UAV/UGV协同环境下的目标识别与全局路径规划研究

针对单独机器人难以执行复杂环境中任务的问题,Unmanned Air/Ground Vehicle(UAV/UGV)协同系统近年来受到了广泛关注。为了提高执行任务的工作效率,提出一种基于视觉传感器下UAV/UGV协同系统中UAV目标识别下UGV全局路径规划的方法,无人机利用高空视野优势获取目标物与环境信息, SURF算法和图像分割实现环境建模。无人车根据无人机获取的信息,利用优化的A*算法完成全局路径规划,并且在典型搜救场景中进行了仿真验证。实验表明,SURF算法能满足目标识别的精确度、实时性和鲁棒性;并且利用优化的A*算法实现了UGV快速准确的全局路径规划。     

空地两用机器人

地面无人驾驶车辆(UGV)及无人驾驶飞行器(UAV)一个在地上一个在天上,各有各的用途.目前日本正在研制一种两用机器人,就是要把两者的长处结合起来.形成一种新的机器人.空地两用机器人可用来执行侦察及监视任务,见图.它首先以UAV的形态进入作战地区,这时它可以垂直起飞,飞过一些UGV无法通过的障碍地区,由于它飞行速度快、观察范围广,因而能充分发挥其优势.然后它降落在作战地区前面的地面上,以UGV形态出现.它可隐蔽在有利地形后面,对敌人进行监视及侦察.由于它不象UAV那样会发出很大的噪声,因而不易被敌人发现.要实现上述两用机器人有许多困难,但如果能实现机器人驱动及控制系统的程序化,且对机器人的载重量及飞行时间有一定的限制,这一设想是可以实现的.     

通信时延下UAV/UGV混合编队控制系统的稳定性分析

针对通信时延下的高维异构无人机(UAV,unmanned aerial vehicle)/无人车(UGV,unmanned ground vehicle)混合编队控制系统,对系统稳定的充分必要条件和准确时延边界的计算方法进行了研究;具体地,为了处置UAV/UGV工作空间、运动学模型的差异,建立考虑异构特性的UAV/UGV混合编队模型;并针对UAV群组、UGV群组,分别设计基于信息一致性的分布式控制器;利用矩阵相似变换,将高维异构的UAV/UGV混合编队控制系统降维拆分为若干等价的低维子系统,极大地降低了稳定性分析的解析难度和运算量;在此基础上,利用辅助特征函数法推导准确的时延边界,得到系统稳定的充要条件;最后通过仿真验证了所提出稳定性分析方法的有效性。     

多追捕者-单-逃跑者追逃问题实现成功捕获的约束条件

针对包含有n个追捕者及1个逃跑者的2维平面多机器人追逃问题,对实现成功捕获的约束条件进行了研究.经过理论分析得出:在机器人拥有全局视野的情况下,即使单一逃跑者性能优于每个追捕者,只要满足追捕者与逃跑者的速率比大于sin(π/n),逃跑机器人落在追捕机器人所构成的凸多边形内部且逃跑者和追捕者构成的相邻追-逃阿波罗尼奥斯圆满足两两相交(相切)这2个约束条件,则追捕者通过选择合适的追捕策略就一定可以实现成功抓捕.此外,还给出了在此约束条件下的追捕者和逃跑者的追逃策略.多组仿真实验同样证明了本文提出的约束条件是正确的.     

基于合作博弈的移动代理网管任务协作模型

为提高网络管理任务性能,需要研究在复杂网管任务下多移动代理协作问题 .由于传统代理协作模型(如合同网协议)并不适合大规模网络中复杂任务的代理协作,不能保证协作模型中个体代理性能的稳定 .为此合作博弈理论成为移动代理的网管任务协作问题的重要途径,在该协作模型中,单个功能代理被视为具有自主意识的主体,它具有自身的效用函数评估个体的性能 .将代理协作问题转化成为凸联盟博弈模型并利用Shapley值作为协作模型中任务分配合理性的评判标准,并基于上述理论模型,提出3阶段的任务协作算法 .     

图注意力网络的微分博弈追逃问题最优策略

微分博弈追逃问题的最优策略，是建立在追逃双方的轨迹预测模型基础上，通过双方轨迹进行预判，从而做出更有预见性的动态策略。因此为了获得博弈双方最优策略，提出并设计双方随机运动算法，建立了追逃双方的状态方程，并在此基础上通过改进图注意力网络（graph attention network,GAT），对其网络中邻接矩阵和特征数据连接方式进行重新设计，构建了攻击方与目标方轨迹预测模型并进行数值验证。此外采用将双方随机运动的轨迹由圆环覆盖的方法，建立轨迹连接图。结果表明，GAT网络在MAE、MAPE、RMSE等预测指标上均优于图卷积网络和契比雪夫频谱卷积网络，可用于微分博弈追逃问题的最优策略研究。     

基于微分博弈的追逃问题最优策略设计

本文设计了基于线性二次型微分博弈的多个攻击者、多个防御者和单个目标的追逃问题最优策略. 首先, 针对攻防双方保持聚合状态的情形, 基于攻击方内部、防御方内部以及双方之间的通信拓扑, 分别给出了目标沿固定轨迹运动和目标采取逃跑时攻防双方的最优策略. 其次, 针对攻防双方保持分散状态的情形, 利用二分图最大匹配算法分配相应的防御者与攻击者, 将多攻击者、多防御者追逃问题转化为多组两人零和微分博弈, 并求解出了攻防双方的最优策略. 最后, 数值仿真验证了所提策略的有效性.     

基于后悔值的多Agent冲突博弈强化学习模型

对于冲突博弈,研究了一种理性保守的行为选择方法,即最小化最坏情况下Agent的后悔值.在该方法下,Agent当前的行为策略在未来可能造成的损失最小,并且在没有任何其他Agent信息的条件下,能够得到Nash均衡混合策略.基于后悔值提出了多Agent复杂环境下冲突博弈的强化学习模型以及算法实现.该模型中通过引入交叉熵距离建立信念更新过程,进一步优化了冲突博弈时的行为选择策略.基于Markov重复博弈模型验证了算法的收敛性,分析了信念与最优策略的关系.此外,与MMDP(multi-agent markov decision process)下Q学习扩展算法相比,该算法在很大程度上减少了冲突发生的次数,增强了Agent行为的协调性,并且提高了系统的性能,有利于维持系统的稳定.     

UGV协同系统研究进展*

无人地面车辆（UGV）在工业自动化、星球探索、灾后救援、智能交通以及军事作战等多任务领域都具有广阔的应用前景。UGV协同系统通过嵌入组织架构、合作策略、交互机制等协同内容,可以达到拓展环境感知范围、提高复杂环境理解适应能力和增强复杂任务工作效能的目的,受到了国内外广泛的关注。从UGV单体/群体体系结构、多重任务协同分配方法以及协同定位、编队、覆盖/探索等几个方面对目前国内外UGV协同工作关键技术进行了总结,给出了一个UGV协同系统的应用实例,并指出了系统发展趋势。     

基于微分博弈的移动目标防御最优策略

目前,针对移动目标防御最优策略研究大多采用经典单/多阶段博弈和Markov博弈模型,无法在连续实时网络攻防对抗中进行灵活决策.为实现实时选取最优移动目标防御策略,在研究节点级传染病模型与微分博弈理论的基础上,提出了一种移动目标防御微分博弈模型,对网络空间重要节点构造安全状态演化方程与攻防收益目标函数,并设计开环纳什均衡求解算法以得出最优防御策略.仿真结果表明,该方法可有效对网络攻击进行实时防御,并且可针对网络关键节点制定相应移动目标防御策略.     

A cooperative pursuit-evasion game in wireless sensor and actor networks

This paper studies the problem of the pursuit-evasion game under the wireless sensor and actor networks (WSANs). In order to plan paths for pursuers to capture an evader in the pursuit-evasion game, a novel multi-step cooperative strategy is presented. Under this strategy, the pursuit-evasion game is studied in two stages. In the first stage we assume that the evader is always static in the workplace, and in the second stage the evader will move once it senses the existence of pursuers. A Daisy-Chain Formation algorithm and a sliding mode-based method are presented to control the pursuit. Based on Lyapunov stability theory, the proposed algorithm is proved to be convergent. At last, simulation results are provided to demonstrate the effectiveness of the proposed method.     

强化学习的地-空异构多智能体协作覆盖研究

以无人机（unmanned aerial vehicle, UAV）和无人车（unmanned ground vehicle, UGV）的异构协作任务为背景,通过UAV和UGV的异构特性互补,为了扩展和改进异构多智能体的动态覆盖问题,提出了一种地-空异构多智能体协作覆盖模型。在覆盖过程中,UAV可以利用速度与观测范围的优势对UGV的行动进行指导;同时考虑智能体的局部观测性与不确定性,以分布式局部可观测马尔可夫（decentralized partially observable Markov decision processes,DEC-POMDPs）为模型搭建覆盖场景,并利用多智能体强化学习算法完成对环境的覆盖。仿真实验表明,UAV与 UGV间的协作加快了团队对环境的覆盖速度,同时强化学习算法也提高了覆盖模型的有效性。     

A Decentralized Fuzzy Learning Algorithm for Pursuit-Evasion Differential Games with Superior Evaders

In this paper, we consider multi-pursuer single-superior-evader pursuit-evasion differential games where the evader has a speed that is similar to or higher than the speed of each pursuer. A new fuzzy reinforcement learning algorithm is proposed in this work. The proposed algorithm uses the well-known Apollonius circle mechanism to define the capture region of the learning pursuer based on its location and the location of the superior evader. The proposed algorithm uses the Apollonius circle with a developed formation control approach in the tuning mechanism of the fuzzy logic controller (FLC) of the learning pursuer so that one or some of the learning pursuers can capture the superior evader. The formation control mechanism used by the proposed algorithm guarantees that the pursuers are distributed around the superior evader in order to avoid collision between pursuers. The formation control mechanism used by the proposed algorithm also makes the Apollonius circles of each two adjacent pursuers intersect or be at least tangent to each other so that the capture of the superior evader can occur. The proposed algorithm is a decentralized algorithm as no communication among the pursuers is required. The only information the proposed algorithm requires is the position and the speed of the superior evader. The proposed algorithm is used to learn different multi-pursuer single-superior-evader pursuit-evasion differential games. The simulation results show the effectiveness of the proposed algorithm.     

Evasion strategies of a three-player lifeline game

This study examines a multi-player pursuit-evasion game, more specifically, a three-player lifeline game in a planar environment, where a single evader is tasked with reaching a lifeline prior to capture. A decomposition method based on an explicit policy is proposed to address the game qualitatively from two main aspects: (1) the evader’s position distribution to guarantee winning the game (i.e., the escape zone), which is based on the premise of knowing the pursuers’ positions initially, and (2) evasion strategies in the escape zone. First, this study decomposes the three-player lifeline game into two two-player sub-games and obtains an analytic expression of the escape zone by constructing a barrier, which is an integration of the solutions of two sub-games. This study then explicitly partitions the escape zone into several regions and derives an evasion strategy for each region. In particular, this study provides a resultant force method for the evader to balance the active goal of reaching the lifeline and the passive goal of avoiding capture. Finally, some examples from a lifeline game involving more than one pursuer are used to verify the effectiveness and scalability of the evasion strategies.     

Randomized pursuit-evasion in a polygonal environment

This paper contains two main results. First, we revisit the well-known visibility-based pursuit-evasion problem, and show that in contrast to deterministic strategies, a single pursuer can locate an unpredictable evader in any simply connected polygonal environment, using a randomized strategy. The evader can be arbitrarily faster than the pursuer, and it may know the position of the pursuer at all times, but it does not have prior knowledge of the random decisions made by the pursuer. Second, using the randomized algorithm, together with the solution to a problem called the "lion and man problem" as subroutines, we present a strategy for two pursuers (one of which is at least as fast as the evader) to quickly capture an evader in a simply connected polygonal environment. We show how this strategy can be extended to obtain a strategy for a polygonal room with a door, two pursuers who have only line-of-sight communication, and a single pursuer (at the expense of increased capture time).     

A cooperative Homicidal Chauffeur game

We address a pursuit-evasion problem involving an unbounded planar environment, a single evader and multiple pursuers moving along curves of bounded curvature. The problem amounts to a multi-agent version of the classic Homicidal Chauffeur problem; we identify parameter ranges in which a single pursuer is not sufficient to guarantee evader capture. We propose a novel multi-phase cooperative strategy in which the pursuers move in specific formations and confine the evader to a bounded region. The proposed strategy is inspired by the hunting and foraging behaviors of various fish species. We characterize the required number of pursuers for which our strategy is guaranteed to lead to confinement.     

空地协同机器人目标定位方法

针对空地协同机器人中无人机对地面无人车的实时精准定位问题,提出一种红色双圆型定位标记及标记识别与定位方法。引入颜色分割与轮廓提取相结合的方式,减少提取到的轮廓特征数量,排除背景信息干扰以减少误识别;提出一种圆形轮廓快速检测算法,快速识别目标轮廓并准确定位目标像素坐标和方向;基于针孔相机成像模型,根据目标像素坐标和方向,估计出目标在机体坐标系下三维坐标和偏航角。实验结果表明,无人机与地面无人车相对高度1.5 m时,该方法在[x]轴和[y]轴方向定位误差分别为3.9 mm和3.6 mm,每帧图像平均处理耗时为11.6 ms,优于基于核相关滤波的识别定位方法的13.3 mm、14.3 mm和56.3 ms。该方法与无人机控制相结合,可以实现无人机协同跟踪与自主降落功能,提升空地协同机器人作业效率,具有显著的工程意义。     

Scalable and practical pursuit-evasion with networked robots

In this paper, we consider the design and implementation of practical pursuit-evasion games with networked robots, where a communication network provides sensing-at-a-distance as well as a communication backbone that enables tighter coordination between pursuers. We first develop, using the theory of zero-sum games, an algorithm that computes the minimal completion time strategy for pursuit-evasion when pursuers and evaders have same speed, and when all players make optimal decisions based on complete knowledge. Then, we extend this algorithm to when evader are significantly faster than pursuers. Unfortunately, these algorithms do not scale beyond a small number of robots. To overcome this problem, we design and implement a partition algorithm where pursuers capture evaders by decomposing the game into multiple multi-pursuer single-evader games. We show that the partition algorithm terminates, has bounded capture time, is robust, and is scalable in the number of robots. We then describe the design of a real-world mobile robot-based pursuit evasion game. We validate our algorithms by experiments in a moderate-scale testbed in a challenging office environment. Overall, our work illustrates an innovative interplay between robotics and communication.     

On Discrete-Time Pursuit-Evasion Games With Sensing Limitations

In this paper, we address discrete-time pursuit-evasion games in the plane where every player has identical sensing and motion ranges restricted to closed disks of given sensing and stepping radii. A single evader is initially located inside a bounded subset of the environment and does not move until detected. We propose a sweep-pursuit-capture pursuer strategy to capture the evader and apply it to two variants of the game. The first involves a single pursuer and an evader in a bounded convex environment, and the second involves multiple pursuers and an evader in a boundaryless environment. In the first game, we give a sufficient condition on the ratio of sensing to stepping radius of the players that guarantees capture. In the second, we determine the minimum probability of capture, which is a function of a novel pursuer formation and independent of the initial evader location. The sweep and pursuit phases reduce both games to previously studied problems with unlimited range sensing, and capture is achieved using available strategies. We obtain novel upper bounds on the capture time and present simulation studies that address the performance of the strategies under sensing errors, different ratios of sensing to stepping radius, greater evader speed, and a different number of pursuers.