基于模糊自适应的智能车驱动与转向协同控制研究

为改善智能车驱动电机调速与舵机转向的协调性,简化调参适配步骤,提出了基于MK60FN1(MK60)芯片的驱动与转向协同控制的模糊自适应控制方案。MK60计算出摄像头拍摄图像中车体与车道中线的位置偏差和角度偏差,根据位置偏差与舵机角度、角度偏差与测量到的车速,采用局部参数优化理论设计模糊自适应控制算法实时调整驱动电机和舵机的可调增益实现协同控制。与驱动、转向分开独立控制的策略相比较,本方案减小了稳态误差,智能车能够更快完成自主循迹,稳定性更好。     

基于LQR算法的车道保持控制策略

介绍一种基于LQR算法的车道保持控制方法.采用TLC与DLC联合预警模型结合驾驶员意图识别对车辆当前的行驶状态进行判断并在偏离时做出报警,当驾驶员未做出反应时车道保持系统对转向系统的输出转角值进行转向控制,帮助驾驶员纠正车辆偏离动作,在Carsim/Simulink环境下进行仿真,对比不同车速下横/航向偏差量与输出方向...     

基于深度强化学习的端到端无人驾驶决策

端到端的驾驶决策是无人驾驶领域的研究热点.本文基于DDPG（Deep Deterministic Policy Gradient）的深度强化学习算法对连续型动作输出的端到端驾驶决策展开研究.首先建立基于DDPG算法的端到端决策控制模型,模型根据连续获取的感知信息（如车辆转角,车辆速度,道路距离等）作为输入状态,输出车辆驾驶动作（加速,刹车,转向）的连续型控制量.然后在TORCS（The Open Racing Car Simulator）平台下不同的行驶环境中进行训练并验证,结果表明该模型可以实现端到端的无人驾驶决策.最后与离散型动作输出的DQN（Deep Q-learning Network）模型进行对比分析,实验结果表明DDPG决策模型具有更优越的决策控制效果.     

Vehicle Stability Enhancement of Four-Wheel-Drive Hybrid Electric Vehicle Using Rear Motor Control

A vehicle stability enhancement control algorithm for a four-wheel-drive hybrid electric vehicle (HEV) is proposed using rear motor driving, regenerative braking control, and electrohydraulic brake (EHB) control. A fuzzy-rule-based control algorithm is proposed, which generates the direct yaw moment to compensate for the errors of the sideslip angle and yaw rate. Performance of the vehicle stability control algorithm is evaluated using ADAMS and MATLAB Simulink cosimulations. HEV chassis elements such as the tires, suspension system, and steering system are modeled to describe the vehicle's dynamic behavior in more detail using ADAMS, whereas HEV power train elements such as the engine, motor, battery, and transmission are modeled using MATLAB Simulink with the control algorithm. It is found from the simulation results that the driving and regenerative braking at the rear motor is able to provide improved stability. In addition, better performance can be achieved by applying the driving and regenerative braking control, as well as EHB control.     

Development of Steering Control System for Autonomous Vehicle Using Geometry‐Based Path Tracking Algorithm

In this paper, a steering control system for the path tracking of autonomous vehicles is described. The steering control system consists of a path tracker and primitive driver. The path tracker generates the desired steering angle by using the look‐ahead distance, vehicle heading, and a lateral offset. A method for applying an autonomous vehicle to path tracking is an advanced pure pursuit method that can reduce cutting corners, which is a weakness of the pure pursuit method. The steering controller controls the steering actuator to follow the desired steering angle. A servo motor is installed to control the steering handle, and it can transmit the steering force using a belt and pulley. We designed a steering controller that is applied to a proportional integral differential controller. However, because of a dead band, the path tracking performance and stability of autonomous vehicles are reduced. To overcome the dead band, a dead band compensator was developed. As a result of the compensator, the path tracking performance and stability are improved.     

An adaptive hierarchical control approach of vehicle handling stability improvement based on Steer-by-Wire Systems

This paper proposes a novel adaptive hierarchical control approach for Steer-by-Wire (SbW) vehicles to improve the handling stability. The high-level stability control scheme contains a variable steering ratio (VSR) strategy based on the adaptive-network-based fuzzy inference system (ANFIS) and an active front steering (AFS) controller designed with the integral sliding mode method by tracking the expected yaw rate, in which the desired front wheel angle is generated to enhance the cornering stability performance. Besides, an adaptive tracking controller (ATC) for the SbW system is designed by using the adaptive sliding mode control method to achieve desired steering performance in the lower level. The proposed adaptive control strategy is validated with different driving circles from ISO standards in simulation tests and hardware-in-the-loop (HiL) experiments. The results demonstrate that the designed control approach improve the vehicle handling stability significantly, even in some extreme driving conditions.     

Visual control of an autonomous vehicle (BART)-thevehicle-following problem

The authors consider the problem of vehicle-following including automatic steering and speed control of an autonomous vehicle following the motion of a lead vehicle. A visual control system for vehicle-following is presented. The system consists of the following modules: image processing, recursive filtering, and a driving command generator. First, the range and heading signal of the lead vehicle are obtained by visually identifying a unique tracking feature on the lead vehicle. Based upon this information, appropriate steering wheel and speed commands for driving are generated, which are then downloaded and executed on a microprocessor controller. The visual control system was tested on BART (Binocular Autonomous Research Team), a testbed vehicle developed at Texas A&M University for autonomous mobility. Successful full-scale test runs have been accomplished for speeds up to 20 mi/h     

Adaptive vehicle skid control

In this paper, adaptive vehicle skid control, for stability and tracking of a vehicle during slippage of its wheels without braking, is addressed. Two adaptive control algorithms are developed: one for the case when no road condition information is available, and one for the case when certain information is known only about the instant type of road surface on which the vehicle is moving. The vehicle control system with an adaptive control law keeps the speed of the vehicle as desired by applying more power to the drive wheels where the additional driving force at the non-skidding wheel will compensate for the loss of the driving force at the skidding wheel, and also arranges the direction of the vehicle motion by changing the steering angle of the two front steering wheels. Stability analysis proves that the vehicle position and velocity errors are both bounded. With additional road surface information available, the adaptive control system guarantees that the vehicle position error and velocity error converge to zero asymptotically even if the road surface parameters are unknown.     

星敏感器高动态下自主星跟踪算法

当飞行器大角速度机动时,采用传统的星跟踪算法来提取星像坐标时,必须选取较大的扫描星图区域,从而增加了区域内包含其它星像部分像元或全部像元的可能,需要多次采用星对角距比较来选取正确的星像坐标,因此,在选取正确的星像坐标时增加了误匹配的可能。为此,文中提出一种星敏感器高动态下自主星跟踪算法,首先根据前邻时刻的瞬时姿态来预测下一时刻的输出姿态,再利用预测姿态预测当前时刻恒星在下一时刻的星像坐标,最后扫描在以预测的星像坐标为中心的星图范围内提取实际的恒星星像坐标。这样克服了采用传统星跟踪算法带来的数据更新率低、可能误匹配高甚至不能提取正确地星像坐标的缺点。最后,采用该方法进行了仿真验证以及外场观星试验。     

Yaw stability control of a steer-by-wire equipped vehicle via active front wheel steering

A novel yaw stability control algorithm with active front wheel steering control of a vehicle equipped with a steer-by-wire system is presented in this paper. The proposed algorithm achieves the decoupling of the lateral and yaw motion of a vehicle and the vehicle’s yaw damping simultaneously by the feedback of both yaw rate and front steering angle. A trade-off is then made between the robust decoupling and yaw rate damping through the adjustment of the feedback gains with respect to vehicle speed. With this trade-off, the gain scheduled steering controller provides the desired yaw rate damping while keeping the yaw-lateral motion decoupled. The robustness of the yaw-lateral decoupling is achievable when arbitrary yaw damping is not required. The proposed control system is implemented on a steer-by-wire vehicle, and the experimental results are presented illustrating the benefits.     

Toyota electronic modulated air suspension system for the 1986Soarer

An electronically controlled air-suspension system is described that uses sensors to detect vehicle speed, throttle position, steering angle, height, and other factors related to vehicle attitude. Its electronic control unit (ECU) drives the actuators to control spring rate, damping force, and height. As a result, the system reduces changes in vehicle attitude such as rolls, dives, squats, etc., and also provides stable maneuverability in high-speed cruising and improved drive characteristics on rough roads. A newly developed single-chip microcomputer is used in the ECU. The actuators for the sporting rate and damping force use DC motors. The system also allows drivers to select preferred suspension characteristics from four modes, and displays on a CRT the suspension status     

A Novel Dynamic Obstacle Avoidance Algorithm Based on Collision Time Histogram

Robot path planning in uncertain dynamic environment is a hot issue in the field of Unmanned ground vehicle (UGV). Starting from the practical demands of UGV, we propose a novel dynamic obstacle avoidance al-gorithm based on Collision time histogram (CTH). Given current steering angle, an effective collision check model, which is called Collision check circles (CCC), is firstly cal-culated. The local environment information is then com-bined with CCC to generate the proposed CTH. The non-holonomic nature of the vehicle is embedded in this pro-cess. Finally, the proposed algorithm calculates the execut-ing steering angle by considering both the CTH and the target point. Extensive experiments and comparisons are conducted to evaluate the performance of the proposed al-gorithm. Simulation experiments are firstly conducted to verify its feasibility. Furthermore, real-world experiment is conducted to verify its effectiveness. Experimental results demonstrate the practical value of the proposed algorithm.     

Comparison between braking and steering yaw moment controllers considering ABS control aspects

Two yaw motion control systems that improve a vehicle lateral stability are proposed in this study: a braking yaw motion controller (BYMC) and a steering yaw motion controller (SYMC). A BYMC controls the braking pressure of the rear inner wheel, while a SYMC steers the rear wheels to allow the yaw rate to track the reference yaw rate. A 15 degree-of-freedom vehicle model, simplified steering system model, and driver model are used to evaluate the proposed BYMC and SYMC. A robust anti-lock braking system (ABS) controller is also designed and developed. The performance of the BYMC and SYMC are evaluated under various road conditions and driving inputs. They reduce the slip angle when braking and steering inputs are applied simultaneously, thereby increasing the controllability and stability of the vehicle on slippery roads. The SYMC performs better than the BYMC because the SYMC vehicle has four-wheel steering. However, both the BYMC and SYMC vehicles show improved performance during lane-change maneuvers.     

Motor control and torque coordination of an electric vehicle actuated by two in-wheel motors

In this research, an electric vehicle actuated by two in-wheel DC motors is developed. By properly coordinating the motor torques, both drive-by-wire and electrical steering can be achieved. Two critical issues respectively related to the design of motor controllers and the coordination of the two motor torques under control saturation are investigated in this study. Firstly, as for the in-wheel motors that are used for driving and steering simultaneously, their operation covers a wider dynamic range that forward acceleration (deceleration), and reverse acceleration (deceleration) may occur alternately. To perform driving and steering smoothly and efficiently, each motor should be switched to an appropriate mode to generate the torque demanded. Secondly, during the high-speed maneuvering, the high back-emf voltage in the motor coil substantially reduces the motor’s torque generating capability. Since the electrical steering depends on the differential torque of two wheels, when electrical steering is demanded in this case, torque/current saturation may occur in either one of the motors and the electrical steering performance could be seriously degraded. To address these issues, controllers of two levels are proposed. For the low-level controller (the motor controller), it operates the motor automatically in an appropriate mode for performance and efficiency consideration. An input transformation is introduced to cancel the nonlinearity in current dynamics so as to control the motor torque easily and precisely regardless of mode switching. For the high-level controller (the torque coordination controller), besides generating reference commands to the low-level controllers, during control saturation it can also properly re-distributes control signals to maintain consistent steering performance and provides compensation for integrator windup. The control system is implemented and the performance is experimentally and numerically validated.     

汽车传动系统熄火工况减振控制算法研究

车辆安装双质量飞轮(DMF)可改善正常行驶过程中舒适性，但会加剧汽车在熄火过程中传动系统的振动响应。针对该问题，以某型汽车为对象，基于安装双质量飞轮后汽车传动系统的特性，提出了相应的减振控制算法并进行了试验验证。通过不同试验方案及试验结果对比，提出了在汽车熄火时刻，通过ECU控制逻辑关闭进气节流(TVA)阀和废气再循环(EGR)阀，并适当延迟断油时刻的控制算法。该算法使传动系统穿越共振转速区的时间缩短了50%，大幅改善了汽车传动系统的熄火振动。     

Autonomous driving in the uncertain traffic—— a deep reinforcement learning approach

Driving in the complex traffic safely and efficiently is a difficult task for autonomous vehicle because of the stochastic characteristics of engaged human drivers. Deep reinforcement learning (DRL), which combines the abstract representation capability of deep learning (DL) and the optimal decision making and control capability of reinforcement learning (RL), is a good approach to address this problem. Traffic environment is built up by combining intelligent driver model (IDM) and lane-change model as behavioral model for vehicles. To increase the stochastic of the established traffic environment, tricks such as defining a speed distribution with cutoff for traffic cars and using various politeness factors to represent distinguished lane-change style, are taken. For training an artificial agent to achieve successful strategies that lead to the greatest long-term rewards and sophisticated maneuver, deep deterministic policy gradient (DDPG) algorithm is deployed for learning. Reward function is designed to get a trade-off between the vehicle speed, stability and driving safety. Results show that the proposed approach can achieve good autonomous maneuvering in a scenario of complex traffic behavior through interaction with the environment.     

Hierarchical control strategies for multi-mode steering system of emergency rescue vehicle

It is difficult for the traditional emergency rescue vehicles (ERVs) to pass through narrow and complicated areas quickly, which leads to the ERVs missing the best time to rescue disasters seriously. How to improve the trafficability and mobility of vehicles effectively in narrow and complex areas has become an urgent technical demand for the ERVs. In this context, this paper proposes a multi-mode steering system to realize four steering modes of the ERVs. A fire rescue prototype vehicle is developed, and its multi-mode steering system is designed in detail. The hierarchical control strategies of the multi-mode steering system consist of the upper controller and the lower controller. The upper controller is responsible for assigning the steering angles of four wheels of the ERVs based on the Ackerman principle. The lower controller is used to control the ERVs to turn four wheels independently based on the electro-hydraulic fractional order PID (FOPID) control strategy, and then the parameters of the FOPID controller are optimized by the adaptive clonal selection algorithm. The multi-mode steering system proposed was tested on the homemade fire rescue prototype vehicle. The numerical simulations and experiments were conducted to verify the effectiveness of the proposed multi-mode steering system.     

基于二次型约束的鲁棒自适应波束形成算法

针对期望信号方向向量存在偏差会导致自适应波束形成算法的性能急剧下降这一问题,该文提出了一种基于二次型约束的鲁棒自适应波束形成算法。通过对期望信号波达方向附近范围内的方向向量的误差模值进行约束,来提高算法的鲁棒性,并在此约束条件下对权重向量进行优化求解,且优化解中的参数能够准确求出。该算法可有效地控制波束主瓣区域内信号的畸变,并能够抑制方向向量偏差所带来的影响,提高了系统的鲁棒性,同时使干扰和噪声的功率输出最小,保证了对干扰信号的抑制能力,改善了阵列输出的信干噪比,使其更接近最优值。仿真结果验证了所提算法的有效性与优越性。     

智能寻迹模型车的控制策略及算法研究

在输入信号及硬件有限的条件下,运用一种有效寻迹、转向与速度控制算法,对于提高智能车的运动性能,有着重要的作用.为提高智能车的性能,对控制算法进行了研究.针对传统的路径离散识别算法只能获得少而离散化路径信息的问题,提出了采用连续化路径识别算法对路径信息采集;针对制约智能车快速寻迹的转向及速度问题,提出了采用优化的PID控制算法对智能车的舵机和电机进行控制.实验结果表明,与传统方法相比,采用连续的信号、基于反馈控制的PID控制算法,智能车的快速性、灵敏性、稳定性明显改善,从而验证了算法的可行性.