Adaptive cruise control method and system capable of changing time headway
By introducing variable front time distance and model prediction control technology into the adaptive cruise control system of electric vehicles, the problem of traditional systems dealing with the difficulty of changing acceleration of the vehicle in the forward in a complex environment is solved, and safer and more stable cruise control is achieved. Improves system response speed and robustness.
Patent Information
- Application Number
- CN202411247856.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-06
- Publication Date
- 2024-11-19
AI Technical Summary
Traditional adaptive cruise control systems are difficult to fully utilize their advantages in electric vehicles, especially in complex traffic environments, which is difficult to effectively respond to changes in the acceleration of the vehicle in front, resulting in unstable driving experience and safety risks. The control optimization problem involves multiple variables and multiple Constraints, it is difficult to find feasible solutions in high-dimensional optimization spaces, affecting the system response speed and robustness.
Adaptive cruise control method with variable front time distance is adopted, and the variable workshop time distance strategy and model prediction control technology that considers the acceleration of the vehicle ahead, the relaxation factor is introduced to transform the control optimization problem into a secondary planning with constraints, and the expansion of Feasible solutions to ensure safety and smooth cruise.
It realizes the improvement of driving safety and cruise stability in complex environments, enhances the system response speed and robustness, and smoothly realizes cruising speed and accurate forward car follow functions.
Smart Images

Figure CN118977709A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of intelligent assisted driving technology, and more specifically, to a variable headway adaptive cruise control method and system. Background Art
[0002] In electric vehicles, the adaptive cruise control (ACC) system is an important part of intelligent driving assistance technology. With the widespread application of electric vehicles, the requirements for their intelligent driving systems are becoming higher and higher. Due to their fast instantaneous torque response and high energy recovery efficiency, electric vehicles have certain uniqueness in the design of ACC systems. Traditional ACC systems are usually based on a fixed headway strategy, which makes it difficult to give full play to the advantages of electric vehicles, especially in complex and changeable traffic environments. It is difficult to effectively respond to the acceleration changes of the vehicle in front, resulting in an unsmooth driving experience and potential safety risks. It is difficult to adapt to the characteristics of electric vehicles' rapid response. In the ACC system, electric vehicles need to comprehensively consider multiple goals such as endurance and driving comfort. These goals will conflict with each other. How to effectively balance these requirements in multi-objective control while ensuring the real-time and stability of the system is a technical problem that needs to be solved urgently. In the ACC system of electric vehicles, control optimization problems usually involve multiple variables and multiple constraints. How to effectively find feasible solutions in a high-dimensional optimization space and expand the scope of solutions is the key to improving the response speed and robustness of the system. Summary of the invention
[0003] In order to overcome the above-mentioned defects of the prior art, the present invention provides an adaptive cruise control method and system with variable headway, which improves safety by introducing a variable headway strategy that takes into account the acceleration of the leading vehicle, adopts model predictive control technology, introduces a relaxation factor in a multi-objective adaptive cruise system, expands the range of feasible solutions, and transforms the control optimization problem into a quadratic programming with constraints, thereby ensuring safety while achieving smooth cruising and accurate following.
[0004] To achieve the above object, the present invention provides the following technical solutions:
[0005] An adaptive cruise control method with variable headway time comprises the following steps:
[0006] Step 1, establishing hierarchical control logic of the adaptive cruise control system;
[0007] Step 2: Switch between the cruise control mode and the following cruise control mode according to the acquired vehicle information;
[0008] Also includes:
[0009] Step 3, establishing a safe spacing strategy for variable headway distances taking into account the involved acceleration;
[0010] Step 4: Based on the safety distance model established in step 3, model predictive control is applied to the multi-objective adaptive cruise control system, and a relaxation factor is introduced to expand the feasible domain solution, converting the optimization objective of the ACC system control algorithm into a quadratic programming problem with constraints.
[0011] As a further solution of the present invention, a hierarchical control logic of an adaptive cruise control system is established in step 1. The upper-level controller obtains the speed, acceleration and relative distance between the front vehicle and the two vehicles through sensors, radars and vehicle status information in the Carsim software, and transmits these data to the Simulink software. According to relevant control theories, the upper-level controller calculates the expected acceleration value and transmits it to the lower-level controller. The lower-level controller is mainly composed of a drive / brake switching logic and a vehicle inverse model. According to the information provided by the upper-level controller, a reasonable expected drive torque and brake pressure are calculated, and these control signals are input into Carsim to form a closed-loop control system.
[0012] As a further solution of the present invention, in step 3, the variable headway safety strategy considering the acceleration of the preceding vehicle is:
[0013] In t max ≤t 0 -cv r -ka 1 When t h =t max ;
[0014] In t min ≤t 0 -cv r -ka 1 ≤t max When t h =t 0 -cv r -ka 1 ;
[0015] Otherwise, t h =t min ;
[0016] In the above strategy, k is a constant greater than 0, a 1 is the acceleration of the preceding vehicle, t max ,t min are the maximum and minimum time headway between workshops, t 0 is the minimum safe time distance between two vehicles, t h is the current workshop time distance, v r is the relative speed of the two vehicles, c is the adjustment coefficient, which is set according to actual needs, where t h satisfy:
[0017] d des =t h v h +d 0
[0018] Where: v h is the vehicle speed, d 0 The minimum safe distance between two workshops is 5m, d des Expected safe distance.
[0019] As a further solution of the present invention, in step 4, the model predictive control is applied to the multi-objective adaptive cruise control system. At each discrete moment, the state variables are updated according to the current state, control input and disturbance, reflecting the vehicle's following control behavior, and the vehicle's dynamic model is established. The state equation in the model is:
[0020] x(k+1)=Ax(k)+Bu(k)+Gw(k)
[0021] Where: k is the discrete time step, x(k+1) is the state variable of the system at the k+1th discrete moment in the future, x(k) is the state variable of the system at the kth discrete moment, A is the state transfer matrix, B is the control input matrix, A and B are obtained according to the dynamic characteristics and control target modeling of the system, G is the disturbance matrix, u(k) is the control input of the system, and w(k) is the disturbance of the system.
[0022] Through these matrices, the system can update the state variables at each discrete moment k according to the state variables, control input variables and disturbances of the current system to reflect the vehicle's following control behavior, and express the acceleration and acceleration change rate in discrete form. At the same time, in order to make the equation better reflect the actual situation during following, the acceleration of the leading vehicle is used as a disturbance.
[0023] As a further solution of the present invention, in the state equation of the vehicle dynamics model established in step 4, the actual vehicle distance, the vehicle speed, the relative vehicle speed, the vehicle acceleration, the vehicle acceleration, and the vehicle acceleration change rate are used as inputs of the state equation, and the formula of the system state variables is:
[0024] x(k)=[Δd(k),v f (k),v r (k),a f (k),j f (k)] T
[0025] Where: Δd(k) is the actual vehicle spacing at the kth discrete moment, v f (k) is the vehicle speed at the kth discrete moment, v r (k) is the relative speed of the two vehicles at the kth discrete moment, af (k) is the vehicle acceleration at the kth discrete moment, j f (k) is the acceleration change rate of the vehicle at the kth discrete moment.
[0026] As a further solution of the present invention, in the state equation of the vehicle dynamics model established in step 4, the state matrix is:
[0027]
[0028] Where: T s is the system sampling time interval, T g is the inertia time constant;
[0029] The control input matrix is:
[0030] The perturbation matrix is:
[0031] As a further solution of the present invention, in step 4, the distance between the two vehicles, the speed of the vehicle, the relative speed of the two vehicles, the acceleration of the vehicle, and the rate of change of the acceleration of the vehicle are compared with the system target state to generate an optimized performance index vector for guiding the operation of the adaptive cruise system to meet the requirements of safety, comfort, followability and economy. The equation for obtaining the optimized performance index vector is:
[0032] y(k)=[Δd(k),v f (k),v r (k),a f (k),j f (k)] T =Cx(k)-D
[0033] Where: y(k) is the optimization performance index vector, which is the output quantity to be optimized in the kth discrete time step of the adaptive cruise control system; C is the output matrix, which is used to map the state variables to the optimization performance index; D is the offset vector, which is equal to the expected value of the system and is used to correct the output result.
[0034] As a further solution of the present invention, in step 4, the following hard constraints are set for the equation for obtaining the optimization performance index vector:
[0035] d≥d des
[0036] j min ≤j f ≤j max
[0037] a min ≤a f≤a max
[0038] u min ≤u≤u max
[0039] Where: d is the distance between two vehicles, j f is the acceleration change rate of the vehicle, j min 、j max are the minimum and maximum values of the acceleration change rate of the vehicle, respectively. f is the vehicle acceleration, a min 、a max are the lower and upper limits of the vehicle’s acceleration, u is the control input of the system, and u min 、u max are the lower and upper limits of the control input respectively.
[0040] As a further solution of the present invention, in step 4, the objective function of the model predictive control algorithm weights the comprehensive performance index at the future moment to obtain the optimal control effect. The formula of the objective function is:
[0041]
[0042] Where: Q, R are weighted coefficients, Q = diag (ω Δd ,ω v ,ω u ,ω j ),ω Δd ,ω v ,ω u ,ω j are the weight coefficients of the distance error between the two vehicles, the relative speed weight coefficient of the two vehicles, the acceleration weight coefficient of the vehicle, and the acceleration change rate weight coefficient of the vehicle, i is the discrete time index, J is the objective function value, N p is the length of the prediction time domain, N c To control the length of the time domain, is the output performance index predicted at the i-th moment when the system state is known at the current moment k, y r (k+i|k) is the ideal state that the system will reach at the (k+i)th moment in the future when the system state is known at the current moment k, and u(k+i) is the control input of the system at the (k+i)th moment in the future when the system state is known at the current moment k.
[0043] As a further solution of the present invention, in step 4, a relaxation factor is introduced into the hard constraint condition to selectively soften different constraint conditions and expand the effective range of the constraint condition. The hard constraint condition into which the relaxation factor is introduced is:
[0044]
[0045] Where: are the lower and upper relaxation coefficients of the vehicle acceleration, ε 1 is the relaxation factor of the vehicle acceleration, are the lower and upper relaxation coefficients of the vehicle speed, ε 2 is the relaxation factor of the vehicle speed, are the lower and upper relaxation coefficients of the acceleration change rate of the vehicle, ε 3 is the relaxation factor of the vehicle’s acceleration rate of change, are the lower and upper bound relaxation coefficients of the system control input variables, ε 4 It is the relaxation factor of the system control input variable. Each relaxation factor, lower limit relaxation coefficient and upper limit relaxation coefficient are obtained through simulation analysis of various vehicle operation scenarios.
[0046] Introducing relaxation factors into hard constraints and selectively softening different constraints can expand the effective range of constraints, thereby ensuring that the optimization problem can be solved.
[0047] An adaptive cruise control system with variable headway is used to implement the above-mentioned adaptive cruise control method with variable headway, including a vehicle-mounted controller, a sensor module, an actuator module, a communication module and a human-computer interaction unit. The vehicle-mounted controller is connected to the sensor module, the actuator module and the human-computer interaction unit through the communication module. The vehicle-mounted controller includes an adaptive learning module, a safety monitoring module and an energy management module. The adaptive learning module is connected to the safety monitoring module and the energy management module.
[0048] The on-board controller is the core processing unit of the entire adaptive cruise control system. It is responsible for executing complex control algorithms and real-time data processing, receiving data from the sensor module, sending control commands to the actuator module through the communication module, and exchanging data with the human-computer interaction unit. Adaptive learning module: Dynamically adjust the cruise control parameters (headway, acceleration, control input) according to the vehicle's historical driving data and real-time traffic information to improve the system's adaptability and optimization performance. Through adaptive learning, it can automatically adjust the cruise control strategy according to different driving styles and traffic conditions to ensure optimal performance in a changing environment. The safety monitoring module monitors the system's operating status and changes in the external environment (obstacles ahead, road conditions) in real time to ensure that warnings are issued or emergency braking measures are taken when potential dangers are detected. This module includes fault detection and diagnosis functions, and can quickly take over control or switch to safety mode when the system is abnormal to ensure driving safety. The energy management module is particularly suitable for electric vehicles. This module optimizes energy consumption strategies to maximize the range without affecting driving performance. The energy management module is connected to the battery management system (BMS) to adjust the power output and energy recovery strategies in real time to balance the vehicle's performance and energy efficiency. The sensor module is responsible for collecting data about the vehicle's surrounding environment and its own status, and providing accurate input information to the on-board controller, including vehicle speed, acceleration, vehicle spacing, speed and acceleration of the vehicle in front, road obstacles, and road curvature. The actuator module executes the control commands issued by the on-board controller, including the acceleration, deceleration, and steering operations of the vehicle. The actuator module directly affects the vehicle's power output and driving state. It adjusts the output torque of the motor according to the controller's acceleration command, controls the vehicle's acceleration performance, adjusts the brake pressure according to the braking command, realizes the vehicle's deceleration and emergency braking, and adjusts the steering angle according to the steering command to ensure that the vehicle travels along the predetermined route. The communication module ensures real-time communication between the on-board controller and the sensor module, actuator module, and human-computer interaction unit. At the same time, it is also responsible for data exchange between the on-board controller and external devices (cloud servers, other vehicles, and traffic infrastructure), supports vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), and vehicle-to-pedestrian (V2P) communications, can obtain real-time traffic information, optimize vehicle driving paths and energy management strategies, and is used to communicate with cloud servers to achieve data upload, remote diagnosis, and software updates. The human-machine interaction unit provides the driver with a display interface for system status, vehicle information, cruise control settings and warning messages, and allows the driver to input parameters, select driving modes or manually control the vehicle through the interface.
[0049] Compared with the prior art, the technical effect of the present invention is as follows: the present invention enhances safety by introducing a variable time spacing strategy that takes into account the acceleration of the leading vehicle, adopts model predictive control technology, introduces a relaxation factor in a multi-objective adaptive cruise control system to expand the range of feasible solutions, and transforms the control optimization problem of the automatic cruise system into a quadratic programming problem with constraints. On the basis of ensuring safety, it can achieve smooth cruise control and accurate leading vehicle following function. BRIEF DESCRIPTION OF THE DRAWINGS
[0050] Figure 1 It is a hierarchical control logic diagram of the adaptive cruise system in the present invention;
[0051] Figure 2 It is the cruise speed response diagram in the present invention;
[0052] Figure 3 It is the acceleration response diagram of the cruise control in the present invention;
[0053] Figure 4 It is the following vehicle cruising speed response diagram in the present invention;
[0054] Figure 5 It is the acceleration response diagram of the following vehicle cruising in the present invention;
[0055] Figure 6 It is the following distance response diagram in the present invention;
[0056] Figure 7 A switching strategy diagram between the cruise mode and the following mode of the present invention;
[0057] Figure 8 This is a schematic diagram of the improved safety spacing strategy of the present invention;
[0058] Fig. 9 This is a control logic diagram of the system mentioned in the present invention. DETAILED DESCRIPTION
[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0060] The present invention provides an adaptive cruise control method with variable headway, comprising the following steps:
[0061] Step 1, establishing hierarchical control logic of the adaptive cruise control system;
[0062] Step 2: Switch between the cruise control mode and the following cruise control mode according to the acquired vehicle information;
[0063] Also includes:
[0064] Step 3, establishing a safe spacing strategy for variable headway considering the acceleration of the preceding vehicle;
[0065] Step 4: Based on the safety distance model established in step 3, model predictive control is applied to the multi-objective adaptive cruise control system, and a relaxation factor is introduced to expand the feasible domain solution, converting the optimization objective of the ACC system control algorithm into a quadratic programming problem with constraints.
[0066] It should be noted that if Figure 1 As shown in Figure 1, in step 1, the hierarchical control logic of the adaptive cruise control system is established. The upper controller obtains the speed, acceleration and relative distance between the front vehicle and the two vehicles through the sensors, radars and vehicle status information in the Carsim software, and passes these data to the Simulink software. According to the relevant control theory, the upper controller calculates the expected acceleration value and passes it to the lower controller. The lower controller is mainly composed of the drive / brake switching logic and the vehicle inverse model. According to the information provided by the upper controller, the reasonable expected drive torque and brake pressure are calculated, and these control signals are input into Carsim to form a closed-loop control system.
[0067] It should be noted that in step 3, the variable headway safety strategy considering the acceleration of the preceding vehicle is:
[0068] In t max ≤t 0 -cv r -ka 1 When t h =t max ;
[0069] In t min ≤t 0 -cv r -ka 1 ≤t max When t h =t 0 -cv r -ka 1 ;
[0070] Otherwise, t h =t min ;
[0071] In the above strategy, k is a constant greater than 0, a 1 is the acceleration of the preceding vehicle, t max ,t min are the maximum and minimum time headway between workshops, t 0is the minimum safe time distance between two vehicles, t h is the current workshop time distance, v r is the relative speed of the two vehicles, c is the adjustment coefficient, which is set according to actual needs, where t h satisfy:
[0072] d des =t h v h +d 0
[0073] Where: v h is the vehicle speed, d 0 The minimum safe distance between two workshops is 5m, d des Expected safe distance.
[0074] It should be noted that the model predictive control used in step 4 is applied to the multi-objective adaptive cruise control system. At each discrete moment, the state variables are updated according to the current state, control input and disturbance, reflecting the vehicle's following control behavior and establishing the vehicle's dynamic model. The state equation in the model is:
[0075] x(k+1)=Ax(k)+Bu(k)+Gw(k)
[0076] Where: k is the discrete time step, x(k+1) is the state variable of the system at the k+1th discrete moment in the future, x(k) is the state variable of the system at the kth discrete moment, A is the state transfer matrix, B is the control input matrix, A and B are obtained according to the dynamic characteristics and control target modeling of the system, G is the disturbance matrix, u(k) is the control input of the system, and w(k) is the disturbance of the system.
[0077] Through these matrices, the system can update the state variables at each discrete moment k according to the state variables, control input variables and disturbances of the current system to reflect the vehicle's following control behavior, and express the acceleration and acceleration rate in discrete form. At the same time, in order to make the equation better reflect the actual situation during following, the acceleration of the leading vehicle is used as a disturbance.
[0078] It should be noted that in the state equation of the vehicle dynamics model established in step 4, the actual vehicle distance, the vehicle speed, the relative vehicle speed, the vehicle acceleration, the vehicle acceleration, and the vehicle acceleration change rate are used as inputs of the state equation, and the formula of the system state variables is:
[0079] x(k)=[Δd(k),v f (k),v r (k),a f (k),j f (k)] T
[0080] Where: Δd(k) is the actual vehicle spacing at the kth discrete moment, v f (k) is the vehicle speed at the kth discrete moment, v r (k) is the relative speed of the two vehicles at the kth discrete moment, a f (k) is the vehicle acceleration at the kth discrete moment, j f (k) is the acceleration change rate of the vehicle at the kth discrete moment.
[0081] It should be noted that in the state equation of the vehicle dynamics model established in step 4, the state matrix is:
[0082]
[0083] Where: T s is the system sampling time interval, T g is the inertia time constant;
[0084] The control input matrix is:
[0085] The perturbation matrix is:
[0086] It should be noted that in step 4, the distance between the two vehicles, the speed of the vehicle, the relative speed between the two vehicles, the acceleration of the vehicle, the rate of change of the acceleration of the vehicle are compared with the system target state to generate an optimized performance index vector, which is used to guide the operation of the adaptive cruise system to meet the requirements of safety, comfort, followability and economy. The equation for obtaining the optimized performance index vector is:
[0087] y(k)=[Δd(k),v f (k),v r (k),a f (k),j f (k)] T =Cx(k)-D
[0088] Where: y(k) is the optimization performance index vector, which is the output quantity to be optimized in the kth discrete time step of the adaptive cruise control system; C is the output matrix, which is used to map the state variables to the optimization performance index; D is the offset vector, which is equal to the expected value of the system and is used to correct the output result.
[0089] It should be noted that in step 4, the following hard constraints are set for the equation for obtaining the optimization performance index vector:
[0090] d≥ des
[0091] j min≤j f ≤j max
[0092] a min ≤a f ≤a max
[0093] u min ≤u≤u max
[0094] Where: d is the distance between two vehicles, j f is the acceleration change rate of the vehicle, j min 、j max are the minimum and maximum values of the acceleration change rate of the vehicle, respectively. f is the vehicle acceleration, a min 、a max are the lower and upper limits of the vehicle’s acceleration, u is the control input of the system, and u min 、u max are the lower and upper limits of the control input respectively.
[0095] It should be noted that in step 4, the objective function of the model predictive control algorithm weights the comprehensive performance index at future moments to obtain the optimal control effect. The formula of the objective function is:
[0096]
[0097] Where: Q, R are weighted coefficients, Q = diag (ω Δd ,ω v ,ω u ,ω j ),ω Δd ,ω v ,ω u ,ω j are the weight coefficients of the distance error between the two vehicles, the relative speed weight coefficient of the two vehicles, the acceleration weight coefficient of the vehicle, and the acceleration change rate weight coefficient of the vehicle, i is the discrete time index, J is the objective function value, N p is the length of the prediction time domain, N c To control the length of the time domain, is the output performance index predicted at the i-th moment when the system state is known at the current moment k, y r (k+i|k) is the ideal state that the system will reach at the (k+i)th moment in the future when the system state is known at the current moment k, and u(k+i) is the control input of the system at the (k+i)th moment in the future when the system state is known at the current moment k.
[0098] It should be noted that in step 4, a relaxation factor is introduced into the hard constraint conditions to selectively soften different constraint conditions and expand the effective range of the constraint conditions. The hard constraint conditions that introduce the relaxation factor are:
[0099]
[0100] Where: are the lower and upper relaxation coefficients of the vehicle acceleration, ε 1 is the relaxation factor of the vehicle acceleration, are the lower and upper relaxation coefficients of the vehicle speed, ε 2 is the relaxation factor of the vehicle speed, are the lower and upper relaxation coefficients of the acceleration change rate of the vehicle, ε 3 is the relaxation factor of the vehicle’s acceleration rate of change, are the lower and upper bound relaxation coefficients of the system control input variables, ε 4 It is the relaxation factor of the system control input variable. Each relaxation factor, lower limit relaxation coefficient and upper limit relaxation coefficient are obtained through simulation analysis of various vehicle operation scenarios.
[0101] Introducing relaxation factors into hard constraints and selectively softening different constraints can expand the effective range of constraints, thereby ensuring that the optimization problem can be solved.
[0102] An adaptive cruise control system with variable headway is used to implement the above-mentioned adaptive cruise control method with variable headway, including a vehicle-mounted controller, a sensor module, an actuator module, a communication module and a human-computer interaction unit. The vehicle-mounted controller is connected to the sensor module, the actuator module and the human-computer interaction unit through the communication module. The vehicle-mounted controller includes an adaptive learning module, a safety monitoring module and an energy management module. The adaptive learning module is connected to the safety monitoring module and the energy management module.
[0103] The on-board controller is the core processing unit of the entire adaptive cruise control system. It is responsible for executing complex control algorithms and real-time data processing, receiving data from the sensor module, sending control commands to the actuator module through the communication module, and exchanging data with the human-computer interaction unit. Adaptive learning module: Dynamically adjust the cruise control parameters (headway, acceleration, control input) according to the vehicle's historical driving data and real-time traffic information to improve the system's adaptability and optimization performance. Through adaptive learning, it can automatically adjust the cruise control strategy according to different driving styles and traffic conditions to ensure optimal performance in a changing environment. The safety monitoring module monitors the system's operating status and changes in the external environment (obstacles ahead, road conditions) in real time to ensure that warnings are issued or emergency braking measures are taken when potential dangers are detected. This module includes fault detection and diagnosis functions, and can quickly take over control or switch to safety mode when the system is abnormal to ensure driving safety. The energy management module is particularly suitable for electric vehicles. This module optimizes energy consumption strategies to maximize the range without affecting driving performance. The energy management module is connected to the battery management system (BMS) to adjust the power output and energy recovery strategies in real time to balance the vehicle's performance and energy efficiency. The sensor module is responsible for collecting data about the vehicle's surrounding environment and its own status, and providing accurate input information to the on-board controller, including vehicle speed, acceleration, vehicle spacing, speed and acceleration of the vehicle in front, road obstacles, and road curvature. The actuator module executes the control commands issued by the on-board controller, including the acceleration, deceleration, and steering operations of the vehicle. The actuator module directly affects the vehicle's power output and driving state. It adjusts the output torque of the motor according to the controller's acceleration command, controls the vehicle's acceleration performance, adjusts the brake pressure according to the braking command, realizes the vehicle's deceleration and emergency braking, and adjusts the steering angle according to the steering command to ensure that the vehicle travels along the predetermined route. The communication module ensures real-time communication between the on-board controller and the sensor module, actuator module, and human-computer interaction unit. At the same time, it is also responsible for data exchange between the on-board controller and external devices (cloud servers, other vehicles, and traffic infrastructure), supports vehicle-to-vehicle (V2V), vehicle-to-infrastructure (V2I), and vehicle-to-pedestrian (V2P) communications, can obtain real-time traffic information, optimize vehicle driving paths and energy management strategies, and is used to communicate with cloud servers to achieve data upload, remote diagnosis, and software updates. The human-machine interaction unit provides the driver with a display interface for system status, vehicle information, cruise control settings and warning messages, and allows the driver to input parameters, select driving modes or manually control the vehicle through the interface.
[0104] The present invention enhances safety by introducing a variable headway strategy that takes the acceleration of the leading vehicle into consideration. It adopts model predictive control technology and introduces a relaxation factor to expand the range of feasible solutions in a multi-objective adaptive cruise control system. It converts the control optimization problem of the automatic cruise system into a quadratic programming problem with constraints. On the basis of ensuring safety, it can achieve smooth cruise control and accurate leading vehicle following function.
[0105] Example
[0106] In order to verify the spacing strategy, upper control algorithm and lower control of the method and system proposed in the present invention, the algorithm model is built using the MATLAB / Simulink platform. In the system, the following vehicle information and the main vehicle information are transmitted to the upper control algorithm module of ACC, which selects the working mode according to the current state of the main vehicle, mainly including two modes: cruise control and following vehicle cruise. The core of the upper control algorithm is the MPC algorithm. After the upper control algorithm module determines the expected acceleration, it transmits it to the lower control algorithm module. The lower control module determines whether the vehicle is accelerated or decelerated according to the received expected acceleration through the driving and braking switching logic, and completes the control of the vehicle through the driving torque or braking force. Two typical working conditions (cruise control and following vehicle cruise) are selected for simulation analysis: First, under the cruise control working condition, the system will keep the vehicle running at a constant speed to test the stability of the system under constant speed; secondly, in the following vehicle cruise working condition, the simulation will simulate the situation where the vehicle follows the front vehicle at different distances to evaluate the response speed and accuracy of the system in dynamic following.
[0107] The hierarchical control structure of the adaptive cruise control system in the present invention includes an upper controller and a lower controller. The modules and processes are described as follows:
[0108] Upper controller
[0109] Input signal: The upper controller receives vehicle status information and environmental data from bicycle status and environmental information sensors. These data include vehicle speed, acceleration, distance to the vehicle in front, and other information. The vehicle-following cruise module in the upper controller includes two submodules, namely the improved VTH spacing strategy and the MPC controller. The improved VTH spacing strategy is used to calculate the safe following distance of the vehicle. The VTH strategy can dynamically adjust the vehicle spacing according to the vehicle speed and the acceleration of the vehicle in front. MPC controller: Based on the model predictive control (MPC) algorithm, it calculates the optimal acceleration or deceleration command when following the vehicle and passes it to the lower controller. The PID controller is used in the cruise control module to maintain the set speed of the vehicle in the cruise control mode. The PID controller adjusts the acceleration of the vehicle according to the speed error (the difference between the set speed and the actual speed).
[0110] Output signal: The upper controller sends the corresponding acceleration or deceleration command to the lower controller for further execution according to the output of the current mode (cruise or fixed speed cruise).
[0111] Lower level controller
[0112] Carsim vehicle dynamics model: In the lower-level controller, the Carsim vehicle dynamics model is used to simulate the actual dynamic response of the vehicle. This module receives the driving torque and brake pressure instructions transmitted by the upper-level controller and simulates the dynamic behavior of the actual vehicle under these instructions.
[0113] On-board drive / brake control actuator: The lower-level controller also contains an on-board drive / brake control actuator module, which sends control signals to the vehicle's drive system or brake system based on the simulation results of the Carsim model to achieve actual acceleration or deceleration operations of the vehicle.
[0114] PID lower-level algorithm: The lower-level control also includes a PID lower-level algorithm for further fine-tuning the drive torque and brake pressure to ensure that the vehicle's power output is consistent with the expected value of the upper-level controller.
[0115] Feedback loop
[0116] Vehicle status feedback: The actual status information of the vehicle is fed back to the upper-level controller through driving status and environmental information sensors, so that the control system can adjust the control strategy in real time to adapt to the current driving environment and vehicle status.
[0117] like Figure 7 As shown, it is a switching strategy diagram of the cruise mode and the following mode of the present invention. The system starts and enters the preparation state of the adaptive cruise control mode. The radar monitors the road conditions in front of the vehicle, especially detects whether there are other vehicles in front. If there is a vehicle in front, the system will continue to make subsequent judgments; if there is no vehicle in front, the system directly enters the fixed speed cruise mode and maintains the set cruising speed. Compare the speed of the front vehicle with the set cruising speed. If the speed of the front vehicle is not higher than the set cruising speed, the system continues to maintain the fixed speed cruise mode. Otherwise, it enters the following cruise mode and adjusts the vehicle speed to maintain a safe distance from the front vehicle. In the following cruise mode, the system continuously monitors the distance between the vehicle and the front vehicle, and determines whether emergency braking is required or whether there is active intervention by the driver (such as braking or acceleration). If the system detects that emergency braking is required or the driver has actively intervened, the process ends and the ACC system exits automatic control; if emergency braking is not required and there is no driver intervention, the system remains in the following cruise mode until the process ends. The system exits the adaptive cruise mode according to the situation and ends the process.
[0118] like Figure 8As shown in the figure, it is the improved safety distance strategy of the present invention. The safety distance model is the foundation of the adaptive cruise control system (ACC). The actual application standard of the safety distance model depends not only on the safety performance of the ACC system, but also on the traffic density of the road. If the safety distance is set too large, the traffic efficiency of the lane will be reduced, and the probability of vehicles in the side lanes inserting and vehicles behind overtaking will be increased; if the safety distance is set too small, when the front vehicle encounters an emergency, it cannot react in time, thus causing traffic accidents. It can be seen that it is extremely important to set a safe and reliable safety distance model. At present, there are two main types of vehicle spacing algorithms: fixed vehicle spacing and variable vehicle spacing. Fixed vehicle spacing means that the safety distance between the vehicle and the front vehicle remains unchanged regardless of the speed of the front vehicle or the surrounding road environment. Although this method has a simple structure, due to the constant vehicle spacing, the algorithm is difficult to adapt to complex driving conditions, and it is impossible to ensure the safety of the vehicle while ensuring the smooth flow of the road, resulting in undesirable consequences. The variable safety vehicle spacing model refers to dynamically adjusting the safety vehicle spacing according to factors such as vehicle speed, thereby making up for the shortcomings of the fixed vehicle spacing model. This model can adapt to driving needs under different vehicle conditions and road conditions. The variable headway model is usually designed based on the headway between vehicles, and mainly includes two types: the constant time headway algorithm (CTH) and the variable time headway algorithm (VTH). Figure 8 As shown in FIG. 3 , in step 3, the variable headway safety strategy considering the acceleration of the preceding vehicle is:
[0119] In t max ≤t 0 -cv r -ka 1 When t h =t max ;
[0120] In t min ≤t 0 -cv r -ka 1 ≤t max When t h =t 0 -cv r -ka 1 ;
[0121] Otherwise, t h =t min ;
[0122] In the above strategy, k is a constant greater than 0, a 1 is the acceleration of the preceding vehicle, t max ,t min are the maximum and minimum time headway between workshops, t0 is the minimum safe time distance between two vehicles, t h is the current workshop time distance, v r is the relative speed of the two vehicles, c is the adjustment coefficient, which is set according to actual needs, where t h satisfy:
[0123] d des =t h v h +d 0
[0124] Where: v h is the vehicle speed, d 0 The minimum safe distance between two workshops is 5m, d des Expected safe distance.
[0125] like Fig. 9 The figure shows the control logic diagram of the system mentioned in the present invention. The system uses sensors to identify the vehicle speed and headway (the distance from the vehicle in front at the current moment). This control system effectively ensures that the vehicle maintains a safe distance from the vehicle in front through a feedback mechanism. The adaptive cruise control system dynamically adjusts the following variables:
[0126] Vehicle speed (V_host): The current speed of the host vehicle.
[0127] Dis_rel: The relative distance between the vehicle in front and the vehicle in front.
[0128] Relative speed (Spd_rel): The speed difference between the host vehicle and the preceding vehicle.
[0129] Braking and torque commands (ex_brake, ex_torque): used to adjust the brake or throttle control to maintain or reduce speed.
[0130] Input signal:
[0131] Dis_rel (relative distance): used to measure the distance between the main vehicle and the vehicle in front.
[0132] Spd_Lead (lead vehicle speed): The leading vehicle speed is used to appropriately adjust the speed of the lead vehicle.
[0133] V_host (host vehicle speed): The current speed of the host vehicle, which is a key variable to ensure safe and comfortable driving.
[0134] Ax_host (host vehicle acceleration): The longitudinal acceleration of the host vehicle, which helps calculate the adjustments needed for cruise control.
[0135] Spd_rel (relative speed): The speed difference between the main vehicle and the vehicle in front is an important basis for determining acceleration or deceleration.
[0136] Control logic: Headway control: This component processes the relative speed and distance data (Dis_rel and Spd_rel) and dynamically adjusts the headway between the host vehicle and the vehicle ahead. Headway is the main safety function in adaptive cruise control.
[0137] Switch: The switch selects different control modes and switches between manual input and automatic control adjustment.
[0138] State machine: used to manage different driving modes (such as braking, acceleration, coasting), adjusting according to traffic conditions and driver input.
[0139] Actuator and output:
[0140] Brake application (ex_brake): The brake system is activated when the system detects that the relative distance to the vehicle ahead is decreasing rapidly or the vehicle ahead is decelerating.
[0141] Torque Adjustment (ex_torque): The system adjusts the throttle to maintain a safe distance and a preset speed.
[0142] Vehicle Control (vs_sf): This module represents the overall vehicle speed and acceleration control mechanism, coordinating throttle, brake and steering inputs to maintain set parameters.
[0143] Feedback loop: The system uses feedback from multiple sensors to make real-time decisions on whether to accelerate or decelerate to ensure the set headway is maintained.
[0144] Safety & Adjustment: AW_JL (Yaw Angle): Related to the system's monitoring of lateral movement or keeping the vehicle properly aligned, which indirectly affects how the system adjusts speed when turning.
[0145] Ax_L: represents the lateral acceleration and is used to ensure safe driving under dynamic conditions.
[0146] The system dynamically adjusts headway distance in the following ways:
[0147] Relative speed: When the relative speed increases (i.e. the leading vehicle slows down), the system slows down the host vehicle by applying brakes or reducing torque.
[0148] Distance to vehicle ahead: If the distance decreases and falls below a set threshold, the system intervenes to restore a safe headway.
[0149] Leading vehicle speed: If the leading vehicle speeds up or slows down, the host vehicle's speed will be adjusted to match the leading vehicle's speed.
[0150] Adaptive features:
[0151] Dynamic Adjustment: The system continuously monitors traffic conditions and adjusts vehicle speed as needed.
[0152] Switch control: The driver selects different following distances or driving modes (such as sport mode, comfort mode) to adjust the system's braking or acceleration response intensity.
[0153] Emergency Braking: If the vehicle ahead suddenly slows down, the system applies full braking to avoid a collision.
[0154] like Figure 2 - Figure 6 This is the result diagram obtained after simulation:
[0155] from Figure 2 It can be seen from the figure that at 0 seconds, the vehicle speed starts to rise from 0, showing the process of the vehicle accelerating from a stationary state to a cruising speed. At 5 seconds, the vehicle speed gradually approaches the target cruising speed, indicating that the vehicle has reached the set speed of the cruise control during this period; the dotted line represents the target speed of the cruise control, and the solid line represents the actual speed of the vehicle; it can be seen from the figure that the actual speed of the vehicle gradually stabilizes after 5 seconds and is completely consistent with the target cruise speed, indicating that the vehicle control system effectively stabilizes the vehicle speed at the target cruise speed; the vehicle reaches the target cruise speed in a relatively short time (5 seconds), indicating that the cruise control system has a fast response speed. The system can remain stable after reaching the target speed, without obvious overshoot or oscillation; it can be seen from the figure that after reaching the target speed, the vehicle speed remains consistent with the cruise control set speed, and there is no steady-state error. This shows that the cruise control system has good control accuracy.
[0156] from Figure 3 It can be seen that at the start time (time is 0 seconds), the actual acceleration rises rapidly to about 2.5m / s 2 , which is close to the ideal acceleration value, indicating that the vehicle's control system can respond quickly and achieve the expected acceleration target; in the first few seconds, the actual acceleration curve has some small fluctuations, which are caused by errors or noise generated by the control system during the adjustment process. In about 2 seconds, these fluctuations gradually subside and the acceleration stabilizes near the ideal value; at about 5 seconds, the actual acceleration drops rapidly and tends to 0m / s 2, which indicates that the vehicle is close to the target speed, and the control system gradually reduces the acceleration to reach and maintain the target speed; after 5 seconds, the actual acceleration is close to zero and coincides with the ideal acceleration curve, which means that the vehicle has reached the cruising speed and the control system has stopped accelerating to keep the vehicle at a constant speed; overall, the actual acceleration is very close to the ideal acceleration, especially in the initial acceleration stage and the stable stage, which shows that the performance of the control system is good, it can operate according to the expected acceleration curve, and quickly reduce the acceleration to zero when the vehicle reaches the cruising speed.
[0157] from Figure 4 It can be seen from the figure that the solid line represents the speed of the leading vehicle, and the dotted line represents the speed of the following vehicle. The speed of the following vehicle can basically follow the speed of the leading vehicle well in each time period, indicating that the following cruise control system can better follow the speed of the leading vehicle; in each time period (15 seconds, 30 seconds, 60 seconds or so), the speed of the leading vehicle changes, and the speed of the following vehicle is adjusted accordingly. In the acceleration and deceleration stages, the speed of the following vehicle can quickly respond to the speed changes of the leading vehicle, showing good dynamic response ability. When the speed of the leading vehicle remains stable in each time period, the speed of the following vehicle can also quickly reach and maintain the same speed as the leading vehicle. It shows that the system performs well in steady state; at some speed change points in the figure (at the moment when the front vehicle accelerates and decelerates), it is observed that the speed of the following vehicle lags slightly behind the change of the front vehicle speed. This is because the vehicle control system needs a certain amount of time to detect the speed change of the front vehicle and respond. However, this lag is not obvious, and the overall following performance is good; in the stage where the front vehicle speed is stable, the speed curve of the following vehicle is almost the same as the speed curve of the front vehicle, showing good speed stability. This shows that the cruise control system can accurately control the vehicle speed while maintaining the relative distance between the vehicle and the front vehicle, avoiding excessive speed fluctuations.
[0158] from Figure 5It can be seen from the figure that the solid line represents the acceleration of the leading vehicle, and the dotted line represents the acceleration of the following vehicle. The acceleration curve of the following vehicle can generally follow the acceleration changes of the leading vehicle, especially in the relatively stable acceleration or deceleration process, the acceleration of the following vehicle is very close to the acceleration of the leading vehicle; at the mutation point of acceleration or deceleration, it can be observed that the acceleration of the following vehicle lags slightly behind the acceleration of the leading vehicle. This lag is caused by the response time of the control system and the vehicle dynamics characteristics. Despite the lag, the system can adjust and approach the acceleration of the leading vehicle relatively quickly; in some acceleration stages, especially when the acceleration of the leading vehicle changes suddenly, the following vehicle The acceleration of the leading vehicle showed brief oscillations, indicating that the control system introduces some small errors or instabilities when dealing with sudden or discontinuous acceleration changes; at around 60 seconds, the acceleration of the leading vehicle showed a large negative value (i.e. deceleration), and the following vehicle responded quickly, and its acceleration also decreased significantly to follow the leading vehicle, indicating that the following cruise control system can react quickly to sudden deceleration, thereby avoiding the risk of collision; in the stage where the acceleration of the leading vehicle changes steadily (between 10 and 30 seconds), the acceleration of the following vehicle also changes relatively smoothly, without excessive jitter or oscillation, indicating that the system performs well in handling routine driving conditions.
[0159] from Figure 6 It can be seen that: the solid line in the figure represents the actual following distance, and the dotted line represents the ideal following distance. The actual following distance and the ideal following distance are very close in most time periods, indicating that the cruise control system can maintain the set following distance well. In different time periods, the following distance is adjusted as the speed of the vehicle in front changes. For example, at about 15 seconds, 30 seconds and 60 seconds, the following distance changes significantly, which corresponds to the change in the speed of the vehicle in front. The system can adjust the following distance according to the change in the speed of the leading vehicle to maintain a safe distance; at certain moments, especially when the speed of the leading vehicle changes significantly, the actual following distance lags slightly behind the ideal following distance. For example, at around 15 seconds and 60 seconds, the actual following distance is adjusted slightly slower than the ideal following distance. This lag is due to the fact that it takes a certain amount of time for the vehicle to accelerate or decelerate. In the stage where the speed of the leading vehicle remains stable (such as between 30 and 60 seconds), the following distance also remains stable, and the actual following distance almost coincides with the ideal following distance, indicating that the system performs well under stable conditions and can effectively maintain the set distance. In the transition stage of each speed change, although the actual following distance lags behind, it can eventually be adjusted to the ideal following distance, indicating that the system has a certain adjustment ability in the face of dynamic changes. Although there is a slight lag, it can eventually achieve the expected following effect.
[0160] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0161] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.
Claims
1. An adaptive cruise control method with variable headway, comprising the following steps: Step 1, establishing hierarchical control logic of the adaptive cruise control system; Step 2: Switch between the cruise control mode and the following cruise control mode according to the acquired vehicle information; It is characterized by further comprising: Step 3, establishing a safe spacing strategy for variable headway considering the acceleration of the preceding vehicle; Step 4: Based on the safety distance model established in step 3, model predictive control is applied to the multi-objective adaptive cruise control system, and a relaxation factor is introduced to expand the feasible domain solution, converting the optimization objective of the ACC system control algorithm into a quadratic programming problem with constraints.
2. The adaptive cruise control method with variable headway according to claim 1, characterized in that: In step 3, the variable headway safety strategy considering the acceleration of the preceding vehicle is: In t max ≤t0-cv r -ka1, t h =t max ; In t min ≤t0-cv r —ka1≤t max When t h =t0-cv r -ka1; Otherwise, t h =t min ; In the above strategy, k is a constant greater than 0, a1 is the acceleration of the preceding vehicle, and t max ,t min are the maximum and minimum time intervals between two vehicles, t0 is the minimum safe headway between two vehicles, t h is the current workshop time distance, v r is the relative speed of the two vehicles, c is the adjustment coefficient, which is set according to actual needs, where t h satisfy: d des =t h v h +d0 Where: v h is the speed of the vehicle, d0 is the minimum safe distance between the two vehicles, which is 5m, and d des Expected safe distance.
3. The adaptive cruise control method with variable headway according to claim 1, characterized in that: In step 4, the model predictive control is applied to the multi-objective adaptive cruise control system. At each discrete moment, the state variables are updated according to the current state, control input and disturbance, reflecting the vehicle's following control behavior and establishing the vehicle's dynamic model. The state equation in the model is: x(k+1)=Ax(k)+Bu(k)+Gw(k) Where: x(k+1) is the state variable of the system at the k+1th discrete moment in the future, x(k) is the state variable of the system at the kth discrete moment, A is the state transfer matrix, B is the control input matrix, A and B are obtained according to the dynamic characteristics and control target modeling of the system, G is the disturbance matrix, u(k) is the control input of the system, and w(k) is the disturbance of the system.
4. The adaptive cruise control method with variable headway according to claim 3, characterized in that: In the state equation of the vehicle dynamics model established in step 4, the actual vehicle distance, the vehicle speed, the relative vehicle speed, the vehicle acceleration, the vehicle acceleration, and the vehicle acceleration change rate are used as inputs of the state equation. The formula of the system state variables is: x(k)=[Δd(k),v f (k),v r (k),a f (k),j f (k)] T Where: Δd(k) is the actual vehicle spacing at the kth discrete moment, v f (k) is the vehicle speed at the kth discrete moment, v r (k) is the relative speed of the two vehicles at the kth discrete moment, a f (k) is the vehicle acceleration at the kth discrete moment, j f (k) is the acceleration change rate of the vehicle at the kth discrete moment.
5. The adaptive cruise control method with variable headway according to claim 3, characterized in that: In the state equation of the vehicle dynamics model established in step 4, the state matrix is: Where: T s is the system sampling time interval, T g is the inertia time constant; The control input matrix is: The perturbation matrix is:
6. The adaptive cruise control method with variable headway according to claim 5, characterized in that: In step 4, the distance between the two vehicles, the speed of the vehicle, the relative speed between the two vehicles, the acceleration of the vehicle, and the rate of change of the acceleration of the vehicle are compared with the system target state to generate an optimized performance index vector to guide the operation of the adaptive cruise system. The equation for obtaining the optimized performance index vector is: y(k)=[Δd(k),v f (k),v r (k),a f (k),j f (k)] T =Cx(k)-D Where: y(k) is the optimization performance index vector, which is the output quantity to be optimized in the kth discrete time step of the adaptive cruise control system; C is the output matrix, which is used to map the state variables to the optimization performance index; D is the offset vector, which is the expected value of the system and is used to correct the output result.
7. The adaptive cruise control method with variable headway according to claim 6, characterized in that: In step 4, the following hard constraints are set for the equation for obtaining the optimization performance index vector: d≥d des j min ≤j f ≤j max a min ≤a f ≤a max in min Oh, oh. max Where: d is the distance between two vehicles, j f is the acceleration change rate of the vehicle, j min 、j max are the minimum and maximum values of the acceleration change rate of the vehicle, respectively. f is the vehicle acceleration, a min 、a max are the lower and upper limits of the vehicle’s acceleration, u is the control input of the system, and u min 、u max are the lower and upper limits of the control input respectively.
8. The adaptive cruise control method with variable headway according to claim 7, characterized in that: In step 4, the objective function of the model predictive control algorithm weights the comprehensive performance indicators at future moments to obtain the optimal control effect. The formula of the objective function is: Where: Q, R are weighted coefficients, Q = diag (ω Δd ,ω v ,ω u ,ω j ),ω Δd ,ω v ,ω u ,ω j are the weight coefficients of the distance error between the two vehicles, the relative speed weight coefficient of the two vehicles, the acceleration weight coefficient of the vehicle, and the acceleration change rate weight coefficient of the vehicle, i is the discrete time index, J is the objective function value, N p is the length of the prediction time domain, N c To control the length of the time domain, is the output performance index predicted at the i-th moment when the system state is known at the current moment k, y r (k+i|k) is the ideal state that the system will reach at the (k+i)th time in the future when the system state is known at the current time k, and u(k+u) is the control input of the system at the (k+u)th time in the future when the system state is known at the current time k.
9. The adaptive cruise control method with variable headway according to claim 8, characterized in that: In step 4, a relaxation factor is introduced into the hard constraints to selectively soften different constraints and expand the effective range of the constraints. The hard constraints with the relaxation factor are: Where: are the lower and upper relaxation coefficients of the vehicle acceleration, ε1 is the relaxation factor of the vehicle acceleration, are the lower and upper relaxation coefficients of the vehicle speed, ε2 is the relaxation factor of the vehicle speed, are the lower and upper relaxation coefficients of the acceleration change rate of the vehicle, ε3 is the relaxation factor of the acceleration change rate of the vehicle, are the lower and upper relaxation coefficients of the system control input variables, respectively. ε4 is the relaxation factor of the system control input variables. Each relaxation factor, lower and upper relaxation coefficient are obtained through simulation analysis of various vehicle operation scenarios.
10. An adaptive cruise control system with variable headway time, used to implement an adaptive cruise control method with variable headway time as claimed in any one of claims 1 to 9, comprising a vehicle-mounted controller, a sensor module, an actuator module, a communication module and a human-computer interaction unit, wherein the vehicle-mounted controller is connected to the sensor module, the actuator module and the human-computer interaction unit via the communication module, and characterized in that: The on-board controller includes an adaptive learning module, a safety monitoring module and an energy management module, and the adaptive learning module is connected with the safety monitoring module and the energy management module.
Citation Information
Cited By
Multi-target adaptive cruise control method based on fuzzy model predictive control
CN119389198A
Passive safety distance control system based on monocular perception
CN120756442A
A passive safety vehicle distance control system based on monocular perception
CN120756442B
Vehicle cruise parameter determination method and device, vehicle and storage medium
CN120942315A
