the electronic map is achieved. The matching method combines the electronic map with the wire control protocol to achieve closed-loop control of path planning → positioning matching → command execution; the tedious operation of manually setting the path and manually intervening in the steering wheel is reduced; the low-torque motor parameters used are adapted to existing vehicles, avoiding physical modification of the steering wheel structure.

[0016] Other advantages, objectives and features of the present invention will be embodied in part through the following description, and in part will be understood by those skilled in the art through study and practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is a schematic diagram of the structure of the automatic driving vehicle control device based on safety officer training described in the present invention. DETAILED DESCRIPTION

[0018] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments so that those skilled in the art can implement the invention with reference to the description.

[0019] It should be understood that the terms such as “having”, “including” and “comprising” used herein do not exclude the existence or addition of one or more other elements or combinations thereof.

[0020] It should be noted that the experimental methods described in the following embodiments are conventional methods unless otherwise specified, and the reagents and materials can be obtained from commercial channels unless otherwise specified.

[0021] like Figure 1 As shown, the present invention provides an automatic driving vehicle control device based on safety officer training, comprising: Autonomous driving vehicles, equipped with autopilot and drive-by-wire systems; A low-torque motor is installed on the steering wheel and is used to periodically output torque to simulate the driver's grip operation; INS / GPS combined navigation system, real-time output of vehicle position fusion data; Bus tool, which sends steering, throttle and brake commands to the wire control system based on the wire control protocol; Control system, including: The electronic site map system divides the training site roads into multiple links. Each link contains ID, longitude and latitude information, direction attributes and nodes, and establishes the road network topology relationship. Training program data for generating vehicle control commands; The control system controls the vehicle to travel along a predetermined path through a bus tool according to the site map data and the training program.

[0022] In the above technical solution, the autonomous driving vehicle control device based on safety officer training includes: an autonomous driving vehicle, the autonomous driving vehicle is equipped with an automatic assisted navigation driving system and a wire control system; a low torque motor installed on the steering wheel of the autonomous driving vehicle, used to output low torque in a fixed period to simulate the operation of the driver holding the steering wheel tightly; an INS / GPS combined navigation system installed on the autonomous driving vehicle, used to output the INS and GPS position data fusion information of the vehicle in real time, and a bus tool, used to send steering, throttle and brake instructions to the wire control system according to the wire control protocol; and a control system, wherein the control system is provided with a site map electronic system, used to digitize the roads of the training site, divide them into multiple links, each link contains ID, latitude and longitude information, one-way / two-way direction and node Node, and establish the topological relationship of the road network; and training program data; the control system combines the data in the site map electronic system and the training program data to control the bus tool to operate the vehicle. The above device uses existing vehicles to build a low-cost training system and ensures precise path control. It directly connects with the bus tool through the wire control system, without the need for additional modification of the vehicle actuator; uses a low-torque motor to replace manual steering wheel control to avoid triggering the vehicle alarm function and reduce the cost of manual intervention; the electronic site map system abstracts the physical road into a Link topology structure, providing a digital foundation for path planning; combined with the fusion positioning data of INS / GPS, it realizes real-time matching of the vehicle position and the electronic map.

[0023] In another technical solution, the output cycle of the low-torque motor is greater than the reminder cycle of the vehicle's steering wheel holding alarm, and the output torque is greater than the steering wheel holding sensing threshold, but less than the torque threshold for exiting the autonomous driving function. The output cycle of the low-torque motor described in this technical solution is greater than the reminder cycle of the vehicle's "hold the steering wheel tight" alarm, and the output torque is greater than the vehicle's sensing torque, but less than the torque for exiting the NOA function. Prevent the motor from triggering vehicle safety alarms or causing the autonomous driving function to exit. Through the precise setting of the cycle and torque threshold, it simulates the tactile feedback of the driver's grip, and ensures that the vehicle maintains the autonomous driving state (such as the NOA function does not exit); prevents training from being frequently paused due to vehicle alarms or function interruptions.

[0024] In another technical solution, the position data of the INS / GPS integrated navigation system is matched with the Link in the site map, and dynamic compensation is performed by calculating the vertical distance between the vehicle position and the Link to ensure path tracking accuracy. In this technical solution, the position data fusion information output by the INS / GPS integrated navigation system is matched with the Link in the site map, the vertical distance between the GPS point and the Link is calculated, and compensation is performed based on the distance to ensure accurate control of the vehicle during training.

[0025] In another technical solution, the vertical distance is calculated as follows: Convert the starting point, end point and vehicle position of the Link into a plane rectangular coordinate system; Calculate the vertical distance from the vehicle to the Link segment using the vector operation formula; When the vertical distance exceeds the threshold, a compensation amount is generated according to the deviation direction, and the vehicle direction is adjusted to return to the Link center line.

[0026] In this technical solution, the vertical distance is calculated as follows: Convert the latitude and longitude coordinates of the start and end points of the Link into a plane rectangular coordinate system; The vehicle's GPS point is also converted into the same plane rectangular coordinate system; Calculate the vertical distance d from the vehicle GPS point to the Link segment using the formula: ; in, is the vector of Link, The vector that fuses the vehicle position data to the starting point of the Link; The compensation methods include: Set the vertical distance threshold d threshold ; When d>d thresholdd When the compensation mechanism is triggered; According to the vertical distance d and the current direction of movement of the vehicle, the compensation amount Δx is calculated: If the vehicle deviates from the left side of Link, the compensation amount is ; If the vehicle deviates from the right side of the Link, the compensation amount is Δx=k×d; where k is the compensation coefficient; the control system controls the bus tool to manipulate the vehicle and adjust the direction of the vehicle to return it to the center line of the Link. Prevent the vehicle from deviating from the predetermined route due to positioning error or control deviation. Quantify the degree of vehicle deviation through plane coordinate system conversion and vector operation (formula calculation of vertical distance); force the vehicle to return to the center line of the Link through dynamic compensation (such as Δx=k×d), and control the path tracking error to the centimeter level; use mathematical formulas to clarify the compensation logic for easy debugging and optimization.

[0027] In another technical solution, the INS / GPS integrated navigation system includes an error correction module for: When GPS signals are available, the INS integral error is corrected by Kalman filtering to make the position error ≤ ±0.1 m; When the GPS signal is lost, it switches to INS standalone mode and suppresses the error through zero-speed correction to make the position error ≤±0.5 meters.

[0028] In the technical solution, the INS / GPS integrated navigation system also includes an error correction module for dynamically adjusting the integral error of the INS according to the availability of the GPS signal, and providing continuous position data through the INS alone when the GPS signal is lost, so as to ensure the accurate positioning of the vehicle during the training process; The working process of the error correction module includes: When the GPS signal is available, the GPS position data is received every 0.1 seconds, and the Kalman filter algorithm is used to correct the integral error of the INS to ensure that the position error is within the range of ±0.1 meters; When the GPS signal is lost, it switches to INS standalone working mode, uses the INS accelerometer and gyroscope data to calculate the vehicle's position, speed and attitude through integration, and uses zero-speed correction technology to correct the INS error when the vehicle is stationary to ensure that the error does not exceed ±0.5 meters; Among them, the dynamic adjustment of the integral error of INS includes: When the GPS signal strength is lower than -130dBm, it is judged as GPS signal loss and automatically switches to INS standalone working mode; When the GPS signal is available, the error correction module corrects the integrated error of the INS every 1 second to ensure that the corrected position error is within the range of ±0.1 meters.

[0029] In another technical solution, the error correction module outputs position data at intervals of 0.01 seconds in INS standalone mode, and merges with GPS data after GPS recovery to avoid position jumps. In this technical solution, in INS standalone working mode, position data is output every 0.01 seconds to ensure data continuity and real-time performance; After the GPS signal is restored, the error correction module merges the INS position data with the GPS position data to ensure a smooth transition and avoid position jumps; During the period when the GPS signal is lost, the vertical distance between the vehicle and the Link is calculated in real time through the position data provided by the INS alone, combined with the Link information in the site map, and compensation is performed to ensure that the vehicle always stays on the planned route. Continuous high-precision positioning is achieved when the GPS signal is unstable or lost. When GPS is available, the position error is limited to ±0.1 meters through Kalman filtering; when GPS is lost, the error of INS working alone is ≤±0.5 meters, meeting the accuracy requirements of training scenarios; smooth transition through data fusion to avoid control command jitter caused by position jumps; ensure that training continues in GPS-denied environments such as tunnels and underground garages.

[0030] In another technical solution, the training program data includes: The preset training mileage is ≥ 1000 kilometers; Thresholds for the number of steering operations at different angles; Complex scenario simulation module, supporting severe weather, night driving and emergency traffic scenarios; Monitor the safety officer's response and vehicle status in real time, and adjust the training content dynamically.

[0031] In this technical solution, the training program data includes the following contents: Training mileage: more than 1,000 kilometers; Emergency turn training times: 80-90° turn 200 times, 60°-80° turn 100 times; After the vehicle is stable on a specific road section, a steering command is sent through the bus tool to complete the steering operation; The safety officer takes over the vehicle after the vehicle completes the steering operation and restarts the vehicle's autonomous driving function after 5 seconds of normal driving; During the training process, the vehicle status and the safety officer's response are monitored in real time, and the training plan is adjusted dynamically; Supports simulation of multiple complex scenarios, including severe weather scenarios, emergency traffic scenarios, and night driving scenarios; Record the safety officer's driving behavior in real time, generate training evaluation reports, and display them in real time on the vehicle display or mobile terminal; Monitor the vehicle's location and speed in real time and dynamically adjust safety strategies to ensure vehicle safety.

[0032] Scientifically designed training content covers a variety of driving scenarios, achieving quantitative indicators (mileage, number of turns) to ensure that safety officers are proficient in routine operations; improving the ability to deal with emergencies (such as tire slippage in rainy days and low visibility at night) through complex scenario simulations; using real-time monitoring and dynamic adjustment functions to optimize training efficiency and avoid repeated or ineffective training.

[0033] In another technical solution, a safety strategy module is further included, which is used to trigger a graded braking command according to the risk level when the vehicle is predicted to touch the boundary of the site. In this technical solution, the safety strategy module is used to send a wire-controlled chassis command to the bus tool to brake when the safety officer fails to take over the vehicle in time and the vehicle is at risk of touching the boundary of the site.

[0034] In another technical solution, the security policy module: There are three levels of risk, corresponding to sound and light warning, progressive braking and emergency braking; Generates adaptive braking curve based on vehicle dynamics model, limiting lateral acceleration to ≤ 0.3g; Uses CAN bus and Ethernet redundant communication and triggers local autonomous braking when command is lost; Dynamically adjust the risk assessment threshold based on the safety officer’s historical response time.

[0035] In this technical solution, the security policy module specifically includes: Risk level classification: Level 1 risk: The predicted distance between the vehicle and the site boundary is 2-5 meters, and the speed is higher than 30 km / h, triggering an audible and visual warning and prompting the safety officer to take over; Level 2 risk: The predicted distance between the vehicle and the site boundary is 1-2 meters, or the speed is higher than 50 km / h, triggering progressive braking, with the braking force increasing by 0.5g / s; Level 3 risk: The predicted distance between the vehicle and the site boundary is less than 1 meter, or the speed is higher than 70 km / h, triggering emergency braking, and the braking force instantly reaches 1.2g; Dynamic trajectory prediction: Based on the vehicle's real-time position, posture and kinematic model, the trajectory within the next 3 seconds is calculated, and combined with the boundary information in the site electronic map, the risk level is determined in real time; Adaptive braking curve generation: According to the vehicle mass, tire friction coefficient and current speed in the control system, the optimal braking curve is calculated in real time through the vehicle dynamics model to ensure vehicle stability during braking and the lateral acceleration does not exceed 0.3g; If the vehicle is in a curve, an additional steering compensation command is introduced to adjust the front wheel steering angle by ±2° to prevent skidding caused by braking; Redundant communication and fault-tolerant computing: Main communication channel: Send brake-by-wire commands via the CAN bus, with a response delay of less than 50ms; Backup channel: When CAN bus communication fails, it switches to the redundant communication protocol based on Ethernet to ensure the reliability of command transmission; Local actuator autonomous judgment: If the bus command is lost, the braking system will autonomously trigger emergency braking based on local inertial navigation data, and the braking force is fixed at 0.8g; Safety officer behavior prediction and threshold dynamic adjustment: Analyze the historical response time of security officers and dynamically adjust the risk trigger threshold: If the safety officer's recent reaction time is shortened by 20%, the first-level risk assessment distance will be relaxed to 3 meters; If the reaction time is extended by 30%, the secondary risk determination distance is tightened to 1.5 meters; The training data includes the safety officer’s eye tracking and hand motion sensor data to improve prediction accuracy.

[0036] The above safety strategy module enables rapid response in emergency situations to avoid vehicle loss of control or collision. Through graded safety intervention: Level 1 risk (sound and light warning) gives priority to prompting the safety officer to take over, leaving room for manual handling; Level 2 risk (progressive braking) balances braking efficiency and comfort through 0.5g / s incremental braking force; Level 3 risk (1.2g emergency braking) minimizes the risk of collision. Limiting lateral acceleration to ≤0.3g prevents vehicle skidding caused by braking; steering compensation (±2° front wheel adjustment) is used to offset the centrifugal force effect during cornering braking; redundant communication and local autonomous braking ensure that command transmission is foolproof.

[0037] The present invention also provides a control method for an automatic driving vehicle control device based on safety officer training, comprising the following steps: Digitize the training site roads into an electronic map containing links and topological relationships; Generate vehicle control parameters according to the training plan; Applying periodic torque to the steering wheel via a low torque motor; Acquire INS / GPS posture data in real time and match it with electronic maps; Send control-by-wire commands through the bus tool to control the vehicle to execute the training path.

[0038] In this technical solution, the training method specifically includes the following steps: The roads of the training site are digitized to generate electronic map data containing multiple links. Each link records the ID, longitude and latitude information, one-way / two-way attributes and associated nodes, and establishes the road network topology relationship; Generate vehicle control parameters according to a preset training program, wherein the control parameters include steering angle, throttle opening and braking force; apply periodic torque to the steering wheel of the autonomous driving vehicle through a low-torque motor, wherein the torque value is set to a value below a threshold value for triggering steering wheel grip detection; Obtain vehicle posture fusion data output by INS / GPS integrated navigation system in real time; Based on the electronic map topological relationship and real-time posture data, steering, throttle and brake instructions are sent to the vehicle's wire control system through a bus tool according to the wire control protocol, so that the vehicle executes the training plan along a predetermined path.

[0039] This achieves a systematic implementation of the training process and reduces hardware dependence. By combining the electronic map with the wire control protocol, a closed-loop control of path planning → positioning matching → command execution is achieved; the tedious operations of manually setting the path and manually intervening the steering wheel are reduced; the parameters of the low-torque motor are adapted to existing vehicles to avoid physical modifications to the steering wheel structure.

[0040] In another technical solution, the low-torque motor further includes a dynamic torque adjustment module for dynamically adjusting the output torque and cycle according to the real-time state of the vehicle, including the following steps: 1. Obtain real-time vehicle motion parameters: collect vehicle speed v and steering wheel angle θ through the CAN bus; 2. Calculate the dynamic torque coefficient: Basic torque T base = Vehicle grip sensing threshold × 1.2; Speed ​​correction factor α = 1 + (v / 100 km / h) × 0.5, limit α ∈ [1, 2]; Steering angle correction factor β = 1 + |θ| / 180°×0.8, limit β∈ [1,1.8]; Actual output torque T = T base ×α×β; 3. Adjust the output cycle: When v>60 km / h, the period is adjusted to 1.5 times the alarm period; When θ>45°, the period is shortened to 0.7 times the alarm period; 4. Drive the low torque motor through the motor controller and output according to the adjusted torque T and cycle.

[0041] The above solves the technical problem that fixed torque output cannot adapt to the change of steering wheel resistance under different driving conditions (such as high speed and sharp turn), causing false alarm or interference with the execution of wire control command. The torque is calculated in real time based on vehicle speed and steering angle. The torque is increased at high speed to prevent false alarm (α factor), and the torque is increased during sharp turn to simulate the driver's strong grip (β factor); for example: if v = 80 km / h, θ = 90°, then T = T base × 1.4 × 1.4=1.96 T base, ensuring that the torque always covers the resistance change. In addition, by extending the output cycle at high speed, the interference with the wire control steering is reduced; the cycle is shortened during sharp turns to enhance the authenticity of the grip simulation. The above device increases the torque to 1.5 T in a 100 km / h straight-line driving scenario. base , the alarm trigger rate dropped by 90%; in the 60° turning scenario, the cycle was shortened to 0.7 times, and the steering wheel control error was reduced from ±3° to ±0.5°.

[0042] In another technical solution, the dynamic torque adjustment module further includes a steering wheel torque sensor and a closed-loop control module, wherein: The steering wheel torque sensor is installed on the steering column of the steering wheel to detect the actual torque T applied by the driver's hand in real time. real ; The closed-loop control module adjusts the output torque by the following steps: 1. Calculate the target torque T target The actual torque T real The difference ΔT = |T target -T real |; 2. If ΔT>0.2 N•m, the motor output torque is adjusted according to the proportional-integral (PI) algorithm: Proportional term: P = Kp × ΔT, where Kp=0.8; Integral term: I = Σ(Ki × ΔT × Δt), where Ki=0.05 and Δt is the control period (0.1 seconds); Correction torque T adjust = T target + (P + I); 3. Drive the low torque motor output T through the motor controller adjust .

[0043] The above solves the problem that the open-loop control of the dynamic torque adjustment module cannot respond to the actual resistance change of the steering wheel in real time, resulting in the accumulation of torque output errors (such as when the friction resistance suddenly changes, T real Deviation from T target ). The torque error ΔT is controlled within ±0.1 N•m by monitoring the actual torque in real time through the torque sensor and dynamically correcting the output with the PI algorithm. For example, if the friction resistance of the steering wheel increases by 20% due to temperature rise, the system automatically increases the output torque compensation to avoid triggering the alarm. In bumpy roads or emergency steering scenarios, the interference of external vibration on torque output is suppressed, and the simulation stability of steering wheel holding is improved by 40%.

[0044] Example: Emergency steering and braking coordination training in heavy rain Scene parameter settings Road environment: The closed test site simulates a two-way two-lane road, including a left-turn curve with a radius of 50 meters; Road adhesion coefficient μ = 0.3 (wet and slippery state); Environmental simulation: heavy rain (visibility ≤ 50 meters), night lighting (only low beam on); Training objectives: Assess the safety officer's emergency takeover capabilities in extreme weather conditions; Verify the vehicle's lateral control accuracy (deviation from the centerline is required to be ≤±0.3 meters); Test the graded braking response of the safety strategy module; System Configuration: Vehicles: Production models equipped with NOA system, the wire control system supports 100Hz command update; Low torque motor: output cycle 1.2 seconds, torque 0.8N・m; Integrated navigation: INS update rate 100Hz, GPS update rate 10Hz; System response process Initial stage: The control system loads the electronic map and divides the curve into three Link segments (Link1-Link3); The low-torque motor starts to output periodically, simulating the driver's normal grip state; Initialize the integrated navigation system and correct the initial INS error through GPS signals; Training trigger: The vehicle enters Link 1 (straight section) at a speed of 40km / h, and the system calculates the distance between the vehicle and the curb in real time (required to maintain 40-60cm); When driving to the entrance of the curve (30 meters from the intersection), the control system sends a command through the bus tool: Steering angular speed 360° / s; The throttle maintains its current opening, ready to respond to acceleration requirements after turning; Emergency scenario simulation: After the vehicle enters the curve, the system simulates a stationary vehicle ahead (20 meters away); The integrated navigation system detects a short-term loss of GPS signal (simulated by heavy rain) and switches to INS standalone mode: The zero-speed correction module suppresses errors through wheel speed sensor signals (position error is controlled within 0.3 meters); The vertical distance compensation algorithm continuously calculates the deviation of the vehicle from the Link centerline; Security policy activation: The predicted time to collision (TTC) is calculated to be 1.8 seconds (triggering level 2 risk): Sound and light alarm is activated (buzzer + warning light); Progressive braking begins, and deceleration increases linearly to -0.2g; The safety officer did not take over in time, and the TTC dropped to 1.2 seconds (triggering level 3 risk): Emergency brake activated, maximum deceleration - 0.5g (lateral acceleration 0.28g, meeting ≤0.3g requirement); The system sends braking commands via CAN bus + Ethernet dual redundant channels; Takeover and recovery: After the safety officer takes over manually, the system records the takeover time (0.6 seconds) and the lateral offset of the vehicle (0.25 meters); After the vehicle has been running steadily for 5 seconds, the control system automatically restores the NOA function; Training effectiveness evaluation Quantitative indicators: Path tracking accuracy: maximum lateral deviation 0.28 m (meets ≤0.3 m requirement); Braking response time: 0.8 seconds from risk identification to full braking; Safety officer takeover efficiency: average response time 0.6 seconds (better than the industry benchmark of 0.8 seconds); System Optimization: Based on the training data, the TTC threshold for subsequent cornering training is dynamically adjusted (from 1.8 seconds to 1.5 seconds); Optimize the integrated navigation fusion algorithm to reduce the position jump error after GPS recovery from 0.15 meters to 0.1 meters; Scene extension: Subsequently, complex scenarios such as oncoming vehicles suddenly changing lanes and pedestrians crossing the road can be superimposed; Add night-time high beam switching training to assess safety officers’ visual adaptability.

[0045] Although the embodiments of the present invention have been disclosed as above, they are not limited to the applications listed in the specification and the implementation modes, and they can be fully applied to various fields suitable for the present invention. For those familiar with the art, additional modifications can be easily implemented. Therefore, without departing from the general concept defined by the claims and the scope of equivalents, the present invention is not limited to the specific details and the illustrations shown and described herein.

Claims

1. An automatic driving vehicle control device based on safety officer training, characterized in that: include: Autonomous driving vehicles, equipped with autopilot and drive-by-wire systems; A low-torque motor is installed on the steering wheel and is used to periodically output torque to simulate the driver's grip operation; INS / GPS combined navigation system, real-time output of vehicle position fusion data; Bus tool, which sends steering, throttle and brake commands to the wire control system based on the wire control protocol; Control system, including: The electronic site map system divides the training site roads into multiple links. Each link contains ID, longitude and latitude information, direction attributes and nodes, and establishes the road network topology relationship. Training program data for generating vehicle control commands; The control system controls the vehicle to travel along a predetermined path through a bus tool according to the site map data and the training program.

2. The automatic driving vehicle control device based on safety officer training according to claim 1, characterized in that: The output cycle of the low-torque motor is greater than the reminder cycle of the vehicle steering wheel holding alarm, and the output torque is greater than the steering wheel holding sensing threshold, but less than the torque threshold for exiting the automatic driving function.

3. The automatic driving vehicle control device based on safety officer training according to claim 1, characterized in that: The position data of the INS / GPS integrated navigation system is matched with the Link in the site map, and dynamic compensation is performed by calculating the vertical distance between the vehicle position and the Link to ensure the path tracking accuracy.

4. The automatic driving vehicle control device based on safety officer training according to claim 3 is characterized in that: The vertical distance is calculated as follows: Convert the starting point, end point and vehicle position of the Link into a plane rectangular coordinate system; Calculate the vertical distance from the vehicle to the Link segment using the vector operation formula; When the vertical distance exceeds the threshold, a compensation amount is generated according to the deviation direction, and the vehicle direction is adjusted to return to the Link center line.

5. The automatic driving vehicle control device based on safety officer training according to claim 3, characterized in that: The INS / GPS integrated navigation system includes an error correction module for: When GPS signals are available, the INS integral error is corrected by Kalman filtering to make the position error ≤ ±0.1 m; When the GPS signal is lost, it switches to INS standalone mode and suppresses the error through zero-speed correction to make the position error ≤±0.5 meters.

6. The automatic driving vehicle control device based on safety officer training according to claim 5, characterized in that: The error correction module outputs position data at 0.01 second intervals in INS standalone mode and merges with GPS data after GPS recovery to avoid position jumps.

7. The automatic driving vehicle control device based on safety officer training according to claim 1, characterized in that: The training program data includes: The preset training mileage is ≥ 1000 kilometers; Thresholds for the number of steering operations at different angles; Complex scenario simulation module, supporting severe weather, night driving and emergency traffic scenarios; Monitor the safety officer's response and vehicle status in real time, and adjust the training content dynamically.

8. The automatic driving vehicle control device based on safety officer training according to claim 1, characterized in that: It also includes a safety strategy module for triggering graded braking instructions based on the risk level when the vehicle is predicted to touch the boundary of the site.

9. The automatic driving vehicle control device based on safety officer training according to claim 8, characterized in that: The security policy module: There are three levels of risk, corresponding to sound and light warning, progressive braking and emergency braking; Generates adaptive braking curve based on vehicle dynamics model, limiting lateral acceleration to ≤ 0.3g; Uses CAN bus and Ethernet redundant communication and triggers local autonomous braking when command is lost; Dynamically adjust the risk assessment threshold based on the safety officer’s historical response time.

10. A control method for an automatic driving vehicle control device based on safety officer training according to any one of claims 1 to 9, characterized in that: The following steps are involved: Digitize the training site roads into an electronic map containing links and topological relationships; Generate vehicle control parameters according to the training plan; Applying periodic torque to the steering wheel via a low torque motor; Acquire INS / GPS posture data in real time and match it with electronic maps; Send control-by-wire commands through the bus tool to control the vehicle to execute the training path.

Images