Adaptive critic-based neuro-fuzzy controller in multi-agents: Distributed behavioral control and path tracking

Authors:
Ramin Vatankhah;Shahram Etemadi;Aria Alasty;Gholamreza Vossoughi
Affiliations:
Center of Excellence in Design, Robotics, and Automation (CEDRA), School of Mechanical Engineering, Sharif University of Technology, P.O. Box 11365-9567, Azadi Avenue, Tehran, Iran;Department of Mechanical and Aerospace Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran;Center of Excellence in Design, Robotics, and Automation (CEDRA), School of Mechanical Engineering, Sharif University of Technology, P.O. Box 11365-9567, Azadi Avenue, Tehran, Iran;Center of Excellence in Design, Robotics, and Automation (CEDRA), School of Mechanical Engineering, Sharif University of Technology, P.O. Box 11365-9567, Azadi Avenue, Tehran, Iran
Venue:
Neurocomputing
Year:
2012

Citing 10
Cited 1

Real-time obstacle avoidance for manipulators and mobile robots

International Journal of Robotics Research
Adaptive critic designs: a case study for neurocontrol

Neural Networks
Group Behaviors for Systems with Significant Dynamics

Autonomous Robots
Artificial Intelligence: A Modern Approach

Artificial Intelligence: A Modern Approach
Experimental Study on Self-organized and Error Resistant Control of Distributed Autonomous Robotic Systems

International Journal of Robotics Research
Tracking and formation control of multiple autonomous agents: A two-level consensus approach

Automatica (Journal of IFAC)
Technical communique: Distributed observers design for leader-following control of multi-agent networks

Automatica (Journal of IFAC)
Adaptive critic autopilot design of Bank-to-turn missiles using fuzzy basis function networks

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Reinforcement structure/parameter learning for neural-network-based fuzzy logic control systems

IEEE Transactions on Fuzzy Systems
Learning and tuning fuzzy logic controllers through reinforcements

IEEE Transactions on Neural Networks

Dynamic adaptive learning algorithm based on two-fuzzy neural-networks

Neurocomputing

Quantified Score

Hi-index	0.01

Visualization

Abstract

In this paper, we follow two control tasks in a leader following frame with undirected network and local communications. As the first goal, distributed behavioral imitation, which is necessary to fit agents with complicated motion equations in kinematic frames, is discussed. Providing real agents with behavioral controller makes them capable to act as a kinematic particle. The second goal is to design an active leading strategy for the LA to move the group on a predefined path. Both problems can be mathematically modeled in an affine form, which is the reason behind using a unique adaptive controller to solve them. The controller is based on a neuro-fuzzy structure with critic-based leaning structure. It is shown that the proposed controller can successfully handle both tasks.