Neural-Network-Based Path Planning for a Multirobot System With Moving Obstacles

Recently, a coordinated hybrid agent (CHA) framework was proposed for the control of multiagent systems (MASs). It was demonstrated that an intelligent planner can be designed for the CHA framework to automatically generate desired actions for multiple robots in an MAS. However, in previous studies,...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on human-machine systems 2009-07, Vol.39 (4), p.410-419
Main Authors: Li, H., Yang, S.X., Seto, M.L.
Format: Article
Language:English
Subjects:
Applied sciences
Artificial intelligence
Automatic control
Commands
Computer science
control theory
systems
Computer simulation
Computer systems and distributed systems. User interface
Control systems
Control theory. Systems
Exact sciences and technology
Framework
hybrid systems
Intelligent robots
Learning and adaptive systems
Matlab
Modules
Moving obstacles
Multiagent systems
multiagent systems (MASs)
Multirobot systems
Multirobots
Neural networks
Neurons
Path planning
Robot kinematics
Robotics
Robotics and automation
Robots
Software
Weight control
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Recently, a coordinated hybrid agent (CHA) framework was proposed for the control of multiagent systems (MASs). It was demonstrated that an intelligent planner can be designed for the CHA framework to automatically generate desired actions for multiple robots in an MAS. However, in previous studies, only static obstacles in the workspace were considered. In this paper, a neural-network-based approach is proposed for a multirobot system with moving obstacles. A biologically inspired neural-network-based intelligent planner is designed for the coordination of MASs. A landscape of the neural activities for all neurons of a CHA agent contains information about the agent's local goal and moving obstacles. The proposed approach is able to plan the paths for multiple robots while avoiding moving obstacles. The proposed approach is simulated using both Matlab and Vortex. The Vortex module executes control commands from the control system module, and provides the outputs describing the vehicle state and terrain information, which are, in turn, used in the control module to produce the control commands. Simulation results show that the developed intelligent planner of the CHA framework can control a large complex system so that coordination among agents can be achieved.
ISSN:1094-6977
2168-2291
1558-2442
2168-2305
DOI:10.1109/TSMCC.2009.2020789