Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omnidirectional target with multiple, homogeneous agents that are subject to unicycle kinematic constraints. We use shared experience to train a policy for a given number of pursuers, executed independently by each agent at run-time. The training uses curriculum learning, a sweeping-angle ordering to locally represent neighboring agents, and a reward structure that encourages a good formation and combines individual and group rewards. Simulated experiments with a reactive evader and up to eight pursuers show that our learning-based approach outperforms recent reinforcement learning techniques as well as non-holonomic adaptations of classical algorithms. The learned policy is successfully transferred to the real-world in a proof-of-concept demonstration with three motion-constrained pursuer drones.

Decentralized Multi-Agent Pursuit Using Deep Reinforcement Learning

Pursuit-evasion is the problem of capturing mobile targets with one or more pursuers. We use deep reinforcement learning for pursuing an omni-directional target with multiple, homogeneous agents that are subject to unicycle kinematic constraints. We use shared experience to train a policy for a given number of pursuers that is executed independently by each agent at run-time. The training benefits from curriculum learning, a sweeping-angle ordering to locally represent neighboring agents and encouraging good formations with reward structure that combines individual and group rewards. Simulated experiments with a reactive evader and up to eight pursuers show that our learning-based approach, with non-holonomic agents, performs on par with classical algorithms with omni-directional agents, and outperforms their non-holonomic adaptations. The learned policy is successfully transferred to the real world in a proof-of-concept demonstration with three motion-constrained pursuer drones.

Decentralized Multi-Agent Pursuit using Deep Reinforcement Learning

In this paper, a new method is proposed for the path planning of multi-robots in unknown environments. The method is inspired by multi-objective particle swarm optimization (MOPSO) and is named multi-robot MOPSO. It considers shortness, safety, and smoothness. Due to the obscurity of the environment, the robots should decide the moving direction based on the information gathered by sensors only such that the optimal path between the start and goal positions can be found at the end of the algorithm. Sharing knowledge among the navigating robots is necessary to achieve this aim. So, a new concept, named the probabilistic window, is introduced in this paper. It combines the current information obtained through the robot sensors and experiences of the previous robots to select the paths that seem more likely to achieve higher fitness in the mentioned objectives. The proposed method has an outstanding performance on different complex benchmarks, and the results have shown that it is more effective and efficient compared with the classic and the state-of-the-art methods.

/pdf/multi-robot-path-planning-based-on-multi-objective-particle-2149e2iy2j.pdf

Multi-Robot Path Planning Based on Multi-Objective Particle Swarm Optimization

Improving the quality characteristics of abrasive water jet machining of marble material using multi-objective artificial bee colony algorithm

Unmanned Aerial Vehicles (UAV) path planning can be considered as a complicated function optimization problem with constraint condition. Population based algorithm, especially the artificial bee colony (ABC) algorithm, is known as an effective tool to solve this problem. ABC algorithm is a relatively predominant optimization technique with an advantage of having fewer control parameters over other population algorithms. Considering the ergodicity and the stochastic of the chaotic map, we propose a modified strategy of initialization for the standard ABC, which utilizing the logistic map and opposition based learning to generate the initial population as well as the scout bee position. In addition, the employed bee search equation is modified by adding weight coefficients for the purpose of increasing the convergence speed. Then we test the modified artificial bee colony algorithm in four function optimization problems and path planning problems. The results demonstrate a superior performance of our algorithm in solving UAV path planning in two dimensions compare with the standard ABC algorithm.

Path planning for Unmanned Air Vehicles using an improved artificial bee colony algorithm

An improved multi-objective artificial bee colony algorithm is designed in this paper reflecting the multi-objective characteristic of multi-robot path planning problems. Firstly, the foraging mechanism is optimized and a new method to calculate crowding distance is proposed. The restructuring and elimination mechanism of food sources are also presented. Secondly, an improved environment map representation method is presented in which the path information of robots is denoted using Cartesian coordinates directly. Thirdly, three objective functions for path planning are designed according to three key performance indicators which are length, safety and smoothness of the path. Finally, the simulation results show that the improved multi-objective artificial bee colony algorithm can be effectively applied to solve multi-robot path planning problems.

A novel multi-objective artificial bee colony algorithm for multi-robot path planning

This paper applies game theory to multi-robot hunting target problem. A coordinated multi-robot hunting model based on extended cooperation game is established. And obstacle avoidance model and two kinds of target searching strategies--roaming search and regional search are proposed. Then an effective escape strategy for the target is also presented. Finally the whole process of the hunting task is analyzed. The hunting algorithm using non-formation movement to execute the task is more flexibly. The simulation verifies the feasibility of the method.

Coordinated multi-robot target hunting based on extended cooperative game

This paper presents a path planning and collision avoidance method based on artificial bee colony (ABC) optimization algorithm for multi-robot systems. Standard ABC algorithm can find a proper way for the robots quickly, but it still has shortcomings. An improved artificial bee colony optimization algorithm (IABC) is proposed to plan a reasonable collision-free path for each robot of a multi-robot system in complicated environment. Based on standard ABC algorithm, a new objective function is derived for global planning of each robot's path. The initialization strategy and fitness function are also optimized to improve the performance of IABC algorithm. Compared with standard ABC algorithm, IABC algorithm simplifies the parameter setting and achieves better performance. The feasibility and availability of the proposed IABC algorithm have been verified by simulation results.

A novel artificial bee colony optimization algorithm for global path planning of multi-robot systems

The invention provides a method for capturing targets by the aid of multiple robots on the basis of extensive cooperative games. The method includes steps of firstly, mathematically building multi-robot capturing extensive cooperative game models; secondly, generating robot operation strategies; thirdly, generating capturing task executing procedures. The method has the advantages that the capturing robots can be flexibly positioned in the task executing procedures, can quickly pursue the targets, can avoid obstacles and companions in pursuing procedures and can ultimately besiege target robots, and accordingly the target robots cannot escape from rings of encirclement.

Method for capturing targets by aid of multiple robots on basis of extensive cooperative games

The invention provides a multi robot path planning method based on a multi-target artificial bee colony algorithm and belongs to the technical field of path planning. The method includes path planning problem environment modeling, multi-target artificial bee colony algorithm parameter initialization, three-variety bee iteration optimization path and non-inferior solution determination, good path reservation by sequencing and optimum path set outputting. By means of the method, the standard artificial bee colony algorithm is improved based on the concept of non-domination sequence of Pareto domination and crowd distance, and the multi-target artificial bee colony algorithm applicable to solving the multi-target optimization problem is provided. In the path planning process, multiple performance indexes of path length, smoothness and safety are considered in the algorithm, and a group of Pareto optimum paths can be acquired through one-step path planning. The path planning method belongs to meta-heuristic intelligent optimization methods, is different from the traditional single-target path planning method, and can well adapt to path planning tasks in complex environment.

Multi robot path planning method based on multi-target artificial bee colony algorithm

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Yang Li

Author Tools

Chat about Author