Neural network based path planning for a multi-robot system with moving obstacles

摘要

Recently, a Coordinated Hybrid Agent (CHA) framework was proposed for the control of Multi-Agent Systems (MASs). In the past few years, it has been applied to both homogeneous and heterogeneous multi-agent systems. In previous studies, the coordination among agents were implemented based on the designer’s knowledge of the system. For large complex systems, it would be desirable if we can plan the coordination among agents dynamically. It was demonstrated that an intelligent planner can be designed for the CHA framework to automatically generate desired actions for multiple robots in a multi-agent system. However, in previous studies, only static obstacles in the environment were considered. In this paper, a neural network based approach is proposed for a multi-robot system with moving obstacles. A biologically inspired neural network based intelligent planner is designed for the coordination of multi-agent systems. The dynamics of each neuron in the topologically organized neural network is characterized by a shunting neural equation. 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 objective for building the intelligent planner is to plan actions for multiple mobile robots to coordinate with others and to achieve the global goal. 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 virtual physical world is built using Vortex to test and develop navigation strategies for robot platforms. 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 an intelligent planner can be designed for the CHA framework to control a large complex system so that coordination among agents can be achieved.