Boundary Gap Based Reactive Navigation in Unknown Environments

Due to the requirements for mobile robots to search or rescue in unknown environments,reactive navigation which plays an essential role in these applications has attracted increasing interest.However,most existing reactive methods are vulnerable to local minima in the absence of prior knowledge about the environment.This paper aims to address the local minimum problem by employing the proposed boundary gap(BG)based reactive navigation method.Specifically,the narrowest gap extraction algorithm(NGEA)is proposed to eliminate the improper gaps.Meanwhile,we present a new concept called boundary gap which enables the robot to follow the obstacle boundary and then get rid of local minima.Moreover,in order to enhance the smoothness of generated trajectories,we take the robot dynamics into consideration by using the modified dynamic window approach(DWA).Simulation and experimental results show the superiority of our method in avoiding local minima and improving the smoothness.

Path Planning Approach in Unknown Environment

This paper presents a new algorithm of path planning for mobile robots, which utilises the characteristics of the obstacle border and fuzzy logical reasoning. The environment topology or working space is described by the time-variable grid method that can be further described by the moving obstacles and the variation of path safety. Based on the algorithm, a new path planning approach for mobile robots in an unknown environment has been developed. The path planning approach can let a mobile robot find a safe path from the current position to the goal based on a sensor system. The two types of machine learning： advancing learning and exploitation learning or trial learning are explored, and both are applied to the learning of mobile robot path planning algorithm. Comparison with A＊ path planning approach and various simulation results are given to demonstrate the efficiency of the algorithm. This path planning approach can also be applied to computer games.

Safe Navigation for UAV-Enabled Data Dissemination by Deep Reinforcement Learning in Unknown Environments

Unmanned aerial vehicles(UAVs) are increasingly considered in safe autonomous navigation systems to explore unknown environments where UAVs are equipped with multiple sensors to perceive the surroundings. However, how to achieve UAVenabled data dissemination and also ensure safe navigation synchronously is a new challenge. In this paper, our goal is minimizing the whole weighted sum of the UAV’s task completion time while satisfying the data transmission task requirement and the UAV’s feasible flight region constraints. However, it is unable to be solved via standard optimization methods mainly on account of lacking a tractable and accurate system model in practice. To overcome this tough issue,we propose a new solution approach by utilizing the most advanced dueling double deep Q network(dueling DDQN) with multi-step learning. Specifically, to improve the algorithm, the extra labels are added to the primitive states. Simulation results indicate the validity and performance superiority of the proposed algorithm under different data thresholds compared with two other benchmarks.

Path Optimization Method for the Spherical Underwater Robot in Unknown Environment

One of the major respects of the autonomous capability of underwater robots in unknown environment is to be capable of global path planning and obstacles avoiding when encountering abrupt events.For the Spherical Underwater Robot(SUR)to fulfill autonomous task execution,this paper proposed a novel fuzzy control method that incorporates multi-sensor technology to guide underwater robots in unknown environment.To attain the objective,a SUR we designed is used to design the controller.According to its kinematic model,the safety distance was calculated and sensors(US1000-21 A)were arranged.The novel fuzzy control method was then explored for robot's path planning in an unknown environment through simulation.The simulation results demonstrate the capability of the proposed method to guide the robot,and to generate a safe and smooth trajectory in an unknown environment.The effectiveness of the proposed method was further verified through experiments with a SUR in a real platform.The real environment experiments by using the novel fuzzy control method were compared with the basic control method.The experimental results show that in unknown environments,the proposed method improves the execution efficiency and flexibility of the SUR.

A practical PID variable stiffness control and its enhancement for compliant force-tracking interactions with unknown environments

Compliant interaction control is a key technology for robots performing contact-rich manipulation tasks.The design of the compliant controller needs to consider the robot hardware because complex control algorithms may not be compatible with the hardware performance,especially for some industrial robots with low bandwidth sensors.This paper focuses on effective and easy-to-use compliant control algorithms for position/velocity-controlled robots.Inspired by human arm stiffness adaptation behavior,a novel variable target stiffness(NVTS)admittance control strategy is proposed for adaptive force tracking,in which a proportional integral derivative(PID)variable stiffness law is designed to update the stiffness coefficient of the admittance function by the force and position feedback.Meanwhile,its stability and force-tracking capability are theoretically proven.In addition,an impact compensator(Impc)is integrated into the NVTS controller to enhance its disturbance-suppression capability when the robot is subjected to strong vibration disturbances in complicated surface polishing tasks.The proposed controllers are validated through four groups of experimental tests using different robots and the corresponding results demonstrate that they have high-accuracy tracking capability and strong adaptability in unknown environments.

Obstacle Avoidance Capability for Multi-Target Path Planning in Different Styles of Search

This study investigates robot path planning for multiple agents,focusing on the critical requirement that agents can pursue concurrent pathways without collisions.Each agent is assigned a task within the environment to reach a designated destination.When the map or goal changes unexpectedly,particularly in dynamic and unknown environments,it can lead to potential failures or performance degradation in various ways.Additionally,priority inheritance plays a significant role in path planning and can impact performance.This study proposes a ConflictBased Search(CBS)approach,introducing a unique hierarchical search mechanism for planning paths for multiple robots.The study aims to enhance flexibility in adapting to different environments.Three scenarios were tested,and the accuracy of the proposed algorithm was validated.In the first scenario,path planning was applied in unknown environments,both stationary and mobile,yielding excellent results in terms of time to arrival and path length,with a time of 2.3 s.In the second scenario,the algorithm was applied to complex environments containing sharp corners and unknown obstacles,resulting in a time of 2.6 s,with the algorithm also performing well in terms of path length.In the final scenario,the multi-objective algorithm was tested in a warehouse environment containing fixed,mobile,and multi-targeted obstacles,achieving a result of up to 100.4 s.Based on the results and comparisons with previous work,the proposed method was found to be highly effective,efficient,and suitable for various environments.

环境事件中不明来源固体废物危险特性鉴别——以四川省某地仓库贮存物为例

以四川省某地仓库内非法贮存不明固体废物事件为例,通过对不明固体废物的性状、物相组成、成分分析进行研究,判断该不明固体废物的产生来源。根据其来源判断其可能具有的危险特性,进一步开展实验检测明确其危险特性。经鉴别,该材料为二次铝灰,是列入《国家危险废物名录(2021年版)》中的危险废物,类别为HW48有色金属采选和冶炼废物,并进一步明确了二次铝灰的危险特性为遇水释放氨气的反应性和氟化物的毒性。

激光雷达和神经网络相融合的机器人避障轨迹规划研究

机器人避障轨迹规划研究当前是人工智能研究领域的热点,当前机器人避障轨迹规划方法对环境信息敏感,机器人避障轨迹规划偏差大,在短时间难以找到最优机器人避障轨迹规划结果,为了获得理想的机器人避障轨迹规划结果,提出了基于激光雷达和神经网络相融合的机器人避障轨迹规划方法。首先分析当前机器人避障轨迹规划方法的局限性,并采用测量范围广、精度高的激光雷达对机器移动的环境信息,然后将环境信息作为BP神经网络的输入,对环境信中障碍物进行分类,最后根据障碍物分类结果采用人工势场方法找到机器人避障轨迹规划结果,并与其他机器人避障轨迹规划方法进行了对比测试,结果表明,本方法可以在短时间内找到最优的机器人移动最优避障轨迹规划路径,可以避开各种障碍物,保障机器人安全到达目的地,相对对比方法,本方法获得更理想的机器人移动最优避障轨迹规划结果。

船舶动力定位系统的复合抗干扰控制

针对带有未知时变干扰和推进器故障的动力定位船舶,本文提出一种复合抗干扰控制方法。通过设计随机干扰观测器和故障诊断观测器估计未知干扰和故障,利用线性矩阵不等式证明了船舶的位置和航向保持期望值,且动力定位系统的所有信号都是依均方渐近有界的。最后,以比例模型船进行仿真,验证所提策略的有效性。

无人机群目标搜索的主动感知方法

为提升蚁群搜索算法在规模大的栅格环境中对未知目标的搜索效率,提出基于蚁群算法的主动感知搜索框架。该框架通过应用历史环境信息来选择无人机的运动方式,并由无人机运动方式和感知域信息得到新的环境信息,从而实现无人机群的智能自动化搜索功能。新方法计算出一种具有探索偏好的未搜索概率,可使无人机搜索时偏向未搜索程度高的栅格,以此来提高算法的搜索能力。同时,以未搜索概率和信息素作为运动方式决策的依据来建立一种新的运动方式选择机制。该机制不仅考虑了目标可能出现的区域,又可兼顾未知区域,从而可实现无目标先验信息条件下的搜索过程。仿真结果表明,此算法在规模大的栅格环境中,与现有算法相比具有更高的搜索效率,并且得到的目标分布信息将更加全面。

面向无信号灯十字路口场景的自动驾驶安全决策方法研究

针对环境遮挡与交通参与者行为随机导致的驾驶风险,提出一种面向无信号灯十字路口场景的安全决策方法。首先,建立一种基于值分布式强化学习-全参数化分位数网络(Fully parameterized quantile network,FPQN)的基础决策策略。其次,融合FPQN建模的累积回报分布与条件风险价值函数(Conditional value at risk,CVaR),进而构建具有驾驶风险意识的安全决策策略。再次,引入集成学习理论(Ensemble),建立基于集成FPQN的决策不确定性估计框架EFPQN,能够实时量化决策风险。同时,为应对决策不确定性较高带来的驾驶风险,设计基于模型预测控制的备选策略以提升安全性。最后,采用SUMO仿真平台搭建无信号灯十字路口场景,对提出的安全决策方法进行验证。试验结果表明,与基准方法相比,所提出的方法能够有效降低遮挡与交通参与者行为随机导致的驾驶风险。

未知环境下基于激光雷达的启发式导航算法

针对未知环境下机器人难以准确理解障碍分布并有效搜索目标的问题,提出一种基于激光雷达的启发式导航算法.在雷达数据中引入上升/下降沿进行障碍边沿界定及检测,提出边沿匹配算法识别狭窄间隙和连续障碍,经间隙去除与安全性拓展,得到表征周围环境中的连续障碍集合;面对遮挡目标的障碍,提出启发式临时目标选取方法并设计其切换条件,使机器人以较短路径提前避让各类障碍并渐近抵达全局目标.基于Matlab进行一系列仿真和对比,结果表明,所提出的算法可显著提高机器人在复杂未知环境下的通行效率、轨迹平滑度和全局搜索能力.最后基于ROS的实验验证所提出算法在实际环境中的有效性.

基于状态反馈线性化和ESO的船舶航向跟踪控制

针对船舶航向跟踪控制问题,考虑舵机伺服系统特性、船舶动态参数不确定以及未知时变环境扰动,利用状态反馈线性化原理与扩张状态观测器(ESO)的基本思想,设计船舶航向跟踪控制律.首先,对带有执行机构的船舶操纵数学模型进行非线性坐标变换;然后,构造ESO,实时估计动态参数不确定和未知时变环境扰动构成的总扰动.基于上述,根据状态反馈线性化原理设计船舶航向跟踪控制律.理论分析表明,所构造的ESO估计误差渐近收敛于零,所设计的船舶航向跟踪控制律保证船舶航向跟踪闭环系统是稳定的,且使得船舶航向跟踪误差渐近收敛于零.最后,以一艘军舰为例进行仿真研究,仿真结果显示了所设计的船舶航向跟踪控制律的有效性和对扰动的鲁棒性.

带有执行器故障的多水面船固定时间分布式滑模协同控制

针对未知环境干扰、未知执行器故障等多水面船协同控制问题,提出一种带有执行器故障的多水面船固定时间分布式滑模协同控制方法,可保证协同控制系统的全局固定时间的稳定性.首先,设计一种固定时间干扰观测器,用于估计集总扰动(包括未知环境扰动和未知执行器故障);其次,引入固定时间非奇异快速终端滑模面,可有效地消除系统的奇异性,改善系统的抖振;然后,提出一种基于固定时间非奇异快速终端滑模面和固定时间干扰观测器的分布式容错控制器,使得收敛时间上界与系统初始状态无关;最后,通过仿真实验验证所提出控制律的有效性.