Motor controller intelligent control system based on vehicle behavior data

Abstract

The invention discloses a motor control machine intelligent control system based on vehicle behavior data, and relates to the technical field of motor automation control, and the system comprises a data collection module which is used for collecting vehicle bottom ECU and vehicle-mounted gateway cooperation; the weather adaptation model construction module is used for evaluating the vehicle performance change scores of the driver vehicle under different weather conditions, establishing a driver performance evaluation strategy, evaluating the proficiency of the driver under different weather conditions according to the vehicle performance change, and outputting the driver credibility; and the self-adaptive parameter adjusting module is used for constructing a self-adaptive motor control model, performing weight distribution on control input according to the driver trust degree, and outputting control parameters. The problem of motor control errors caused by personal habits of a driver under different weather conditions is solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of motor automation control, in particular to an intelligent control system of a motor control machine based on vehicle behavior data. BACKGROUND

[0002] The traditional motor control method usually designs a set of globally consistent weights or gains in advance, which cannot dynamically adjust to the driving style, experience level and physiological- psychological state of the driver, such as fatigue and attention fluctuation, during driving. This "one-size-fits-all" control strategy is difficult to meet the precise control needs of experienced drivers in dynamic scenarios, and it cannot intervene in time when the driver's state is not good, resulting in safety hazards.

[0003] Although complex control algorithms perform well in simulation and small-scale testing, their high computational load and dependence on model accuracy make it difficult to meet the real-time control requirements of milliseconds on resource-constrained vehicle ECU / MCU. To reduce computational overhead, many solutions simplify the algorithm or reduce the prediction time domain, thereby sacrificing control accuracy and robustness, making it difficult to promote and apply on actual roads; With the rise of the concept of "human-machine shared control", how to dynamically allocate control rights between the driver and the system, both to ensure safety and not to deprive the driver of the initiative, has become a problem that needs to be solved. Existing researches are mostly based on confidence or simple weighting theoretical models, lacking comprehensive consideration of the real-time state, preferences and historical performance of the driver, and lacking a unified interface and process to closely integrate trust, weather perception and control strategy.

[0004] Different drivers have different proficiency and familiarity with different weather, and the driver may be more familiar with snow road sections and less proficient in driving in rainy weather, so different responses are made according to different weather types and weather conditions; especially in emergency situations, how to quickly and accurately switch control rights to ensure driving safety still needs further exploration.

[0005] Therefore, the present application provides a tea fermentation degree determination method and system based on image recognition. SUMMARY

[0006] The purpose of the present application is to provide an intelligent control system of a motor control machine based on vehicle behavior data to solve the problems in the background art.

[0007] To achieve the above purpose, the present application provides the following technical solution: an intelligent control system of a motor control machine based on vehicle behavior data, comprising: A data acquisition module is used to acquire the cooperation of the vehicle bottom ECU and the vehicle gateway. The weather adaptation model construction module is used for evaluating vehicle performance change scores of the driver's vehicle under different weather conditions, and establishing a driver performance evaluation strategy, according to which the proficiency of the driver under different weather conditions is evaluated, and a driver trust degree is output. The adaptive parameter adjustment module is used for constructing an adaptive motor control model, and performing weight distribution on control input according to the driver trust degree, and outputting a control parameter.

[0008] The data acquisition module comprises environment data, vehicle motion data and driver state data; the environment data comprises camera images, millimeter wave radar point clouds and laser radar point clouds; the vehicle motion data comprises vehicle speed, acceleration, lateral displacement, wheel speed and steering angle; the driver state data comprises eye movement tracking, facial expression and heart rate belt; all data are aligned by time stamp, and noise is eliminated by Kalman filtering.

[0009] The weather adaptation model construction module comprises a performance index evaluation unit, a proficiency evaluation unit and a driver trust degree unit; the performance index evaluation unit is used for obtaining a vehicle performance change score according to the absolute value of the difference between the weighted score after normalization of vehicle trajectory error, speed deviation, slip rate, road friction and smoothness and 1, wherein the performance index weight is updated based on a weather-weight mapping model, and specifically, a weather perception feature vector E is constructed, historical operation data are searched based on a small full connection neural network, the performance index weight combination that maximizes the vehicle performance change score is taken as a label, the unnormalized performance index weight sequence vector is outputted by taking the minimum MSE between the regression output and the label as an objective, and the final performance index weight is obtained by Softmax.

[0010] The performance index evaluation unit further comprises, after each evaluation window ends, calculating a current window vehicle performance change score Cvp, taking a target performance score as Pcvp, and obtaining a performance index error When When the preset performance index error threshold is exceeded, the weather-weight mapping model is updated by gradient Wherein The learning rate is represented by The performance index weight sequence of the kth iteration is set to When When the change threshold is less than the set change threshold, the iteration is stopped.

[0011] The further improvement of the application lies in that the proficiency evaluation unit is equipped with a driver performance evaluation strategy, specifically comprising: creating a weather type vector W, constructing a long-term proficiency model of the driver under each weather condition based on the vehicle performance change score, which is expressed as , represents the proficiency of the driver i under the weather type w, and the initial proficiency of the driver under each weather type is preset , represents the vehicle performance change score of this time.

[0012] The further improvement of the application lies in that the driver trust degree unit is used to judge the driver trust degree according to the current state and historical state of the driver, specifically comprising: obtaining the historical state score average of the driver from the historical driver state data of the current weather type as the historical state baseline dsh of the driver, and calculating the current state score dsc of the driver at the time interval t within the past time window T in the same way; calculating the difference between the current state score of the driver and the historical state baseline as the state baseline correction factor Δds, and then obtaining the driver trust degree under the current weather type, which is expressed as .

[0013] The further improvement of the application lies in that the adaptive motor control model specifically comprises: Step one, after standardizing the weather perception feature vector E to [0, 1] and weighted fusion, the weather influence factor wif is obtained as the weather influence factor; and the control increment of the last control cycle is extracted ; Step two, the driver trust degree under the current weather type, the weather influence factor, the vehicle performance change score and are taken as the state input of the adaptive motor control model; Step three, the negative value of the weighted fusion of the absolute value of the state input is taken as the reward function, and the adaptive motor control model action parameter is outputted; Step four, a cost function is constructed in combination with the output of step three; Step five, the OSQP is adopted to solve the cost function, and the control instruction is outputted.

[0014] The further improvement of the application lies in that the cost function is expressed as: ; Wherein, N represents the prediction time domain length, represents the jth step output predicted at time , and represents the target output of the jth step, and Q and R represent the weight matrixes determined through the driver-weight adaptation strategy.

[0015] The further improvement of the present application is that the driver-weight adaptation strategy specifically comprises determining a weight matrix by introducing a current weather type driver trust degree and a weather influence factor, and the calculation formula is: ; ; Wherein, represents a baseline weight matrix, and represents a default punishment intensity in a normal weather + full trust state.

[0016] On the other hand, the present application provides an intelligent control method of motor control machine based on vehicle behavior data, comprising the following steps: S1, collecting environmental data, vehicle motion data and driver state data in the driving process of the vehicle; S2, evaluating the vehicle performance change score of the driver vehicle under different weather conditions, and establishing a driver performance evaluation strategy, according to the vehicle performance change, the proficiency of the driver under different weather conditions is evaluated, and the driver trust degree is output; S3, constructing an adaptive motor control model, and distributing weights to the control input according to the driver trust degree, and outputting the control parameters.

[0017] Compared with the prior art, the present application has the following advantages: 1. The present application firstly corrects the control strategy in real time by introducing the driver trust degree C, can dynamically match the control strength according to the proficiency and current state of different drivers, improves the human-machine cooperation efficiency, and reduces the conflict of human intervention; 2. Through the weather-weight mapping model and the reinforcement learning strategy, various working conditions such as rain, snow and dryness are automatically adapted, without the need to redesign the algorithm for each scene, greatly simplifying the engineering deployment and subsequent maintenance; 3. When the driver state is not good or the weather is bad, the tracking error punishment is automatically enlarged and the smoothing constraint is relaxed, so that the system quickly and decisively takes over or corrects the deviation, and the risk of side slip, loss of control and collision is significantly reduced. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a kind of intelligent control system framework based on vehicle behavior data of motor control machine of the present application; Figure 2 is a kind of intelligent control system adaptive motor control model construction flow chart based on vehicle behavior data of motor control machine of the present application; Figure 3 is a kind of intelligent control method flow chart based on vehicle behavior data of motor control machine of the present application. DETAILED DESCRIPTION

[0019] The technical scheme of the present application will be described in detail below with reference to the drawings and specific embodiments. It should be understood that the embodiments of the present application and the specific features in the embodiments are detailed descriptions of the technical scheme of the present application, and are not limitations of the technical scheme of the present application. In the case of no conflict, the technical features in the embodiments of the present application and the embodiments can be combined with each other.

[0020] The term "and / or", only describes the association relationship of the associated objects, which means that there can be three kinds of relationships, for example, A and / or B, which can represent the three cases of A alone, A and B together, and B alone.

[0021] Embodiment 1 Figure 1 A framework diagram of an intelligent control system of a motor control machine based on vehicle behavior data is disclosed in the present embodiment, which comprises: A data acquisition module for acquiring vehicle bottom ECU and vehicle gateway cooperation; A weather adaptation model construction module for evaluating the vehicle performance change score of the driver's vehicle under different weather conditions, and establishing a driver performance evaluation strategy, according to the driver's proficiency under different weather conditions, and outputting the driver's trust degree; An adaptive parameter adjustment module for constructing an adaptive motor control model, and distributing weights to the control input according to the driver's trust degree, and outputting the control parameters.

[0022] The data acquisition module includes environmental data, vehicle motion data and driver state data; the environmental data includes camera image, millimeter wave radar point cloud and laser radar point cloud; the vehicle motion data includes vehicle speed, acceleration, lateral displacement, wheel speed and steering angle; the driver state data includes eye tracking, facial expression and heart rate band; all data are aligned by time stamp, and noise is eliminated by Kalman filtering.

[0023] The weather adaptation model construction module includes a performance index evaluation unit, a proficiency evaluation unit and a driver trust degree unit; the performance index evaluation unit is used to obtain the vehicle performance change score according to the absolute value of the difference between the weighted score after normalization of the vehicle trajectory error, the speed deviation, the slip rate, the road friction and the smoothness and 1, wherein the performance index weight is updated based on the weather-weight mapping model, and the specific performance is: A weather perception feature vector E is constructed, wherein, represents the normalized rainfall intensity, represents the normalized snow depth, represents the real-time friction coefficient, represents the visibility, represents the normalized road temperature; Small full connection neural network For historical running data, search the performance index weight combination that makes the vehicle performance change score maximum as the label, and minimize the MSE between the regression output and the label as the goal, the objective function is expressed as Wherein, Indicates the ideal weight vector given to the typical rain / snow working condition in simulation or road test; the output is the performance index weight sequence vector without normalization, and the final performance index weight is obtained by Softmax.

[0024] After each evaluation window ends, the current window vehicle performance change score Cvp is calculated, the target performance score is Pcvp, and the performance index error is obtained When When the performance index error exceeds the preset performance index error threshold, the weather-weight mapping model is updated by gradient Wherein Indicates the learning rate, It can be estimated by finite difference: fine-tune each performance index weight by a small step, and observe the performance change, The performance index weight sequence of the kth iteration, for each performance index weight, is set to When When the change threshold is less than the set change threshold, stop iteration.

[0025] The embodiment dynamically adjusts the weights of key indicators such as "road surface temperature", "road friction" and "visibility" for different working conditions such as rain and snow, so that the system pays attention to the risk factors that are most likely to cause accidents at all times, and significantly reduces the probability of skidding, losing control or collision.

[0026] The proficiency evaluation unit carries a driver performance evaluation strategy, specifically including: creating a weather type vector W, based on the vehicle performance change score, constructing a long-term proficiency model of the driver under each weather condition, which is expressed as, for the kth iteration , Indicates the proficiency of driver i under weather type w, and the initial proficiency of the driver under each weather type is preset According to the mean value of the driver proficiency in the database, the real-time update is Indicates the performance score this time.

[0027] The driver trust degree unit is used for judging the driver trust degree according to the current state and the historical state of the driver; specifically comprising: obtaining the historical state score mean of the driver according to the historical driver state data of the current weather type as the historical state baseline dsh of the driver, and the historical state of the driver is obtained by weighted fusion of the eye movement tracking index, the facial expression index and the heart rate zone index; the eye movement tracking index comprises the eyelid closing proportion Iprec(t)=closed eye frame number(t) / total frame number(t), the higher the value is, the more serious the fatigue is, and the gaze stability , wherein, represents the standard deviation of the line of sight position in the short window, the smaller the value is, the more stable the gaze is, and the eye movement tracking index is obtained by weighted summation of the eyelid closing proportion and the gaze stability; the pre-trained facial emotion recognition network (such as micro-expression classification based on ResNet) is used to output the current “expression stress degree ; the heart rate zone index is expressed by the heart rate variability (HRV) short-time index as , and the smaller the value of SDNN is, the greater the stress or fatigue is.

[0028] The driver current state score dsc of the time interval t in the past time window T is calculated in the same way; the difference between the driver current state score and the historical state baseline is calculated as the state baseline correction factor Δds, if the value is negative, it means that the current state is poor; if the value is positive, it means that the state is rising. Let the trust degree float up and down on the baseline, then the driver trust degree of the current weather type is obtained, which is expressed as When the current state is lower than the historical baseline (Δds<0), the trust degree is reduced in proportion; if Δds≥0, no negative reduction is made, and the trust degree is maintained or slightly improved, Embodiment 2 Based on the inventive concept of embodiment 1, this embodiment proposes a specific construction process of the adaptive motor control model in the adaptive parameter adjustment module, Figure 2 The embodiment shows a flow chart of the adaptive motor control model construction of the intelligent control system of the motor control machine based on vehicle behavior data, which specifically comprises: Step one, after the weather perception feature vector E is standardized to [0, 1] and weighted fusion, the weather influence factor wif is obtained; and the control increment of the last control cycle is extracted ; Step two, the driver trust degree of the current weather type, the weather influence factor, the vehicle performance change score and the control increment of the last control cycle are taken as the state input of the adaptive motor control model; Step three, the negative value of the weighted fusion of the absolute value of the state input is taken as the reward function, and the adaptive motor control model action parameter is outputted; Step three's reinforcement learning updates the policy network according to the reward function generated after the last decision, so as to give the action parameters next time More attention can be paid to "tracking accuracy, control smoothness, constraint satisfaction" and other goals. New action parameters are sent to step four to build a cost function, so that the quadratic objective function of the model at the next moment focuses more on the current most important performance dimension.

[0029] Step four, combined with the output of step three, builds a cost function, which is expressed as: ; Where N represents the prediction horizon, and represents the adaptive motor control model predicting N steps of state and control action from the current time to the future, represents the time The jth step of the predicted output is represented as a measurable quantity of the motor, such as speed or current, The jth step of the target output is given by the upper planning (such as vehicle speed cruise), such as expected speed or torque; Q and R represent the weight matrix, which is determined by the driver-weight adaptation strategy.

[0030] The driver-weight adaptation strategy specifically includes determining the weight matrix by introducing the current weather type driver trust and weather influence factor, and the calculation formula is: ; ; Where represents the baseline weight matrix, which represents the default penalty strength in normal weather + full trust state.

[0031] The driver trust coefficient 1 means full trust in the driver, and the system tends to relax the tracking penalty and give the driver more control space, while 0 means no trust, and the system strengthens the tracking control.

[0032] When the driver trust decreases, it means that the driver is in a poor or unreliable state, and the factor (1−Dtl) increases, so Q is amplified.

[0033] So that the model is more strictly reduced when optimizing the tracking error, to ensure that the system takes over and suppresses the deviation risk caused by poor human-machine cooperation.

[0034] The larger the weather severity (such as heavy rain, heavy snow), the higher the factor .

[0035] Therefore, the model will prioritize trajectory tracking accuracy in high-risk scenarios such as rain and snow to resist deviation under adverse conditions such as skidding and loss of control.

[0036] When the driver trust decreases, R is reduced, resulting in R being reduced.

[0037] The model weakens the inhibition of , allowing greater and more decisive control actions to correct deviations in time In bad weather, R is reduced, resulting in R being reduced. , further reducing the penalty for large actions.

[0038] In this way, in rain or snow or low adhesion scenarios, the system can respond quickly with more aggressive torque or voltage commands, enhancing dynamic stability.

[0039] In safety / comfort situations (high trust, good weather), R≈R0 control commands remain smooth, avoiding abrupt acceleration and deceleration.

[0040] In "low trust or high risk" moments, the system automatically "lets go" to achieve the desired tracking at the fastest speed, improving safety.

[0041] By using an adaptive motor control model, the system prioritizes error minimization when it is most needed (driver state is poor or weather is bad), and allows aggressive control, thereby significantly reducing the risk of accidents; when conditions permit, it returns to the default Q0, R0 setting, avoiding excessive intervention and abrupt actions, and ensuring a comfortable ride; the introduction of driver trust allows the control strategy to dynamically match the actual ability of different drivers, improving system flexibility and human-machine coordination; the double-factor superposition method can smoothly transition to various scenarios, achieving "one framework, multiple working conditions" versatility.

[0042] Step five, use OSQP to solve the cost function, output control instructions; control instructions include voltage vector instructions, current / torque references, and speed / position rate instructions.

[0043] The threshold and weight settings can be set by default according to the present application, or can be set by the person skilled in the art.

[0044] Embodiment 3 Figure 3 The present application shows a flowchart of an intelligent control method for a motor control machine based on vehicle behavior data, which is based on the same inventive concept as embodiments 1 and 2, an intelligent control method for a motor control machine based on vehicle behavior data, comprising the following steps: S1, collecting environmental data, vehicle motion data and driver state data during vehicle driving; S2, evaluating the change score of vehicle performance of the driver under different weather conditions, and establishing a driver performance evaluation strategy, according to the change score of vehicle performance of the driver under different weather conditions, outputting the driver trust degree; S3, constructing an adaptive motor control model, weighting the control input according to the driver trust degree, and outputting a control parameter.

[0045] Those skilled in the art will appreciate that embodiments of the application can be supplied as methods, systems, or computer program products. Accordingly, the application can be embodied in the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the application can be embodied in the form of a computer program product on one or more computer readable storage media (including, but not limited to, disk memory, CD-ROMs, optical storage media, etc.) having computer usable program code embodied therein.

[0046] The present application is described in reference to the flowchart and / or block diagrams of the method, apparatus (system) and computer program product according to embodiments of the application. It should be understood that each flow and / or block in the flowchart and / or block diagrams, as well as combinations of flows and / or blocks in the flowchart and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, a special purpose computer, an embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart and / or block diagrams block or blocks. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified in the flowchart block or blocks.

[0047] These computer program instructions can also be stored in a computer readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer readable memory produce an article of manufacture including instructions which implement the flowchart and / or block diagrams block or blocks. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified in the flowchart block or blocks.

[0048] These computer program instructions can also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the flowchart and / or block diagrams block or blocks. Figure 1 one or more flows and / or blocks Figure 1 means for carrying out the function specified in the flowchart block or blocks.

[0049] The embodiments of the present application are described above with reference to the accompanying drawings, but the present application is not limited to the above-described specific embodiments, and the above-described specific embodiments are merely illustrative, but not restrictive, and a person of ordinary skill in the art can make many forms under the inspiration of the present application without departing from the purpose of the present application and the scope protected by the claims, and these all belong to the protection of the present application.

Claims

1. An intelligent control system for a motor controller based on vehicle behavior data, characterized by: include: Data acquisition module, used to collect data from the vehicle's underlying ECU and the on-board gateway; A weather adaptation model building module is used to evaluate the vehicle performance change score of the driver's vehicle under different weather conditions, establish a driver performance evaluation strategy, evaluate the driver's proficiency under different weather conditions based on the vehicle performance change, and output the driver's trustworthiness; The adaptive parameter adjustment module is used to build an adaptive motor control model, distribute the control input weights according to the driver's confidence, and output control parameters.

2. The intelligent control system for a motor controller based on vehicle behavior data according to claim 1, characterized in that: The data acquisition module includes environmental data, vehicle motion data and driver status data; the environmental data includes camera images, millimeter wave radar point cloud, and lidar point cloud; the vehicle motion data includes vehicle speed, acceleration, lateral displacement, wheel speed and steering angle; the driver status data includes eye tracking, facial expression and heart rate belt; All data are aligned using timestamps and noise is removed using Kalman filtering.

3. The intelligent control system for a motor controller based on vehicle behavior data according to claim 1, characterized in that: The weather adaptation model construction module includes a performance index evaluation unit, a proficiency assessment unit and a driver trust unit; the performance index evaluation unit is used to obtain a vehicle performance change score based on the absolute value of the difference between the normalized weighted score of vehicle trajectory error, speed deviation, slip rate, road friction and smoothness and 1, where the performance index weight is updated based on the weather-weight mapping model, specifically as follows: constructing a weather perception feature vector E, based on a small fully connected neural network, searching for the performance index weight combination that maximizes the vehicle performance change score for historical operation data as a label, with the goal of minimizing the MSE between the regression output and the label, outputting an unnormalized performance index weight sequence vector, and obtaining the final performance index weight through Softmax.

4. The intelligent control system for a motor controller based on vehicle behavior data according to claim 3, characterized in that: The performance index evaluation unit also includes calculating the vehicle performance change score Cvp in the current window after each evaluation window ends, setting the target performance score as Pcvp, and obtaining the performance index error ,when When the preset performance indicator error threshold is exceeded, the weather-weight mapping model is gradient updated. ,in represents the learning rate, The performance indicator weight sequence of the kth iteration, for each performance indicator weight setting ,when When the change is less than the set threshold, the iteration stops.

5. The intelligent control system for a motor controller based on vehicle behavior data according to claim 3, characterized in that: The proficiency assessment unit is equipped with a driver performance evaluation strategy, specifically including: creating a weather type vector W, constructing a long-term proficiency model of the driver under various weather conditions based on the vehicle performance change score, which is expressed as: for the kth iteration , Indicates the proficiency of driver i under weather type w, and pre-sets the initial proficiency of the driver under each weather type , Indicates the performance change score of this vehicle.

6. The intelligent control system for a motor controller based on vehicle behavior data according to claim 3, characterized in that: The driver trust unit is used to determine the driver trust based on the driver's current state and historical state. Specifically, it includes: obtaining the average driver historical state score based on the historical driver state data of the current weather type as the driver's historical state baseline dsh, and calculating the driver's current state score dsc within the past time window T with a time interval of t in the same way; calculating the difference between the driver's current state score and the historical state baseline as the state baseline correction factor Δds, and then obtaining the driver trust of the current weather type, which is expressed as .

7. The intelligent control system for a motor controller based on vehicle behavior data according to claim 1, characterized in that: The specific process of the adaptive motor control model includes: Step 1: Normalize the weather perception feature vector E to [0,1] and then perform weighted fusion to obtain the weather influencing factor wif; and extract the control increment of the previous control cycle. ; Step 2: Combine the driver trust level, weather impact factors, vehicle performance change score and As state input to the adaptive motor control model; Step 3: Use the negative value of the weighted fusion of the absolute value of the state input as the reward function and output the action parameters of the adaptive motor control model ; Step 4: Construct a cost function based on the output of step 3. Step 5: Use OSQP to solve the cost function and output control instructions.

8. The intelligent control system for a motor controller based on vehicle behavior data according to claim 7, characterized in that: The cost function is expressed as: ； Among them, N represents the length of the prediction time domain, Indicates time The predicted output of step j, represents the target output of the jth step, Q and R represent weight matrices, which are determined by the driver-weight adaptation strategy.

9. The intelligent control system for a motor controller based on vehicle behavior data according to claim 7, characterized in that: The driver-weight adaptation strategy specifically includes determining a weight matrix by introducing the driver's trust in the current weather type and the weather influencing factor. The calculation formula is: ； ； Among them, represents the baseline weight matrix, which is the default penalty intensity under normal weather + full trust state.

10. A method for intelligently controlling a motor controller based on vehicle behavior data, for executing the intelligent control system for a motor controller based on vehicle behavior data according to any one of claims 1 to 9, characterized in that: The following steps are involved: S1, collecting environmental data, vehicle motion data and driver status data during vehicle driving; S2. Evaluate the vehicle performance change scores of the driver's vehicle under different weather conditions, and establish a driver performance evaluation strategy to evaluate the driver's proficiency under different weather conditions based on the vehicle performance changes, and output the driver's trustworthiness; S3. Build an adaptive motor control model, assign weights to control inputs according to the driver's confidence, and output control parameters.

Images