Real-time hierarchical stereo Visual SLAM in large-scale environments

In this paper we present a new real-time hierarchical (topological/metric) Visual SLAM system focusing on the localization of a vehicle in large-scale outdoor urban environments. It is exclusively based on the visual information provided by a cheap wide-angle stereo camera. Our approach divides the whole map into local sub-maps identified by the so-called fingerprints (vehicle poses). At the sub-map level (low level SLAM), 3D sequential mapping of natural landmarks and the robot location/orientation are obtained using a top-down Bayesian method to model the dynamic behavior. A higher topological level (high level SLAM) based on fingerprints has been added to reduce the global accumulated drift, keeping real-time constraints. Using this hierarchical strategy, we keep the local consistency of the metric sub-maps, by mean of the EKF, and global consistency by using the topological map and the MultiLevel Relaxation (MLR) algorithm. Some experimental results for different large-scale outdoor environments are presented, showing an almost constant processing time.     

基于局部子地图方法的多机器人主动同时定位与地图创建

研究了多机器人在未知环境下以主动的方式协作完成同时定位与地图创建（SLAM）的问题．引入局部子地图方法,由每个机器人建立自身周围局部区域的子地图,使多个机器人之间的地图创建相互独立,从而对全局环境的SLAM问题进行分解．而每个机器人在建立局部子地图时将主动SLAM问题转化为多目标优化问题;机器人选取最优的控制输入,使定位与地图创建的准确性、信息增益以及多机器人之间的协调关系得到综合优化．最后,通过扩展的卡尔曼滤波器（EKF）对子地图进行融合得到全局地图．仿真结果验证了该方法的有效性．     

多机器人协同SLAM技术研究进展

由于单机器人同步定位与建图（SLAM）技术在实际应用中的局限性,多机器人协同SLAM技术以较强的灵活性和鲁棒性受到研究人员的广泛关注,并且在农业生产、环境监测、海上搜救等领域具有巨大应用前景。多机器人协同SLAM是多机器人协同工作的核心及大范围复杂环境内及时获得场景感知信息的关键,能使多个机器人在协同工作时共同定位并构建任务空间地图,主要基于单机器人SLAM算法、多机器人系统架构、地图融合等技术实现。结合多机器人协同SLAM的发展历程,对比分析当前主流的多机器人协同SLAM算法。从传感器的角度,将多机器人协同SLAM分为激光协同SLAM、视觉协同SLAM以及激光视觉融合协同SLAM三类,并对多机器人协同SLAM的架构选择、多机通信、相对位姿、地图融合和后端优化问题进行讨论,同时指出异构机器人协同、基于深度学习的语义SLAM是多机器人协同SLAM的未来发展趋势。     

面向观测融合和吸引因子的多机器人主动SLAM

针对未知环境下多机器人主动SLAM(simultaneous localization and mapping)存在不能完全遍历环境、定位精度不理想等问题,本文基于EKF-SLAM(extended Kalman filter-simultaneous localization and mapping)算法提出一种多机器人主动SLAM算法。通过引入吸引因子,增强多机器人系统之间的交流,提升机器人自身定位精度与环境建图精度,同时又引导多机器人团队进行探索环境。当同一地标被多个机器人观测到,采用凸组合融合方法融合各个机器人对地标的估计,从而降低被估计地标的不确定度。仿真结果表明,所提算法能够对环境进行覆盖遍历,提升对地标估计的定位精度。     

基于协助校正方法的多机器人主动同时定位与建图

协作策略是多机器人主动同时定位与建图(SLAM)的关键。文中提出一种多机器人相互校正的协作策略, 称为协助校正。 该方法通过优化机器人对陆标的观测来提高定位与建图的精度, 共包括弱协助校正和强协助校正两种模式。 前者是一种间接的协助模式, 可应用于所有机器人自身定位均不准确的情形。 后者是一种直接的协助模式, 由自身定位精度较高的机器人主动校正其它机器人及相应陆标。 文中将这两种协助校正模式利用状态机统一到多机器人主动SLAM应用中。在仿真实验中将协助校正与其它多机器人主动SLAM方法进行对比以验证其精度优势, 并与单机器人主动SLAM对比以验证其导航代价极低的优势。最后在两台Poineer3-DX移动机器人上进行真实环境实验,实验结果证实协助校正方法可在实际应用中有效提高多机器人主动SLAM的探索效率和精度。     

多机器人同步定位与地图构建的地图融合算法的改进

本文主要研究了多机器人同步定位与地图构建(SLAM)的地图实时融合问题.在本文中提出一种混合的SLAM算法(HybridSLAM)算法,可以同时观测和更新多个路标,并根据FastSLAM2.0思想利用选取的最准确的路标观测值来修正机器人位姿.然后,在改进HybridSLAM算法基础上,进一步提出一种改进的多机器人HybridSLAM算法(MR–IHybridSLAM).每个机器人在不同初始位置运行IHybridSLAM算法构建子地图,并将子地图信息实时发送到同一工作站中.根据卡尔曼滤波(KF)原理将每个机器人构建的子地图融合成全局地图.最后,通过仿真实验构建多机器人融合的特征地图并与单一机器人快速的SLAM算法(FastSLAM)和HybridSLAM算法构建的地图进行误差对比,进一步来验证该算法的准确性、快速性和可行性.     

一种基于离散时间一致性理论的多机器人分布式巡逻算法

在多机器人巡逻任务中,由于通信距离的限制,单个机器人很难获得全局信息。然而,现有的大多数多机器人分布式巡逻算法都要求每个机器人获得其巡逻区域的全局信息进行决策。因此,考虑到通信半径约束和局部信息约束,为了通过相邻机器人之间的交互完成巡逻任务,基于离散时间一致性理论提出了两种巡逻算法。算法1使用全局信息进行决策,算法2基于离散时间一致性理论实现局部信息对全局信息的预测进行决策。通过模拟器Stage对所提算法与对比算法在不同机器人数量、通信半径、地图环境下进行了对比。实验验证了所提出的基于局部信息的分布式多机器人巡逻算法具有与原算法类似的特性和性能,能够使机器人在没有全局信息的情况下判断全局状态,并基于邻居之间的协商完成巡逻任务。     

基于声音的分布式多机器人相对定位

提出了一种基于声音的分布式多机器人相对定位方法.首先,每个机器人通过声源定位算法估计发声机器人在其局部坐标系下的坐标;然后,每个机器人（不含发声机器人）通过无线通信方式将发声机器人在其坐标系下的坐标广播给所有其他机器人,通过坐标变换每个机器人可计算出所有其他机器人在其坐标系下的坐标,从而实现分布式相对定位.理论推导及实验证明只要两个机器人先后发声,通过本文所提方法即可实现多机器人相对定位.室内外环境中采用6个自制小型移动机器人实验表明,所提方法在3米的范围内可实现16厘米的相对定位精度.     

Robotic Urban Search and Rescue: A Survey from the Control Perspective

Robotic urban search and rescue (USAR) is a challenging yet promising research area which has significant application potentials as has been seen during the rescue and recovery operations of recent disaster events. To date, the majority of rescue robots used in the field are teleoperated. In order to minimize a robot operator’s workload in time-critical disaster scenes, recent efforts have been made to equip these robots with some level of autonomy. This paper provides a detailed overview of developments in the exciting and challenging area of robotic control for USAR environments. In particular, we discuss the efforts that have been made in the literature towards: 1) developing low-level controllers for rescue robot autonomy in traversing uneven terrain and stairs, and perception-based simultaneous localization and mapping (SLAM) algorithms for developing 3D maps of USAR scenes, 2) task sharing of multiple tasks between operator and robot via semi-autonomous control, and 3) high-level control schemes that have been designed for multi-robot rescue teams.     

Distributed multi-robot coordination in area exploration

This paper proposes a reliable and efficient multi-robot coordination algorithm to accomplish an area exploration task given that the communication range of each robot is limited. This algorithm is based on a distributed bidding model to coordinate the movement of multiple robots. Two measures are developed to accommodate the limited-range communications. First, the distances between robots are considered in the bidding algorithm so that the robots tend to stay close to each other. Second, a map synchronization mechanism, based on a novel sequence number-based map representation and an effective robot map update tracking, is proposed to reduce the exchanged data volume when robot subnetworks merge. Simulation results show the effectiveness of the use of nearness measure, as well as the map synchronization mechanism. By handling the limited communication range we can make the coordination algorithms more realistic in multi-robot applications.     

Multi-Robot Graph Exploration and Map Building with Collision Avoidance: A Decentralized Approach

This paper proposes a decentralized multi-robot graph exploration approach in which each robot takes independent decision for efficient exploration avoiding inter-robot collision without direct communication between them. The information exchange between the robots is possible through the beacons available at visited vertices of the graph. The proposed decentralized technique guarantees completion of exploration of an unknown environment in finite number of edge traversals where graph structure of the environment is incrementally constructed. New condition for declaring completion of exploration is obtained. The paper also proposes a modification in incidence matrix so that it can be used as a data structure for information exchange. The modified incidence matrix after completion represents map of the environment. The proposed technique requires either lesser or equal number of edge traversals compared to the existing strategy for a tree exploration. A predefined constant speed change approach is proposed to address the inter-robot collision avoidance using local sensor on a robot. Simulation results verify the performance of the algorithm on various trees and graphs. Experiments with multiple robots show multi-robot exploration avoiding inter-robot collision.     

Altruistic coordination for multi-robot cooperative pathfinding

When multiple robots perform tasks in a shared workspace, they might be confronted with the risk of blocking each other’s ways, which will lead to conflicts or interference among them. Planning collision-free paths for all the robots is a challenge for a multi-robot system, which is also known as the multi-robot cooperative pathfinding problem in which each robot has to navigate from its starting location to the destination while keeping avoiding stationary obstacles as well as the other robots. In this paper, we present a novel fully decentralized approach to this problem. Our approach allows robots to make real-time responses to dynamic environments and can resolve a set of benchmark deadlock situations subject to complex spatial constraints in a shared workspace by means of altruistic coordination. Specifically, when confronted with congested situations, each robot can employ waiting, moving-forwards, dodging, retreating and turning-head strategies to make local adjustments. Most importantly, each robot only needs to coordinate and communicate with the others that are located within its coordinated network in our approach, which can reduce communication overhead in fully decentralized multi-robot systems. In addition, experimental results also show that our proposed approach provides an efficient and competitive solution to this problem.     

Decentralized Cooperative SLAM for Sparsely-Communicating Robot Networks: A Centralized-Equivalent Approach

Communication between robots is key to performance in cooperative multi-robot systems. In practice, communication connections for information exchange between all robots are not always guaranteed, which adds difficulty in performing state estimation. This paper examines the decentralized cooperative simultaneous localization and mapping (SLAM) problem, in which each robot is required to estimate the map and all robot states under a sparsely-communicating and dynamic network. We show how the exact, centralized-equivalent estimate can be obtained by all robots in the network in a decentralized manner even when the network is never fully connected. Furthermore, a robot only needs to consider its own knowledge of the network topology in order to detect when the centralized-equivalent estimate is obtainable. Our approach is validated through more than 250 min of hardware experiments using a team of real robots. The resulting estimates are compared against accurate groundtruth data for all robot poses and landmark positions. In addition, we examined the effects of communication range limit on our algorithm’s performance.     

Using Embodied Data for Localization and Mapping

Mobile autonomous robots have finally emerged from the confined spaces of structured and controlled indoor environments. To fulfill the promises of ubiquitous robotics in unstructured outdoor environments, robust navigation is a key requirement. The research in the simultaneous localization and mapping (SLAM) community has largely focused on optical sensors to solve this problem, and the fact that the robot is a physical entity has largely been ignored. In this paper, a hierarchical SLAM framework is proposed that takes the interaction of the robot with the environment into account. A sequential Monte Carlo filter is used to generate local map segments with a combination of visual and embodied data associations. Constraints between segments are used to generate globally consistent maps with a focus on suitability for navigation tasks. The proposed method is experimentally verified on two different outdoor robots. The results show that the approach is viable and that the rich modeling of the robot with its environment provides a new modality with the potential for improving existing visual methods and extending the availability of SLAM in domains where visual processing alone is not sufficient.     

Hierarchical multi-robot navigation and formation in unknown environments via deep reinforcement learning and distributed optimization

Compared with a single robot, Multi-robot Systems (MRSs) can undertake more challenging tasks in complex scenarios benefiting from the increased transportation capacity and fault tolerance. This paper presents a hierarchical framework for multi-robot navigation and formation in unknown environments with static and dynamic obstacles, where the robots compute and maintain the optimized formation while making progress to the target together. In the proposed framework, each single robot is capable of navigating to the global target in unknown environments based on its local perception, and only limited communication among robots is required to obtain the optimal formation. Accordingly, three modules are included in this framework. Firstly, we design a learning network based on Deep Deterministic Policy Gradient (DDPG) to address the global navigation task for single robot, which derives end-to-end policies that map the robot’s local perception into its velocity commands. To handle complex obstacle distributions (e.g. narrow/zigzag passage and local minimum) and stabilize the training process, strategies of Curriculum Learning (CL) and Reward Shaping (RS) are combined. Secondly, for an expected formation, its real-time configuration is optimized by a distributed optimization. This configuration considers surrounding obstacles and current formation status, and provides each robot with its formation target. Finally, a velocity adjustment method considering the robot kinematics is designed which adjusts the navigation velocity of each robot according to its formation target, making all the robots navigate to their targets while maintaining the expected formation. This framework allows for formation online reconfiguration and is scalable with the number of robots. Extensive simulations and 3-D evaluations verify that our method can navigate the MRS in unknown environments while maintaining the optimal formation.     

改进萤火虫算法求解多机器人路径规划

为解决多机器人在静态环境中的路径规划问题,以路径长度为优化目标模型,并针对此模型设计了多机器人萤火虫算法(MR-FA)。首先,考虑到路径安全性对环境中的障碍物采取扩张操作,设计初始化规则以提高生成初始种群的效率;其次,根据算法的连续性原理及特点,设计个体等长策略将维度不一致的个体转变为等维度个体以便于萤火虫的移动更新,并对移动更新后的不可行解采取路径修正策略;然后对规划出的每个机器人的移动路径进行碰撞检测,同时针对机器人不同的碰撞情况设计相应的避碰策略,即暂停—回退策略(PFS)、局部路径重规划策略(LPRS);最后,为验证MR-FA的有效性,在三组环境中进行仿真实验并与其他三种算法进行对比,综合得出MR-FA在解决多机器人路径规划时更有优势。     

空地正交视角下的多机器人协同定位及融合建图

针对单一机器人在复杂场景下进行同步定位与建图存在的视角局限等问题,本文提出了一种空地正交视角下的空中无人机与地面机器人协同定位与融合建图方法.鉴于无人机的空中视角与地面机器人视角属于正交关系,该方法主要思想是解决空地正交视角的坐标系转换问题.首先,设计了一种空中无人机和地面机器人协同定位与建图的框架,通过无人机提供的全局俯视图像与地面机器人的局部平视图像获得全面丰富的场景信息.在此基础上,通过融合惯性测量单元和图像信息修正偏移并优化轨迹,利用地面机器人上带有尺度信息的视觉标识,获得坐标系转换矩阵以融合地图.最后多组真实场景实验验证了该方法具有有效性,是空地协同多机器人协同定位及融合建图(simultaneous localization and mapping, SLAM)领域中值得参考的方法.     

Multiple‐Robot Simultaneous Localization and Mapping: A Review

Simultaneous localization and mapping (SLAM) in unknown GPS‐denied environments is a major challenge for researchers in the field of mobile robotics. Many solutions for single‐robot SLAM exist; however, moving to a platform of multiple robots adds many challenges to the existing problems. This paper reviews state‐of‐the‐art multiple‐robot systems, with a major focus on multiple‐robot SLAM. Various issues and problems in multiple‐robot SLAM are introduced, current solutions for these problems are reviewed, and their advantages and disadvantages are discussed.     

基于粒子滤波的移动机器人SLAM改进算法

针对未知环境中移动机器人同时定位和地图创建（Simultaneous Localization and Map Building,SLAM）由于机器人位姿和环境地图都不确定导致定位和地图创建变得更加复杂,提出一种局部最优（全局次优）参数法,即通过局部最优的位姿创建局部最优的环境地图,再通过局部最优的环境地图寻求局部最优的位姿,如此交替进行,直到得到全局确定性的位姿和确定性的环境地图。实验结果表明,同标准的基于粒子滤波的SLAM 算法（Particle Filtering-SLAM,PF-SLAM）比较,改进的算法提高了机器人SLAM过程中定位的准确度和地图创建的精确度,为机器人在未知的室外大环境同时定位和地图创建提供新的方法。