519 results about "Turning angle" patented technology

The invention discloses a tire longitudinal force and lateral force prediction method based on vehicle state parameter estimation, which adopts a seven-order spherical radius criterion to replace the original three-order spherical radial volume criterion on the basis of the traditional volume Kalman filter (CKF), and improves the estimation precision by optimizing sampling point distribution and weight configuration. And the stability of numerical calculation is ensured in combination with QR decomposition. A vehicle-mounted sensor is used for collecting real-time data such as a front wheel turning angle and longitudinal / lateral acceleration under a complex working condition, a time sequence feature set is built by combining longitudinal speed, lateral speed, a side slip angle and yaw velocity estimated by an algorithm, and meanwhile tire force calculated by a Dugoff tire model serves as target output. The TCN-GRU-based tire force prediction method is designed, the calculation complexity can be reduced while key time sequence information is kept, and the real-time prediction performance of the tire force is improved.

The invention relates to a navigation control method and device of agricultural machinery, electronic equipment, a medium and the agricultural machinery, and the method comprises the following steps: acquiring a positioning point coordinate, course information, real-time vehicle speed and yaw rate information of the agricultural machinery at the current moment, and calculating the navigation of the agricultural machinery according to the positioning point coordinate, course information, real-time vehicle speed and yaw rate information at the current moment; calculating transverse deviation, course deviation and estimated values of the front wheel turning angle between the agricultural machine and a preset target path point according to the geometrical relationship, calculating an expected value of the front wheel turning angle at the next moment of the current moment according to the transverse deviation, the course deviation and the estimated values of the front wheel turning angle, and calculating the expected value of the front wheel turning angle at the next moment according to the expected value of the front wheel turning angle at the next moment. The agricultural machine is controlled to advance. By means of the method, the expected value of the front wheel rotation angle at the next moment is optimized, so that accurate control over advancing of the agricultural machine is achieved, the path tracking accuracy of the agricultural machine is remarkably improved, deviation errors in the operation process can be effectively reduced, and it is ensured that the agricultural machine accurately travels according to the preset path.

The invention is suitable for the technical field of automobile chassis, and provides an angle module system and a modular extensible chassis, and the angle module system adopts an unequal-length double-wishbone suspension and has good geometric kinematics characteristics. And the offset distance of the main pin is reasonably controlled through the design of steering knuckle parts. By adopting the angle module bracket, the efficient integration of the driving unit and the frame structure is realized, the number of connecting points of the angle module system and the chassis is reduced, and the serialization, integration and modularization of the chassis system are facilitated. A distributed main pin steering gear is adopted, and the geometrical shape design of upper and lower control arms of the suspension is matched, so that wheels have a larger turning angle range, and the maneuverability is improved. In addition, the modular extensible chassis adopts modular design, and the number of shafts can be flexibly configured according to carrying requirements.

The invention provides a parking method and device and a vehicle, and can be applied to the field of intelligent driving. The method comprises the following steps: acquiring the position of a vehicle and the information of a target parking space; according to the position and the information of the target parking space, a parking path is planned, the parking path comprises a path for driving in a different-direction steering mode and a path for driving in a same-direction steering mode, and the direction of a front wheel turning angle of the vehicle is opposite to the direction of a rear wheel turning angle of the vehicle in the different-direction steering mode; the direction of a front wheel turning angle of the vehicle is the same as that of a rear wheel turning angle of the vehicle in the same-direction steering mode; and according to the first parking path, controlling the vehicle to park in the target parking space from the first position. The method can be applied to an electric automobile or an intelligent automobile, the parking efficiency of the automobile can be improved, and therefore the parking experience of a user can be improved.

The invention discloses an excavation roadway turning construction method and a roadway construction method. According to the method, the turning track is accurately controlled through geological parameter pre-research and surveying and setting-out, and the problems of relaxation and damage caused by track deviation and long surrounding rock exposure time of a traditional turning section are effectively solved in combination with pilot tunnel advanced excavation and dynamic collaborative supporting. Pilot tunnel advanced excavation reserves a space for subsequent expanded excavation, a cutting head of the integrated equipment can horizontally rotate to adapt to curve excavation, and supporting force is dynamically adjusted in cooperation with real-time scanning of surrounding rock deformation data, so that the surrounding rock exposure time in turning section construction is shortened to 5-8 minutes from 40-60 minutes of a traditional process, and the construction efficiency is improved. The wall caving and roof caving risks caused by long-time support-free exposure of the surrounding rock in the turning area are remarkably reduced, meanwhile, it is ensured that the turning radius and the turning angle are matched with the design height through a parameter correction program, and the accuracy and safety of turning section construction are improved.

The invention provides an automatic driving method and system and a readable storage medium, and the method comprises the steps: S1, obtaining point cloud data through a laser radar, and outputting the boundary information of an obstacle; s2, acquiring vehicle position information based on a Beidou positioning module; s3, the obstacle boundary information and the vehicle position information are input into a decision-making module, driving behaviors are determined through a preset state machine, and the driving behaviors comprise driving in a lane, lane-borrowing overtaking and decelerating for giving way; s4, track planning is carried out according to the driving behavior; s5, obtaining a track for control based on the smooth path and the planned speed; s6, generating a steering wheel turning angle by adopting an LQR algorithm based on a kinematic model on the basis of a track for control, and generating an acceleration compensation instruction by adopting a double-PID controller in which a position PID and a speed PID are connected in series; and S7, the vehicle executing mechanism controls the vehicle to run through the steering wheel rotation angle and the acceleration compensation instruction.

A vehicle control method for improving a driving stability of a vehicle includes: obtaining road information and determining a friction coefficient of road surface according to the road information; obtaining first vehicle parameters and a first yaw rate of the vehicle, the first vehicle parameters including a turning angle of steering wheel, and a longitudinal speed, and a lateral speed; determining a second yaw rate of the vehicle according to the first vehicle parameters, the first yaw rate, and the friction coefficient of road surface; determining a yaw moment of the vehicle according to a difference value between the first yaw rate and the second yaw rate; and distributing the yaw moment to a four-wheel driver, the four-wheel driver including four independent drivers for driving wheels. A computing device and a non-transitory storage medium are also provided.

The invention discloses a vehicle steering control method and device, computer equipment and a vehicle, and belongs to the field of vehicle control. The method comprises the steps that under the condition that front wheels of a vehicle steer, steering parameters of the vehicle are collected; determining a dynamic control parameter of the vehicle based on the steering parameter; solving a dynamic model of the vehicle based on the dynamic control parameters to obtain target rear wheel turning angles suitable for a high-speed working condition and a low-speed working condition respectively; setting a vehicle speed interval according to the target rear wheel rotation angle, and controlling rear wheel steering according to the interval of the current vehicle speed in the vehicle driving process. According to the method, dynamic response characteristics of the vehicle at different speeds are fused, physical quantities such as the dynamic yaw velocity and the change rate of the dynamic yaw velocity are adopted as control targets, and compared with a traditional static model, the method has higher responsiveness and adaptability, the vehicle state can be reflected more truly, fine control over the rear wheel steering angle is achieved, and the method is suitable for large-scale popularization and application. Therefore, the requirements of low-speed maneuverability and high-speed stability are met simultaneously.

The invention belongs to the technical field of hydraulic control, and particularly relates to a steering mechanism, a control method of the steering mechanism and an operation machine.The steering mechanism comprises an axle, a steering wheel and a hydraulic control system, and the hydraulic control system comprises a power-assisted steering oil cylinder used for driving the axle to execute steering operation; the oil supply path is used for supplying oil to the power-assisted steering oil cylinder; the electric control reversing valve is arranged on the oil supply way, and two working oil ports of the electric control reversing valve are communicated with a rod cavity and a rodless cavity of the power-assisted steering oil cylinder respectively; the control unit is in communication connection with the electric control reversing valve and is configured to determine the turning angle of an axle under the condition that it is determined that the driver does not place the two hands on a steering wheel; and the working position of the electric control reversing valve is switched according to the turning angle, so that the power-assisted steering oil cylinder drives the axle to return, and the steering wheel is driven to return. By the adoption of the steering mechanism, when the two hands of a driver leave the steering wheel, the power-assisted steering oil cylinder can be automatically controlled to drive the axle and the steering wheel to return.

The invention relates to the technical field of vehicle control, and discloses a method and device for vehicle linear tracking control and a vehicle. The vehicle linear tracking control method comprises the steps of obtaining first position information of a navigation receiver, a vehicle wheelbase and a first distance between the position of the navigation receiver and the center of a vehicle rear axle; determining a preview point on the target driving straight line according to the first position information of the navigation receiver and the current vehicle speed; based on a trigonometric function relationship, determining a target corner according to the first position information of the navigation receiver, the second position information of the preview point, the vehicle wheelbase and the first distance; and controlling the vehicle to run according to the target corner. According to the vehicle linear tracking control method provided by the invention, errors in linear tracking control can be reduced, and the control precision is improved.

The embodiment of the invention provides a vehicle steering control method and device, electronic equipment and a vehicle. The method comprises the steps that under the condition that the yaw velocity deviation of a vehicle is larger than a set threshold value, vehicle driving state parameters, the road curvature of a current lane where the vehicle is located, the distance between the vehicle and a boundary line of the current lane, the steering angle of a steering wheel and vehicle steering parameters are obtained; and determining whether to trigger a lane keeping assist system of the vehicle at a predicted time based on the vehicle driving state parameter, the road curvature, the spacing, the steering wheel angle, and the vehicle steering parameter. According to the method, the specific time when the lane keeping auxiliary system should be triggered can be more accurately judged, the problem that the normal driving operation of a driver is affected due to frequent false triggering of the lane keeping auxiliary system in the returning process after the driver actively steers is avoided, and the vehicle safety is improved.

The invention relates to a vehicle steering control method and device, vehicle-mounted equipment, a vehicle, a medium and a product. The method comprises the following steps: acquiring an ideal Ackerman corner of each wheel in a vehicle in a current driving state; according to the ideal Ackerman rotation angle of each wheel and the current driving state, estimating the side slip angle of each wheel to obtain an estimated side slip angle of each wheel; determining whether the vehicle is in a high-speed steering state according to the current driving state; determining a target steering angle according to whether the vehicle is in a high-speed steering state, the estimated slip angle of each wheel and the ideal Ackerman steering angle of each wheel; and controlling each wheel of the vehicle according to the target steering angle. By adopting the method, the deviation of the ideal Ackerman angle in the steering process can be compensated by estimating the slip angle, so that the handling stability and the steering precision of the vehicle can be improved, and the stability and the safety of the vehicle in the running process are further improved.

The invention discloses a distributed steering control method, and belongs to the technical field of vehicle steering. The control method comprises the following steps: acquiring real-time driving data of a vehicle, wherein the real-time driving data comprises a steering wheel angle, a vehicle speed, a road adhesion coefficient and a side slip angle; determining a target Ackerman rate according to the real-time driving data; and controlling the wheels of the vehicle according to the target Ackerman rate and the real-time driving data. According to the real-time driving data of the vehicle, the Ackerman rate is determined, the vehicle turning angle control value is determined according to the Ackerman rate determined in real time and the real-time driving data, and then vehicle wheels are controlled according to the vehicle turning angle control value. Namely, the Ackerman rate of the vehicle in the driving process can adapt to different real-time driving data of the vehicle, the real-time driving data of the vehicle is fully considered, the control stability of the vehicle in key scenes such as high speed, low attachment and low speed is effectively improved, the driving burden of a driver is relieved, and the risk that the vehicle is unstable or even out of control is reduced.

The invention belongs to the field of wind power equipment transportation, and provides a wind power large piece transportation path intelligent planning system and method based on deep learning, and the method comprises the steps: obtaining terrain DEM data in a wind power plant range, and converting the terrain DEM data into three-dimensional vector data and three-dimensional vertex coordinates; receiving the three-dimensional vertex coordinates, constructing a road network topological structure representation based on a homotopy theory, extracting microscopic local features and a macroscopic global structure of a road network through a multi-level graph neural network, and realizing dynamic representation and updating of the road network based on manifold learning; receiving the road network topological structure representation and the road network features, and generating a vehicle dynamics constraint condition and a road section geometric difficulty coefficient by comprehensively considering the maximum climbing angle, the maximum turning angle, the maximum speed and the braking distance of the vehicle; and receiving the road network dynamic representation, the vehicle dynamics constraint condition and the road section geometric difficulty coefficient, and generating an optimal transportation path with balanced safety, time efficiency and transportation cost by adopting a multi-target reinforcement learning algorithm.

An excavator includes a lower traveling body; an upper turning body turnably mounted to the lower traveling body; an acquisition device mounted to the upper turning body and configured to acquire information including a status around the excavator; and a control device configured to recognize a reference object that is in a stopped state or at a fixed position around the excavator based on the information acquired by the acquisition device, and to estimate a turning angle of the upper turning body based on a change in a position of the reference object as viewed from the upper turning body.

The invention discloses a steering fault-tolerant control strategy suitable for a three-axis modular distributed electric drive heavy-duty vehicle. Determining a six-wheel rotation angle of the health system according to the steering multi-model set, and establishing a model; the input quantity is the front wheel turning angle of the three shafts, and the vehicle yaw velocity is solved by combining the longitudinal velocity of the vehicle; parsing driver pedal input as a target longitudinal speed; setting total driving force and total yawing moment control quantity, and obtaining total driving force and total yawing moment by using a model predictive control algorithm; according to the relation between the longitudinal force and the slip rate and between the lateral force and the slip rate of the tire, the lateral force borne by the fault wheel is minimized, the rotating speed and the driving torque of the fault wheel are calculated, and a cost function is set with the tracking error of the total driving force and the total yawing torque and the attachment rate of the healthy wheel as soft constraints; the maximum torque and the minimum torque which can be output by the hub motor serve as hard constraints, and a multi-objective optimization problem is established and solved; and finally issuing the control quantity. According to the method, steering fault-tolerant control of the three-axle six-wheel vehicle is realized.

The invention belongs to the technical field of distributed electric drive modular transport vehicle planning and control, and particularly relates to a distributed electric drive modular transport vehicle obstacle avoidance planning control method and device. The specific process of the method comprises the steps that two front shafts and two rear shafts which are close to each other are equivalent to two equivalent shafts respectively, two e-SPMT units are used for equivalence, and a monorail dynamic model is established; determining a collision boundary and establishing a collision constraint condition design, establishing a cost function including a swept area, a distance to an obstacle and path smoothness, and optimizing the cost function to obtain an expected path meeting the collision constraint condition; on the basis of the expected path and kinematic constraints, an expected speed and a yaw velocity corresponding to each path point in the expected path are generated; taking the expected speed and the yaw velocity as state quantities, and generating a dynamics control quantity according to the monorail dynamics model; the dynamic control quantity is distributed to each wheel longitudinal force and turn angle.

The invention discloses a driver state monitoring method, system and device based on machine vision and a medium. The method comprises the steps that displacement time sequence data of a brake pedal, rotation angle time sequence data of a steering wheel and image time sequence data of a road in front of a vehicle are obtained; extracting emergency braking time sequence characteristics of a brake pedal according to the displacement time sequence data, extracting emergency steering time sequence characteristics of a steering wheel according to the turning angle time sequence data, and extracting direction time sequence characteristics of an obstacle in front of the vehicle according to the road image time sequence data; inputting the emergency braking time sequence characteristics, the emergency steering time sequence characteristics and the obstacle orientation time sequence characteristics into a pre-trained driver state recognition model to obtain a current driver state; and early warning the driver according to the current driver state. The method improves the accuracy and timeliness of driver state monitoring, also improves the driving safety, and can be applied to the technical field of vehicle monitoring.

The invention belongs to the field of vehicle trajectory tracking control, and discloses an intelligent vehicle trajectory tracking control method and system based on differential programming, and the method comprises the steps: constructing a vehicle dynamics model; a reference trajectory time-varying curvature is introduced, delay of a steering execution mechanism is expressed as pure delay plus a first-order inertia link, and construction of a road tracking model is completed; assuming that the system is in a steady state, calculating reference values of a state quantity and a control quantity; constructing an MPC optimization problem, converting the MPC optimization problem into a QP problem, and calculating to obtain an MPC loss value; constructing a differential programming training calculation network diagram; a hypercube is used for sampling the state quantity of a vehicle, the driving speed and the time-varying reference items of a road, and construction of a network training initial state data set is completed; carrying out MPC trajectory tracking task integration, and constructing a physical model in network training; using a full-link layer network, adding tire slip angle soft constraints, completing the construction of a strategy network, carrying out end-to-end network training, and completing the control of a turning angle instruction. According to the method, the MPC online solving optimization problem can be avoided.

The invention relates to the field of pipeline under-pressure plugging, in particular to an under-pressure plugging device, and a plugging head of the under-pressure plugging device comprises a connecting mechanism arranged at the moving end of a feeding mechanism; the oil cylinder is rotationally arranged at the bottom of the connecting mechanism, the maximum overturning angle of the oil cylinder is smaller than 90 degrees, and the oil cylinder is horizontal after being overturned by the maximum angle; the fixed connecting disc is arranged on the oil cylinder, and a telescopic rod of the oil cylinder penetrates through the fixed connecting disc; the movable connecting disc is arranged at the end part of a telescopic rod of the oil cylinder; the plugging rubber mat is arranged on the end face, facing the movable connecting disc, of the fixed connecting disc, and the outer diameter of the plugging rubber mat in the natural state is smaller than the inner diameter of the pipeline. According to the pipeline plugging device, due to the fact that the outer diameter of the plugging rubber mat in the natural state is smaller than the inner diameter of the pipeline, the plugging rubber mat can smoothly move in the pipeline without damaging the pipeline, after the plugging rubber mat is in place, the plugging rubber mat is extruded through contraction of the oil cylinder to complete effective plugging, and the plugging effect is better.

The vehicle collision avoidance support device executes the collision avoidance control when the collision avoidance control is not executed and the collision condition is satisfied when the prohibition condition that the collision angle is equal to or larger than the predetermined threshold value is satisfied even when the collision condition that the host vehicle may collide with the target object is satisfied. The vehicle collision avoidance support device sets a predetermined threshold value so that the predetermined threshold value becomes smaller when the turning angle is large than when the turning angle is small.

The intelligent rail vehicle hinge device system monitoring method comprises the following steps: step 1, carrying out data acquisition through a test; 2, preprocessing the data; and step 3, carrying out deep learning on the preprocessed data based on the adaptive residual capsule network to obtain parameters of a model used for monitoring, specifically, dividing the preprocessed data, then extracting prominent features in data signals by adopting adaptive residual, and finally outputting the prominent features through a capsule. Fourthly, the model with the determined parameters is installed on the intelligent rail vehicle for real-time monitoring. Real-time monitoring of the rotating angle of the intelligent rail vehicle and the pressure of the damping arm is achieved through the angle sensor and the pressure sensor of the hinge device, problems can be found in time, even part damage caused by long-term vibration is avoided, the safety of stable operation of the hinge device is improved, the deep learning algorithm is simple and practical, and the application range is wide. The method is suitable for engineering application.

The embodiment of the invention provides a wheel turning angle adjusting method of a vehicle, the vehicle and a storage medium, and relates to the technical field of vehicles. The method comprises the steps that in response to the condition that state information of a vehicle meets a preset condition, a rear wheel steering system auxiliary control function of the vehicle is started; when the auxiliary control function of the rear wheel steering system is in the starting state, the first weight of the rear wheel steering system, the second weight of the electronic stability control system and an operation strategy are determined based on the yaw velocity deviation of the vehicle; a rear wheel steering system and an electronic stability control system are operated according to the operation strategy, and in the operation process, the target rear wheel steering angle of the vehicle is determined based on the wheel slip rate and the first weight of the vehicle; a rear wheel steering angle of the vehicle is adjusted to the target rear wheel steering angle based on the execution constraint. The technical problems that in the prior art, braking intervention only depends on ESC, the yaw moment compensation capacity is limited, and energy loss is high are solved.

The invention belongs to the technical field of commercial vehicle automatic driving, and discloses a multi-axle commercial vehicle reconfigurable automatic driving trajectory tracking fault-tolerant motion control method, which specifically comprises the following steps: establishing a vehicle reconfigurable dynamic tracking error prediction model based on a small corner hypothesis and a vectorization modeling method; augmenting a state quantity for a delay phenomenon of a vehicle steering system; traversing different vehicle steering failure configurations offline to generate a steady state reference and a control reference; system feedback is obtained online in real time; an MPC problem with equality constraints is converted into a quadratic programming problem for solving and calculation simplification; performing matrix multiplication on the optimal control law obtained by looking up the table according to the time-varying parameters and state feedback to obtain a steering wheel angle control quantity; and sending the turning angle instruction to a steering wheel of the multi-axle vehicle. According to the invention, the compatibility and real-time performance of the automatic driving motion controller of the multi-axle commercial vehicle can be improved, and the precision of the trajectory tracking process can be improved.

The utility model provides a suspension structure and an all-terrain vehicle. The suspension structure comprises a first steering knuckle, a second steering knuckle, a first control arm and a second control arm. The first steering knuckle is connected with a steering wheel on one side of the frame, and a first limiting part is arranged on the first steering knuckle; the second steering knuckle is connected with a steering wheel on the other side of the frame, and a second limiting part is arranged on the second steering knuckle; the first control arm is connected with the frame and the first steering knuckle; and the second control arm is connected with the frame and the second steering knuckle. When the steering wheel steers to a certain turning angle relative to the frame, the first limiting part is in contact with the third limiting part or the second limiting part is in contact with the fourth limiting part, so that the maximum turning angle of left steering or right steering is limited, and the stability of a vehicle in the running process is guaranteed.

The invention provides a vehicle control method, electronic equipment and a storage medium. The method comprises the following steps: acquiring driving state parameters of a vehicle; determining a current road surface type according to the driving state parameters; determining a target value of a wheel turning angle according to the current road surface type and the driving state parameters; and controlling the vehicle according to the target value of the wheel turning angle. The wheel turning angle is controlled according to the current road surface type, so that the lateral control effect of the vehicle is more stable, and it can be guaranteed that the lateral control effect of the vehicle is better in any environment.

The invention belongs to the technical field of aircraft assembly, and discloses an aircraft front wheel turning angle monitoring device and method, and the device comprises a mechanical sensing module, a signal processing module and a signal receiving device. The mechanical sensing module is detachably mounted on a shock strut of a nose landing gear of an aircraft, and the rotary motion of the shock strut is converted into a linear displacement signal through a gear transmission mechanism in the mechanical sensing module; the signal processing module analyzes the displacement signal into a front wheel turning angle electric signal; and the signal receiving device receives and displays the angle value. The invention further discloses a corresponding monitoring method. The device adopts a modular and non-invasive design, solves the problems that the turning angle of the front wheel cannot be monitored in real time and the over-limit risk exists in the aircraft traction process, has the advantages of being convenient and fast to install, accurate in measurement and wide in applicability, and remarkably improves the safety and the working efficiency of flight guarantee.

The invention discloses a steering control method, device and system and a vehicle, relates to the technical field of vehicle control, and aims to realize small-radius steering of the vehicle. The method comprises the steps that after it is determined that the vehicle enters a low-speed steering scene according to the vehicle speed and the steering wheel rotating angle of the vehicle, at least one shaft of the vehicle is controlled to output first differential torque, an outer wheel of the at least one shaft outputs positive torque, and an inner wheel of the at least one shaft outputs negative torque according to the steering wheel rotating angle and steering wheel hand force of the vehicle; the difference between the negative torque and the positive torque is equal to the first differential torque. When the vehicle enters the low-speed steering scene, at least one shaft of the vehicle is automatically controlled to output the differential torque, small-radius steering and even in-situ turning of the vehicle can be achieved, and the turning angle of the vehicle is effectively reduced. In addition, the steering wheel angle and the steering wheel hand power are parameters related to the steering intention of the driver, the vehicle is controlled to achieve differential steering based on the parameters, the actual steering of the vehicle can meet the subjective requirement of the driver, and the steering experience of the driver is improved.

The invention relates to the field of vehicle parking, in particular to a parking-out method during tire steering limitation and a storage medium. The parking-out method during tire steering limitation comprises the steps that when a parking-out instruction is received, based on a planned parking path, a vehicle tire is controlled to steer towards a target turning angle, and after preset time, if the turning angle of the tire does not reach the target turning angle, based on the current turning angle of the tire, the distance between the vehicle and front and back obstacles and / or the target turning angle, the vehicle tire is controlled to steer towards the target turning angle. And controlling the vehicle to drive out. According to the parking-out method for the limited tire steering and the storage medium, the vehicle can be smoothly parked out of the parking space when the vehicle tire steering is limited.

The present invention discloses a method for calculating the rear wheel angle of an intelligent vehicle that takes driving style into account. The method comprises a driving information acquisition module, a driving style judgment module, a loss function calculation module, and a rear wheel angle calculation module. The driving information acquisition module is used to obtain vehicle driving state information and driver physiological signal information; the driving style judgment module is used to calculate the driver's driving style factor; the loss function calculation module is used to calculate the loss function of the neural network in the rear wheel angle calculation module; and the rear wheel angle calculation module is used to calculate the ratio of the rear wheel angle to the front wheel angle using a deep neural network.