结合状态机和动态目标路径的无人驾驶决策仿真

目的 决策系统是无人驾驶技术的核心研究之一。已有决策系统存在逻辑不合理、计算效率低、应用场景局限等问题,因此提出一种动态环境下无人驾驶路径决策仿真。方法 首先,基于规则模型构建适于无人驾驶决策系统的交通有限状态机;其次,针对交通动态特征,提出基于统计模型的动态目标路径算法计算状态迁移风险;最后,将交通状态机和动态目标路径算法有机结合,设计出一种基于有限状态机的无人驾驶动态目标路径模型,适用于交叉口冲突避免和三车道换道行为。将全速度差连续跟驰模型运用到换道规则中,并基于冲突时间提出动态临界跟车距离。结果 为验证模型的有效性和高效性,对交通环境进行虚拟现实建模,模拟交叉口通行和三车道换道行为,分析文中模型对车流量和换道率的影响。实验结果显示,在交叉口通行时,自主车辆不仅可以检测冲突还可以根据风险评估结果执行安全合理的决策。三车道换道时,自主车辆既可以实现紧急让道,也可以通过执行换道达成自身驾驶期望。通过将实测数据和其他两种方法对比,当车流密度在0.20.5时,本文模型的平均速度最高分别提高32 km/h和22 km/h。当车流密度不超过0.65时,本文模型的换道成功率最高分别提升37%和25%。结论 实验结果说明本文方法不仅可以在动态城区环境下提高决策安全性和正确性,还可以提高车流量饱和度,缓解交通堵塞。     

Trajectory planning and tracking for autonomous overtaking: State-of-the-art and future prospects

Trajectory planning and trajectory tracking constitute two important functions of an autonomous overtaking system and a variety of strategies have been proposed in the literature for both functionalities. However, uncertainties in environment perception using the current generation of sensors has resulted in most proposed methods being applicable only during low-speed overtaking. In this paper, trajectory planning and trajectory tracking approaches for autonomous overtaking systems are reviewed. The trajectory planning techniques are compared based on aspects such as real-time implementation, computational requirements, and feasibility in real-world scenarios. This review shows that two important aspects of trajectory planning for high-speed overtaking are: (i) inclusion of vehicle dynamics and environmental constraints and (ii) accurate knowledge of the environment and surrounding obstacles. The review of trajectory tracking controllers for high-speed driving is based on different categories of control algorithms where their respective advantages and disadvantages are analysed. This study shows that while advanced control methods improve tracking performance, in most cases the results are valid only within well-regulated conditions. Therefore, existing autonomous overtaking solutions assume precise knowledge of surrounding environment which is not representative of real-world driving. The paper also discusses how in a connected driving environment, vehicles can access additional information that can expand their perception. Hence, the potential of cooperative information sharing for aiding autonomous high-speed overtaking manoeuvre is identified as a possible solution.     

基于自适应MPC算法的轨迹跟踪控制研究

为了保证智能车辆在低附着且变速条件下跟踪控制的精确性和稳定性,提出一种基于自适应模型预测控制（MPC）的轨迹跟踪控制算法。针对低附着条件下轨迹跟踪存在行驶稳定性较差的问题,对车辆动力学模型添加侧偏角软约束,分别设计有无添加侧偏角约束的MPC控制器。仿真结果表明,添加侧偏角约束后MPC控制器性能更优,车辆行驶稳定性得到有效提高。在此基础上,又提出了一种自适应的轨迹跟踪控制策略,能够根据车辆速度的变化,实时产生预测时域[(Hp)],分别设计自适应的MPC控制器与4组定值[Hp]的MPC控制器。仿真结果表明,基于自适应模型预测控制的轨迹跟踪控制算法在提高低附着且变速条件下智能车辆轨迹跟踪控制的精度和稳定性方面具有一定的有效性和先进性。     

自动驾驶车辆在无信号交叉口右转驾驶决策技术研究

利用深度强化学习（deep reinforcement learning,DRL）技术实现自动驾驶决策已成为国内外研究热点,现有研究中的车辆交通流缺乏随机性与真实性,同时自动驾驶车辆在环境中的有效探索具有局限性。因此利用TD3算法进行自动驾驶车辆在无信号交叉口下的右转驾驶决策研究,首先在Carla仿真平台中开发无信号交叉口的训练与测试场景,并添加交通流管理功能,提高系统训练和测试随机性。其次,为了提高自动驾驶车辆的探索性,对TD3算法中的Actor网络进行改进,为目标动作添加OU噪声。最后使用通行成功率和平均通行时间评估指标评价自动驾驶行为决策。结果表明,在不同交通流场景下,改进后的TD3算法通行成功率与基于DDPG算法控制的车辆相比平均提升6.2%,与基于规则的AEB模型相比平均提升23%。改进后的TD3算法不仅能够探索更多可能,而且其通行决策表现更加突出。     

基于改进蚁群优化算法的自动驾驶多车协同运动规划

当前面向多辆自动驾驶汽车的协同运动规划方法能有效保证运行车辆与障碍物及其他车辆之间避免发生碰撞并保持安全距离,但车辆间的在线协同与规划能力仍有待提升。为实现多辆自动驾驶汽车在运动过程中的协同控制,提出一种基于改进蚁群优化算法的多车在线协同规划方法。以空间协同与轨迹代价为优化目标,构造多目标优化函数,确保了多车行驶过程中的协同安全性与轨迹平滑性。将多目标优化函数引入蚁群优化算法的信息素更新过程中,根据自动驾驶车辆数量产生多个种群,使得种群之间相互独立的同时为每辆自动驾驶汽车规划可行路线。最终对蚁群优化算法中的挥发因子进行自适应调整,提升了算法全局搜索能力及收敛速度。实验结果表明,该方法能使多辆自动驾驶汽车在运动过程中保持协同控制并规划出无碰撞路线,相比于基于人工势场和模型预测的协同驾驶方法在复杂道路场景下车辆间的协同效果更好且适应性更强。     

适用于路径跟踪控制的自适应MPC算法研究

为提高自动驾驶车辆在不同工况下的路径跟踪精度和行驶稳定性,基于车辆的单轨模型和模型预测控制（MPC）理论,提出一种依据跟踪偏差和道路曲率自适应调整成本函数权重系数的路径跟踪控制算法。该算法主要是通过模糊控制理论动态优化传统MPC路径跟踪控制器中权重系数矩阵,使得当车辆与参考路径偏差比较大时,能够快速减小跟踪偏差,保证车辆行驶的安全性;当路径跟踪偏差比较小,且参考路径曲率比较小时,使得系统更加侧重行驶稳定性的要求。为验证所设计的路径跟踪控制器的性能,搭建CarSim/Simulink联合仿真模型,在联合仿真过程中,基于权重系数自适应的MPC路径跟踪控制器与基于权重系数为常量的MPC路径跟踪控制器相比,路径跟踪精度和车辆的行驶稳定性均得到了提高。     

Interaction-Aware Cut-In Trajectory Prediction and Risk Assessment in Mixed Traffic

Accurately predicting the trajectories of surrounding vehicles and assessing the collision risks are essential to avoid side and rear-end collisions caused by cut-in. To improve the safety of autonomous vehicles in the mixed traffic, this study proposes a cut-in prediction and risk assessment method with considering the interactions of multiple traffic participants. The integration of the support vector machine and Gaussian mixture model (SVM-GMM) is developed to simultaneously predict cut-in behavior and trajectory. The dimension of the input features is reduced through Chebyshev fitting to improve the training efficiency as well as the online inference performance. Based on the predicted trajectory of the cut-in vehicle and the responsive actions of the autonomous vehicles, two risk measurements are introduced to formulate the comprehensive interaction risk through the combination of Sigmoid function and Softmax function. Finally, the comparative analysis is performed to validate the proposed method using the naturalistic driving data. The results show that the proposed method can predict the trajectory with higher precision and effectively evaluate the risk level of a cut-in maneuver compared to the methods without considering interaction.      

无人驾驶车路径跟踪控制研究

研究被控对象无人驾驶车,基于预瞄控制思想,设计一种无人驾驶车路径跟踪控制器,将控制器分为预瞄控制和补偿控制两部分,预瞄控制模拟驾驶员在驾驶车辆过程中对前方的道路环境信息进行预瞄,根据道路曲率程度决定方向盘转向,补偿控制是对车辆遇到干扰偏离原车道的纠正。仿真实验结果表明,该控制器能够保证无人驾驶车准确跟踪各种参考路径,且具有较好的鲁棒性。     

基于多目标协同演化算法的大规模自动驾驶策略

目前无人驾驶技术领域的研究重点主要集中在单车层面的感知、决策与控制,而缺少对多车 之间交互及博弈的研究,因此无法有效降低交通系统整体事故率并提升通行效率。该文提出一种基于 合作博弈理论的大规模自动驾驶策略涌现方法。通过建立面向网联汽车、多目标优化决策的合作博弈 演化平台,并构造了一种网格道路模型和车辆运动学模型,使得系统中各车辆之间以近邻博弈的方式 进行交互;同时系统采用分布式算法并具有间接交互的特点,最终模型计算复杂度与模拟车辆规模呈 线性关系。实验结果表明,最佳策略涌现后,事故率和平均速度均取得明显改善,其中事故率降低了 90%,模型计算速度提升了 30%。该方法可应用于包含数百万辆自动驾驶汽车的城市级智能交通规划 系统中。     

Design and evaluation of a model predictive vehicle control algorithm for automated driving using a vehicle traffic simulator

This paper describes the design and evaluation of a model predictive control algorithm for automated driving on a motorway using a vehicle traffic simulator. For the development of a highly automated driving control algorithm, motion planning is necessary to satisfy driving condition in various road traffic situations. There are two key issues in motion planning of automated driving vehicles. One of the key issues is how to handle potentially dangerous situations that could occur in order to guarantee the safety of vehicles. The second key issue is how to guarantee the disturbance rejection of the controller under model uncertainties and external disturbances. To improve safety with respect to the future behaviors of subject vehicles, not the current states but rather the predicted behaviors of surrounding vehicles should be considered. The desired driving mode and a safe driving envelope are determined based on the probabilistic prediction of surrounding vehicles behaviors over a finite prediction horizon. To obtain the desired steering angle and longitudinal acceleration for maintaining the subject vehicle in the safe driving envelope during a finite prediction horizon, a motion planning controller is designed based on an model predictive control (MPC) approach. The developed control algorithm has been successfully implemented on a vehicle electronic control unit (ECU). The proposed control algorithm has been evaluated on a real-time vehicle traffic simulator. The throttle, brake, and steering control inputs and the controlled vehicle behavior have been compared to those of manual driving.     

基于改进RRT^(*)与行驶轨迹优化的智能汽车运动规划EI北大核心CSCD

针对传统快速扩展随机树算法(Rapidly-exploring random tree,RRT)搜索较慢、规划路径曲折、平顺性差等问题,提出了一种结合改进RRT^(*)与贝塞尔曲线控制点优化的智能车辆运动规划方法.该方法通过在给定概率分布下采样,结合基于方向相似性的多步扩展与路径简化,使用贝塞尔曲线拟合生成规划问题初始解,最后使用序列二次规划优化曲线控制点,从而在动态障碍物环境中生成兼具安全性与驾驶舒适性的车辆行驶轨迹.在仿真实验中将本文算法与常规RRT及曲线拟合方法进行了比较,结果显示本文算法在搜索速度、平顺性、安全性等方面有较大提升.     

Yaw Moment Control Strategy for Four Wheel Side Driven EV

When four wheel side driven EV travals in steering or changes lanes in high speed, the vehicle is easy to side-slip or flick due to the difference of wheel hub motor and a direct effect of vehicle nonlinear factors on vehicle yaw motion, which would affect vehicle handling and stability seriously. To solve this problem, a joint control strategy, combined with the linear programming algorithm and improved sliding mode algorithm, which combines the exponential reaching law and saturation function was proposed. Firstly, the vehicle dynamics model and the reference model according with the structure and driving characteristics of four wheel side driven EV were set up. Then, introduced the basic method of the improved sliding mode variable structure control and complete the sliding mode variable structure controller design basic on vehicle sideslip angle and yaw velocity.The controller accomplish optimal allocation of vehicle braking force through a linear programming algorithm, according to yaw moment produced by the vehicle motion state. Single lane driving simulation results show that the proposed control strategy can not only control vehicle sideslip angle and yaw velocity well, but also accomplish good controlling of the vehicle yaw moment, so as to significantly improve the handling and stability of vehicle.     

电动车驾驶机器人控制器参数自学习方法研究

针对人工驾驶和现有的机械式驾驶机器人在电动车续驶里程试验中存在成本高、耗时长和错误率高的问题,利用电动车结构和控制上的独特性,依托自行设计的电动车转毂驾驶机器人,采用电信号完成对车辆的控制。为了提高系统适应性,采用非线性最小二乘法实现电动车模型参数的在线辨识;并基于粒子群算法对车辆PID控制器参数进行在线整定,从而完成对任意设定工况速度曲线的跟随。实车试验表明,提出的方法能实现加速踏板的平滑控制,且控制重复性高,完全可以代替驾驶员进行电动车续驶里程试验。     

基于深度强化学习的无信号灯交叉路口车辆控制

利用深度强化学习技术实现无信号灯交叉路口车辆控制是智能交通领域的研究热点。现有研究存在无法适应自动驾驶车辆数量动态变化、训练收敛慢、训练结果只能达到局部最优等问题。文中研究在无信号灯交叉路口,自动驾驶车辆如何利用分布式深度强化方法来提升路口的通行效率。首先,提出了一种高效的奖励函数,将分布式强化学习算法应用到无信号灯交叉路口场景中,使得车辆即使无法获取整个交叉路口的状态信息,只依赖局部信息也能有效提升交叉路口的通行效率。然后,针对开放交叉路口场景中强化学习方法训练效率低的问题,使用了迁移学习的方法,将封闭的8字型场景中训练好的策略作为暖启动,在无信号灯交叉路口场景继续训练,提升了训练效率。最后,提出了一种可以适应所有自动驾驶车辆比例的策略,此策略在任意比例自动驾驶车辆的场景中均可提升交叉路口的通行效率。在仿真平台Flow上对TD3强化学习算法进行了验证,实验结果表明,改进后的算法训练收敛快,能适应自动驾驶车辆比例的动态变化,能有效提升路口的通行效率。     

基于模糊神经网络水下机器人直接自适应控制

提出了基于广义动态模糊神经网络的水下机器人直接自适应控制方法, 该控制方法既不需要预先知道模糊神经结构, 也不需要预先的训练阶段, 完全通过在线自适应学习算法构建水下机器人的逆动力学模型. 首先, 本文提出了基于这种网络结构的水下机器人直接自适应控制器, 然后, 利用 Lyapunov 稳定理论, 证明了基于该控制器的水下机器人控制系统闭环稳定性, 最后, 采用某水下机器人模型仿真验证了该控制方法的有效性.     

Global stability analysis of fuzzy path tracking using frequency response

This paper studies the stability of fuzzy path tracking of autonomous vehicles. This problem lies in the generation of the steering commands for a vehicle to follow a given path autonomously. In this control loop, both the plant and the fuzzy controller are nonlinear. Due to this nonlinearity, complex behavioral phenomena can occur, giving rise to the loss of global stability. The extension of conventional frequency response methods for the stability analysis of the nonlinear fuzzy path-tracking control loop is proposed. Simulation experiments show the validity of the proposed method in three different cases: stable origin and unstable limit cycle, delay-induced Hopf bifurcation, and delay-induced unstable limit cycle.     

基于交互车辆轨迹预测的自动驾驶车辆轨迹规划

针对城市道路等复杂行车场景,提出了一种基于交互车辆轨迹预测的自动驾驶车辆轨迹规划方法,将高维度的轨迹规划解耦为低维度的路径规划和速度规划;首先,采用五次多项式曲线和碰撞剩余时间规划车辆行驶路径;其次,在社会生成对抗网络Social-GAN的基础上结合车辆空间影响和注意力机制对交互车辆进行轨迹预测;然后,结合主车规划路径、交互车辆预测轨迹及碰撞判定模型得到主车S-T图,采用动态规划和数值优化方法求解S-T图,从而得到满足车辆动力学约束的安全、舒适最优速度曲线;最后,搭建PreScan-CarSim-Matlab&Simulink-Python联合仿真模型进行实验验证。仿真结果表明,提出的轨迹规划方法能够在对交互车辆有效避撞的前提下,保证车辆行驶的舒适性和高效性。     

自主车辆安全系数估计与T形路口避碰规划

针对自主车辆T形路口协作问题,通过测量车辆速度和预碰点距离,提出安全系数估计方法,结合人工势场基本思想,实现车辆路口避碰,提高路口协作效率.首先以计算得到的安全系数为依据,评价驶入T形路口两辆自主车各自的安全程度,并利用人工势场产生的推拉作用估计协作自主车辆的期望控制力和速度.然后将估计的期望车速与反馈的实际车速形成偏差,利用增量型数字PI控制器实现自主车纵向车速的准确控制.最后以一定的策略完成两辆自主车的并线协作.仿真结果验证了基于安全系数估计的自主车辆T形路口协作避碰的可行性与有效性.     

基于动态规划不同优化目标的HEV转矩分配策略对比研究

双动力源的结构模式使得混合动力汽车相对于传统汽车拥有更高的燃油经济性,同时也给混合动力汽车整车控制器的设计提出了更高的要求。本文采用动态规划算法,分别以油耗最低同时电池SOC波动尽可能小、以及整车效率最高为目标,对混合动力汽车在NEDC循环工况下的最优转矩分配进行求解。并将两种转矩分配结果进行对比分析,得出选择不同优化目标对控制效果的影响以及SOC参数选择的标准,为制定更加高效的控制规则提供了理论依据。     

自动驾驶环境下交叉口车辆路径规划与最优控制模型

自动驾驶环境下的交叉口基于车车/车路之间的双向信息交互, 能保障自动驾驶车辆相互穿插与协作地通过交叉口, 而无需信号灯控制. 因此, 如何设计高效的面向自动驾驶车辆通行的交叉口管控模型, 已成为研究的热点. 已有研究在建模时, 均基于自动驾驶车辆在交叉口内部的行驶路径已知并作为模型输入, 且大多对交叉口内部的冲突点进行简化. 本文首先将交叉口空间离散化处理, 考虑车辆的实际尺寸并面向非常规交叉口, 使用椭圆曲线建立转弯车辆行驶路径的精确轨迹方程, 再通过外边界投影降维法建立轨迹方程和交叉口空间的映射关系. 建立了基于混合整数线性规划(Mixed integer linear programming, MILP)的自动驾驶交叉口管控模型, 以交叉口总延误最小为控制目标, 同时优化车辆在交叉口的最佳行驶路径和驶入时刻, 使用AMPL (A mathematical programming language)对模型进行编译并使用CPLEX求解器求解. 与经典感应控制和先到先服务模型进行对比, 结果表明, 本文所提出模型能对车辆进入交叉口的时刻和行驶路径进行双重优化, 显著降低自动驾驶车辆通过交叉口的车均延误, 提高交叉口空间的利用效率.