Multi-agent based path planning for first responders among moving obstacles

Natural or man-made disasters can cause different kinds of moving obstacles (e.g., fires, plumes, floods), which make some parts of the road network temporarily unavailable. After such incidents occur, responders have to go to different destinations to perform their tasks in the environment affected by the disaster. Therefore they need a path planner that is capable of dealing with such moving obstacles, as well as generating and coordinating their routes quickly and efficiently. In this paper, we present a novel approach for using a multi-agent system for navigating one or multiple responders to one or multiple destinations in the presence of moving obstacles. Our navigation system supports information collection from hazard simulations, spatio-temporal data processing and analysis, connection with a geo-database, and route generation in dynamic environments affected by disasters. We design and develop a set of software geospatial agents that assist emergency actors in dealing with the spatio-temporal data required for emergency navigation, based on their roles in the disaster response. One of the key components of the system is the path planning module, which combines the modified A* algorithm, insertion heuristics, and auction algorithm to calculate obstacle-avoiding routes for multiple responders with multiple destinations. A spatial data model is designed to support the storage of information about the tasks and routes produced during the disaster response. Our system has been validated using four navigation cases. Some preliminary results are presented in this paper and show the potential of the system for solving more navigation cases.     

Dynamic optimal payload path planning of mobile manipulators among moving obstacles

This paper is dealt with dynamic analysis of the wheeled mobile manipulators in the presence of moving obstacles considering optimal payload criterion. General dynamic formulation of the system was derived, and the moving obstacle avoidance strategy was proposed in terms of dynamic potential functions. The problem of dynamic motion planning and payload maximization was formulated using open-loop optimal control theory. Then, the indirect solution based on Pontryagin’s minimum principle was employed to solve the problem. Using the proposed method, complete nonlinear states and control constraints were treated without any simplifications such as linearizing the dynamics equations, discretizing the robot’s workspace, or parameterizing the solution. The proposed method will be useful for the system design and in the situation where the trajectories of obstacles are predefined. Finally, capability and applicability of the proposed method were investigated by the number of simulations on a two-link mobile manipulator.     

Dynamic path planning for a planar articulated robot arm moving amidst unknown obstacles

This work is concerned with planning collision-free paths for a robot arm moving in an environment filled with unknown obstacles, where any point of the robot body is subject to collision. To compensate for the uncertainty, the system is provided with sensory feedback information about its immediate surroundings. In such a setting, which presents significant practical and theoretical interest, human intuition is of little help, and designing algorithms with proven convergence thus becomes an important task. We show that, given the target position, local feedback information is sufficient to guarantee reaching a global objective (the target position) and present a nonheuristic algorithm which generates reasonable—if, in general, not optimal—collision-free paths. In this approach, the path is being planned continuously (dynamically), based on the arm's current position and on the sensory feedback. Here, a case of a planar arm with two revolute joints is studied. No constraints on the shape of the robot links or the obstacles are imposed. The general idea is to reduce the problem of motion planning to an analysis of simple closed curves on the surface of an appropriate two-dimensional manifold.     

UAV path planning method for avoiding restricted areas

Intelligent Service Robotics - Recently, the industry of drone systems has come into the spotlight because a new potential market has been revealed. A considerable number of drones are deployed...     

面向自动驾驶的动态路径规划避障算法

针对自动驾驶中避障的动态路径规划问题,提出一种在已知车辆的初始位置、速度、方向和障碍物位置情况下,实时避开障碍物的动态规划算法。首先,利用三次样条曲线的二阶连续性,结合已知的车道信息产生道路基准线;其次,以车辆的位置方向和道路的曲率构建s-q坐标系,并在s-q坐标系内产生从车辆当前位置到目的位置的一簇平滑曲线,作为候选路径;最后,综合考虑车辆行驶的安全性、平滑性和连贯性准则,设计一种新的代价函数,并且通过使代价函数最小化的方法从候选路径中选择最佳路径。在实验过程中,通过设计多种不同的模拟道路来检验算法的性能。实验结果表明,该方法在多种地形的单车道和多车道道路上都能够规划出安全、平滑的路径,有效避开障碍物,并且具有较好的实时性。     

A variational approach to path planning for hyper-redundant manipulators

Motion planning for hyper-redundant manipulators in a complicated and cluttered workspace is a challenging problem. Many of the path planning algorithms, based on cell decomposition or potential field, fail due to the high dimensionality and complex nature of the C-space. Probabilistic roadmap methods (PRM) which have been proven to be successful in high dimensional C-spaces suffer from the drawback of generating paths which involve a lot of redundant motion. In this paper, we propose a path optimizing method to improve a given path in terms of path length and the safety against the collisions, using a variational approach. The capability of variational calculus to optimize a path is demonstrated on a variety of examples. The approach succeeds in providing a good quality path even in high dimensional C-spaces.     

Automatic path planning for a mobile robot among obstacles ofarbitrary shape

A novel and fast path planning method for a mobile robot (MR) among objects of arbitrary shape is described. It comprises two phases. During the first phase, the graph including all possible collision-free paths from a top view of the environment is first obtained. During the second phase, the optimal path for the MR is then selected. For this, the proposed method uses both the fast distance transformation (FDT) and variations of some topological methods as thinning and skeletonization, to obtain the free space skeleton. Unlike conventional methods, the proposed approach is capable to include the MR and the target intrinsically in the path and, at the same time it obtains the collision-free path's graph, taking advantage of the topological concept of hole. We propose to use a logical operator over the FDT instead of the classical morphologic operators over the discrete array (erosion and dilation), to obtain a much faster algorithm. The optimal path (in terms of length) is next selected and smoothed by conventional algorithms. The resultant path is finally used as a reference by the mobile robot     

基于全局路径规划的相互速度障碍物人群疏散方法

针对相互速度障碍物（RVO）模型缺少全局路径规划,只依靠局部碰撞避免不能很好地模拟复杂的疏散场景问题,提出了一种剩余路径代价尽量小的动态全局路径选择方法。该方法包含路径预处理和路径实时更新两部分:第一部分使用快速最短路径算法（SPFA）求取场景最短路径（SSP）;第二部分根据SSP快速动态地计算每个个体的最优疏散路径,并使用KD树优化障碍物阻挡判断过程。最后将方法扩展到多楼层、多障碍物、多通道、多出口的复杂场景实现了近千人的仿真实验。实验结果表明,该方法在多个场景中都取得了良好的路径规划效果。     

改进人工势场法在机器人路径规划中的应用

为解决传统人工势场法用于机器人路径规划时会出现规划失败的问题,分析了由于局部极小点问题而导致规划失败的原因。在已改进人工势场函数的基础上,提出了通过增加虚拟目标点和原目标点共同对机器人产生引力的方法来解决传统人工势场法中出现的局部极小点问题。在Mobotsim中对算法的仿真结果表明了该方法的可行性和有效性。     

A new potential field-based algorithm for path planning

In this paper, the path-planning problem is considered. We introduce a new potential function for path planning that has the remarkable feature that it is free from any local minima in the free space irrespective of the number of obstacles in the configuration space. The only global minimum is the goal configuration whose region of attraction extends over the whole free space. We also propose a new method for path optimization using an expanding sphere that can be used with any potential or penalty function. Simulations using a point mobile robot and smooth obstacles are presented to demonstrate the qualities of the new potential function. Finally, practical considerations are also discussed for nonpoint robots     

A genetic algorithm approach to piping route path planning

A genetic algorithm (GA) approach to support interactive planning of a piping route path in plant layout design is presented. To present this approach, the paper mainly describes the basic ideas used in the methodology, which include the definition of genes to deal with pipe routes, the concept of spatial potential energy, the method of generating initial individuals for GA optimization, the zone concept in route generation using GAs, the evaluation of crossover methods, and definition and application of fitness functions. The prototype system that has been developed based on the methodology gives designers an environment to design a piping route path in an interactive and collaborative manner with a very simple operation. The GA optimization technique generates a route path through evolution of genes that represent the pipe route. A designer evaluates the route path, modifies it, conducts another GA optimization and/or repeats the procedure until the appropriate route is desig ned. The paper also presents some simulation results using the prototype system to show the validity of this approach.     

飞行器分层势场路径规划算法

传统势场法是飞行器路径规划的一种常用方法,但是存在目标不可达、易收敛到局部极小值和无评价机制等问题.本文针对这些问题提出了一种飞行器路径规划的分层势场算法.利用分段思想对势场函数进行修正,解决了目标不可达问题.引入回环力和飞行器间作用力,解决了易收敛到局部极小值问题和飞行器间的碰撞问题.采用分层方法,建立了多层次多方位路径点阵,并以此计算最优路径点,从而引入了势场法的评价机制.通过数值仿真,对在复杂障碍环境中的飞行器路径规划进行了传统势场法、改进势场法和分层势场法的对比研究.仿真结果验证了所提出的分层势场算法的有效性和可行性.     

A non-retraction path planning approach for extrusion-based additive manufacturing

Notwithstanding the widespread use and large number of advantages over traditional subtractive manufacturing techniques, the application of additive manufacturing technologies is currently limited by the undesirable fabricating efficiency, which has attracted attentions from a wide range of areas, such as fabrication method, material improvement, and algorithm optimization. As a critical step in the process planning of additive manufacturing, path planning plays a significant role in affecting the build time by means of determining the paths for the printing head's movement. So a novel path filling pattern for the deposition of extrusion–based additive manufacturing is developed in this paper, mainly to avoid the retraction during the deposition process, and hence the time moving along these retracting paths can be saved and the discontinuous deposition can be avoided as well. On the basis of analysis and discussion of the reason behind the occurrence of retraction in the deposition process, a path planning strategy called “go and back” is presented to avoid the retraction issue. The “go and back” strategy can be adopted to generate a continuous extruder path for simple areas with the start point being connected to the end point. So a sliced layer can be decomposed into several simple areas and the sub-paths for each area are generated based on the proposed strategy. All of these obtainable sub-paths can be connected into a continuous path with proper selection of the start point. By doing this, separated sub-paths are joined with each other to decrease the number of the startup and shutdown process for the extruder, which is beneficial for the enhancement of the deposition quality and the efficiency. Additionally, some methodologies are proposed to further optimize the generated non-retraction paths. At last, several cases are used to test and verify the developed methodology and the comparisons with conventional path filling patterns are conducted. The results show that the proposed approach can effectively reduce the retraction motions and is especially beneficial for the high efficient additive manufacturing without compromise on the part resistance.     

A Petri net based approach for multi-robot path planning

This paper presents a procedure for creating a probabilistic finite-state model for mobile robots and for finding a sequence of controllers ensuring the highest probability for reaching some desired regions. The approach starts by using results for controlling affine systems in simpliceal partitions, and then it creates a finite-state representation with history-based probabilities on transitions. This representation is embedded into a Petri Net model with probabilistic costs on transitions, and a highest probability path to reach a set of target regions is found. An online supervising procedure updates the paths whenever a robot deviates from the intended trajectory. The proposed probabilistic framework may prove suitable for controlling mobile robots based on more complex specifications.     

A neural network approach to complete coverage path planning.

Complete coverage path planning requires the robot path to cover every part of the workspace, which is an essential issue in cleaning robots and many other robotic applications such as vacuum robots, painter robots, land mine detectors, lawn mowers, automated harvesters, and window cleaners. In this paper, a novel neural network approach is proposed for complete coverage path planning with obstacle avoidance of cleaning robots in nonstationary environments. The dynamics of each neuron in the topologically organized neural network is characterized by a shunting equation derived from Hodgkin and Huxley's (1952) membrane equation. There are only local lateral connections among neurons. The robot path is autonomously generated from the dynamic activity landscape of the neural network and the previous robot location. The proposed model algorithm is computationally simple. Simulation results show that the proposed model is capable of planning collision-free complete coverage robot paths.     

A penalized batch-Bayesian approach to informative path planning for decentralized swarm robotic search

Autonomous Robots - Swarm-robotic approaches to search and target localization, where target sources emit a spatially varying signal, promise unparalleled time efficiency and robustness. With most...     

An innovative multi-agent search-and-rescue path planning approach

Search and rescue path planning is known to be computationally hard, and most techniques developed to solve practical size problems have been unsuccessful to estimate an optimality gap. A mixed-integer linear programming (MIP) formulation is proposed to optimally solve the multi-agent discrete search and rescue (SAR) path planning problem, maximizing cumulative probability of success in detecting a target. It extends a single agent decision model to a multi-agent setting capturing anticipated feedback information resulting from possible observation outcomes during projected path execution while expanding possible agent actions to all possible neighboring move directions, considerably augmenting computational complexity. A network representation is further exploited to alleviate problem modeling, constraint specification, and speed-up computation. The proposed MIP approach uses CPLEX problem-solving technology in promptly providing near-optimal solutions for realistic problems, while offering a robust upper bound derived from Lagrangean integrality constraint relaxation. Modeling extension to a closed-loop environment to incorporate real-time action outcomes over a receding time horizon can even be envisioned given acceptable run-time performance. A generalized parameter-driven objective function is then proposed and discussed to suitably define a variety of user-defined objectives. Computational results reporting the performance of the approach clearly show its value.     

求解PCB钻孔机刀具路径规划的交叉熵方法

工作刀具路径的优化程度是PCB钻孔机的重要性能指标,对其进行很好的优化有助于提高PCB设备的加工质量和加工速度.首先对刀具路径进行建模,然后对交叉熵算法进行描述并应用交叉熵方法对刀具路径进行求解.实验结果表明,选择交叉熵方法对环境进行建模简单、有效,在求解刀具路径规划方面具有一定的优势.     

基于二重势函数法的集群航路规划

人工势场法由于其在构型组织能力上的不足,影响了该方法在集群航路规划上的应用,为此提出基于二重势函数法的集群航路规划法,通过第一重势能场形成集群到目标的可行路径,通过第二重势能场形成构型,从而实现集群航路规划.此外,针对人工势场法存在无谓避碰、陷阱问题等不足,通过引入碰撞危险度来确定障碍物影响距离以及虚拟障碍物,提出改进...     

A morphological adaptation approach to path planning inspired by slime mould

Path planning is a classic problem in computer science and robotics which has recently been implemented in unconventional computing substrates such as chemical reaction–diffusion computers. These novel computing schemes utilise the parallel spatial propagation of information and often use a two-stage method involving diffusive propagation to discover all paths and a second stage to highlight or visualise the path between two particular points in the arena. The true slime mould Physarum polycephalum is known to construct efficient transport networks between nutrients in its environment. These networks are continuously remodelled as the organism adapts its body plan to changing spatial stimuli. It can be guided towards attractant stimuli (nutrients, warm regions) and it avoids locations containing hazardous stimuli (light irradiation, repellents, or regions occupied by predatory threats). Using a particle model of slime mould we demonstrate scoping experiments which explore how path planning may be performed by morphological adaptation. We initially demonstrate simple path planning by a shrinking blob of virtual plasmodium between two attractant sources within a polygonal arena. We examine the case where multiple paths are required and the subsequent selection of a single path from multiple options. Collision-free paths are implemented via repulsion from the borders of the arena. Finally, obstacle avoidance is implemented by repulsion from obstacles as they are uncovered by the shrinking blob. These examples show proof-of-concept results of path planning by morphological adaptation which complement existing research on path planning in novel computing substrates.