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。     

A geometrical approach to the motion planning problem for a submerged rigid body

The main focus of this article is the motion planning problem for a deeply submerged rigid body. The equations of motion are formulated and presented by use of the framework of differential geometry and these equations incorporate external dissipative and restoring forces. We consider a kinematic reduction of the affine connection control system for the rigid body submerged in an ideal fluid, and present an extension of this reduction to the forced affine connection control system for the rigid body submerged in a viscous fluid. The motion planning strategy is based on kinematic motions; the integral curves of rank one kinematic reductions. This method is of particular interest to autonomous underwater vehicles which cannot directly control all six degrees of freedom (such as torpedo-shaped autonomous underwater vehicles) or in case of actuator failure (i.e. under-actuated scenario). A practical example is included to illustrate our technique.     

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。     

城市交叉口车辆速度与交通信号协同优化控制

为了降低城市交通中的行车延误与燃油消耗,针对人类驾驶车辆与自动驾驶车辆混合交通环境,提出一种基于交通信息物理系统(TCPS)的车辆速度与交通信号协同优化控制方法.首先,综合考虑路口交通信号、人类驾驶车辆、自动驾驶车辆三者之间的相互影响,设计一种适用于自动驾驶车辆与人类驾驶车辆混合组队特性的过路口速度规划模型;其次,针对车辆速度规划单一应用时的局限性,即无法减少车辆路口通行延误且易出现无解情况,提出一种双目标协同优化模型,能够综合考虑车辆速度规划与路口交通信号控制,同时降低车辆燃油消耗与路口平均延误.由于双目标优化问题求解的复杂性,设计一种遗传算法-粒子群算法混合求解策略.基于SUMO的仿真实验验证了所提出方法的有效性.     

自主车的运动仿真

在自主车的运动路径规划中,局部路径规划特别重要,而且是自主车的一项关键技术。该文提出了将自主式多智能体的任务和反应性行为模型嵌入到离散事件系统框架中作局部路径规划的方法,此方法克服了势场法（包括早期的虚力场法）的缺陷,为确保自主车运动路径规划的可靠性和合理性,该文就局部路径规划对自主车作运动仿真。     

Receding horizon maneuver generation for automated highway driving

This paper focuses on the problem of decision-making and control in an autonomous driving application for highways. By considering the decision-making and control problem as an obstacle avoidance path planning problem, the paper proposes a novel approach to path planning, which exploits the structured environment of one-way roads. As such, the obstacle avoidance path planning problem is formulated as a convex optimization problem within a receding horizon control framework, as the minimization of the deviation from a desired velocity and lane, subject to a set of constraints introduced to avoid collision with surrounding vehicles, stay within the road boundaries, and abide the physical limitations of the vehicle dynamics. The ability of the proposed approach to generate appropriate traffic dependent maneuvers is demonstrated in simulations concerning traffic scenarios on a two-lane, one-way road with one and two surrounding vehicles.     

General fight rule-based trajectory planning for pairwise collision avoidance in a known environment

This paper presents a general flight rule-based autonomous trajectory planning scheme for two aerial vehicles to avoid obstacles and collisions in known environments in low-altitude airspace for general aviation. Flight rules in low-altitude airspace are first introduced based on the general flight rules in US, UK and China, and then the suitable flight rules are embedded into the trajectory planning algorithm. It is supposed that the flight parameters, such as positions and velocities, are all available to the aerial vehicles involved in the possible conflict. Then the trajectory of each aerial vehicle is calculated by optimizing an objective function, such as distance and fuel consumption, with the constraints corresponding to the airspace traffic rules. The optimization problem is solved by receding horizon control (RHC) based mixed integer linear programming (MILP). Compared with other collision avoidance algorithms, the proposed algorithm can be adapted to plan the autonomous trajectory to avoid pairwise collision and obstacles as proposed general flight rules. Simulations show the feasibility of the proposed scheme.     

多圆碟形水下滑翔机的双层协调三维路径规划

本文研究了欠驱动圆碟形水下滑翔机集群在海流干扰和水下碍航物影响下的三维路径规划问题. 具体地: 第一, 根据圆碟形水下滑翔机的航行特点, 建立了相应的航行时间模型, 设计了三维路径规划的优化目标; 第二, 提 出了一种基于双层协调的多水下滑翔机三维路径规划结构, 采用基于三维离散空间的全局路径规划和基于人工势 场法的局部路径规划, 避免了滑翔机与碍航物以及不同优先级的滑翔机之间发生碰撞; 第三, 基于双层协调路径规 划结构, 采用基于量子行为的自适应粒子群优化方法完成了时间最优目标下多圆碟形水下滑翔机的三维路径规划. 仿真结果验证了所提多圆碟形水下滑翔机三维路径规划方法的有效性.     

基于MCPDDPG的智能车辆路径规划方法及应用

针对智能车路径规划过程中常存在动态环境感知预估不足的问题,使用基于蒙特卡罗深度策略梯度学习(Monte Carlo prediction deep deterministic policy gradient, MCPDDPG)的智能车辆路径规划方法,设计一种基于环境感知预测、行为决策和控制序列生成的框架,实现实时的决策和规划,并输出连续的车辆控制序列.首先,利用序贯蒙特卡罗预估他车行为状态量;然后,设计基于强化Q学习的行为决策方法,使智能车辆实时预知碰撞风险,采取合理的规避策略;最后,构建深度策略梯度学习网络框架,获取智能车辆规划路径的最优轨迹序列.实验结果表明,所提方法能够缓解环境感知的预估不足问题,提升智能车辆行为决策的快速性,保障路径规划的主动安全,并输出连续的轨迹序列,为智能车辆导航控制提供前提.     

基于滚动时域优化的无人飞行器轨迹规划

给出了寻求无人飞行器的最优轨迹的一种方法,其问题描述为使飞行器从初始状态飞行到目标状态,同时避免撞到障碍物。基于混合整数规划的滚动时域优化方法用来求解飞行器的轨迹规划问题。给出的仿真结果显示此方法的有效性以及在复杂环境下的可实时计算性。     

Autonomous driving at the handling limit using residual reinforcement learning

While driving a vehicle safely at its handling limit is essential in autonomous vehicles in Level 5 autonomy, it is a very challenging task for current conventional methods. Therefore, this study proposes a novel controller of trajectory planning and motion control for autonomous driving through manifold corners at the handling limit to improve the speed and shorten the lap time of the vehicle. The proposed controller innovatively combines the advantages of conventional model-based control algorithm, model-free reinforcement learning algorithm, and prior expert knowledge, to improve the training efficiency for autonomous driving in extreme conditions. The reward shaping of this algorithm refers to the procedure and experience of race training of professional drivers in real time. After training on track maps that exhibit different levels of difficulty, the proposed controller implemented a superior strategy compared to the original reference trajectory, and can to other tougher maps based on the basic driving knowledge learned from the simpler map, which verifies its superiority and extensibility. We believe this technology can be further applied to daily life to expand the application scenarios and maneuvering envelopes of autonomous vehicles.     

Heuristic based evolution for the coordination of autonomous vehicles in the absence of speed lanes

The current state of the art in the planning and coordination of autonomous vehicles is based upon the presence of speed lanes. In a traffic scenario where there is a large diversity between vehicles the removal of speed lanes can generate a significantly higher traffic bandwidth. Vehicle navigation in such unorganized traffic is considered. An evolutionary based trajectory planning technique has the advantages of making driving efficient and safe, however it also has to surpass the hurdle of computational cost. In this paper, we propose a real time genetic algorithm with Bezier curves for trajectory planning. The main contribution is the integration of vehicle following and overtaking behaviour for general traffic as heuristics for the coordination between vehicles. The resultant coordination strategy is fast and near-optimal. As the vehicles move, uncertainties may arise which are constantly adapted to, and may even lead to either the cancellation of an overtaking procedure or the initiation of one. Higher level planning is performed by Dijkstra's algorithm which indicates the route to be followed by the vehicle in a road network. Re-planning is carried out when a road blockage or obstacle is detected. Experimental results confirm the success of the algorithm subject to optimal high and low-level planning, re-planning and overtaking.     

基于云网格集成调度的防拥堵车辆路径规划算法

在道路交通路网中,车辆拥堵问题是流量与路网结构之间相互作用的一个复杂动态过程,通过车辆路径规划,实现对路网网格集成调度,从而提高路网通行吞吐量。传统方法采用并行微观交通动态负载平衡预测算法实现车辆拥堵调度和车辆路径规划,不能准确判断路面上的车辆密度,路径规划效益不好。提出一种基于云网格集成调度的防拥堵车辆路径规划算法,即构建基于Small-World模型的云网格路网模型,采用RFID标签信息进行路况信息采集,实现交通网络拥堵评估信息特征的提取,采用固有模态函数加权平均求得各车道的车辆拥塞状态函数,对所有车道内车辆密度取统计平均可获得簇内的车辆密度。设计交通路网拥堵检测算法来对当前个体道路信息进行一维邻域搜索,从而实现车辆路径规划控制目标函数最佳寻优。通过动态博弈的方式求得车辆防拥堵路径的近似最优轨迹,实现路径规划算法的改进。仿真结果表明,该算法能准确规划车辆路径,实现最优路径控制,从而提高严重拥堵路段的车流速度和路网吞吐性能,性能优越。     

自主车的局部路径规划

局部路径规划是自主车的一项关键技术,它的品质 密切关系到整个自主车系统的性能．本文提出了将自主式多智能体的任务和反应性行为模型 嵌入到离散事件系统框架中作局部路径规划的方法,此方法克服了势场法（包括早期的虚力 场法）的缺陷——即由于把所有信息压缩为单个合力而损失部分有价值的局部障碍物分布信 息,从而提高了局部路径规划的可靠性．     

Agile autonomous guidance using spatial value functions

This paper describes an autonomous guidance system based on receding horizon (RH) optimization. The system is integrated around a spatial, state-dependent cost-to-go (SVF) function that is computed as an approximation to the value function associated with the optimal trajectory planning problem. The function captures the critical interaction between the vehicle dynamics and environment, thereby resulting in tighter coupling between planning and control. The consistency achieved between the RH optimization and the SVF enables a more rigorous implementation of the RH framework to autonomous vehicle guidance. The paper describes the overall approach along flight experimental results obtained in an Interactive Guidance and Control Laboratory.     

多无人机协同攻击路径规划研究

如何实现多架无人机规避复杂威胁区域对敌重要目标实施协同打击成为近来研究的难点,研究实现协同打击的关键是规划出多无人机从各自起始点到目标的最优协同攻击路径,以解决路径规划的关键技术为目的。对复杂威胁区域中,多无人机最优协同攻击路径规划进行了研究。首先,构建了多无人机最优协同攻击路径规划系统框架;其次,以人工智能A*算法为基础,结合无人机运动学方程对A*算法进行了改进,得到一种基于步长搜索的无人机路径快速生成算法;再次,基于改进的路径快速生成算法,以多无人机同时攻击目标为约束条件,进行变步长的协同攻击仿真计算。仿真验证了路径规划算法和协同攻击算法的有效性。     

基于改进人工鱼群算法的车辆轨迹规划方法

针对车联网环境下若干典型车辆轨迹规划方法存在车速与轨迹波动性较大的问题,提出一种基于改进人工鱼群算法的车辆轨迹规划方法。该方法以短程通信（DSRC）的车联网应用场景为设计平台,以车辆的最优行车速度为核心计算基础,分析得到了车辆的最佳轨迹。首先,对人工鱼群算法在车联网应用场景的优势和不足进行分析,引入万有引力力学模型与避障模式控制,提出一种改进的人工鱼群算法;然后,分析车辆在车联网应用场景中的受力约束,利用网联车辆的自组织行为控制策略推导最优行车速度;最后,基于最优行车速度实现对车辆的实时轨迹诱导和轨迹避障控制规划。仿真测试结果表明,在运用了基于改进人工鱼群算法的轨迹规划模型后,车辆的驾驶速度更加平稳,轨迹波动性较小,对障碍物可实现零失误避撞;在多车相遇情况下,测试车辆为2~40时,相对于原人工鱼群算法和萤火虫算法,运用改进人工鱼群算法后车速的平均迭代次数减少,迭代效率提高3~7、4~8倍,且随着车辆数目越多,迭代效率提升越明显。     

基于强化学习的自动驾驶汽车路径规划方法研究综述

路径规划作为自动驾驶的关键技术,具有广阔的应用前景和科研价值。探索解决自动驾驶车辆路径规划问题的方法,着重关注基于强化学习的路径规划方法。在阐述基于常规方法和强化学习方法的路径规划技术的基础上,重点总结了基于强化学习和深度强化学习来解决自动驾驶车辆路径规划问题的算法,并将算法按照基于值和基于策略的方式进行分类,分析各类算法的特点、优缺点及改进措施。最后对基于强化学习的路径规划技术的未来发展方向进行了展望。     

Trajectory Planning and Control for Airport Snow Sweeping by Autonomous Formations of Ploughs

This article presents a control approach that enables an autonomous operation of fleets of unmanned snow ploughs at large airports. The proposed method is suited for the special demands of tasks of the airport snow shovelling. The robots have to keep a compact formation of variable shapes during moving into the locations of their deployment and for the autonomous sweeping of runways surfaces. These tasks are solved in two independent modes of the airport snow shoveling. The moving and the sweeping modes provide a full-scale solution of the trajectory planning and coordination of vehicles applicable in the specific airport environment. Nevertheless, they are suited for any multi-robot application that requires complex manoeuvres of compact formations in dynamic environment. The approach encapsulates the dynamic trajectory planning and the control of the entire formation into one merged optimization process via a novel Model Predictive Control (MPC) based methodology. The obtained solution of the optimization includes a complete plan for the formation. It respects the overall structure of the workspace and actual control inputs for each vehicle to ensure collision avoidance and coordination of team members. The presented method enables to autonomously design arbitrary manoeuvres, like reverse driving or turning of compact formations of car-like robots, which frequently occur in the airport sweeping application. Examples of such scenarios verifying the performance of the approach are shown in simulations and hardware experiments in this article. Furthermore, the requirements that guarantee a convergence of the group to a desired state are formulated for the formation acting in the sweeping and moving modes.     

乘客运输的车辆路径规划策略

针对乘客运输问题,提出一种基于粒子群算法的乘客运输车辆路径规划策略。初始化阶段对n个站点、m辆车的乘客运输问题编码成一个（n+2m）维的粒子。迭代阶段对粒子进行解码,将一个（n+2m）维的粒子解码为m辆车的行走路径,对路径进行“移除－插入额外站点”优化。实验结果表明,该策略能有效地解决乘客运输车辆路径规划问题,达到总路程最短、车辆数目最少、服务的乘客数多,减少运输成本的目的。