Journal
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
Volume 69, Issue 2, Pages 1319-1327Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TVT.2019.2958197
Keywords
Robot kinematics; Collision avoidance; Mobile robots; Planning; Navigation; Multi-robot systems; Potential Field Method (PFM); Artificial Neural Network (ANN); Particle Swarm Optimization (PSO); Coordination; Multi-Agent Systems (MAS)
Categories
Funding
- FCT - Fundacao para a Ciencia e a Tecnologia Project [GrantUID/EEA/50008/2019]
- Brazilian National Council for Research andDevelopment (CNPq) [309335/2017-5]
Ask authors/readers for more resources
Multi-robot navigation is a challenging task, especially for many robots, since individual gains may more often than not adversely affect the global gain. This paper investigates the problem of multiple robots moving towards individual goals within a common workspace whereas the motion of every individual robot is deduced by a novel Particle Swarm Optimization (PSO) tuned Feed Forward Neural Network (FFNN). Motion coordination among the robots is implemented using a cooperative coordination algorithm that identifies critical robots and maintains cooperation count while actuating deviation in select robots. The contribution of this paper is twofold; firstly in hybridizing the Artificial Neural Network(ANN) by employing PSO, an evolutionary algorithm, to find optimal values of deviation for every critical robot using velocity and acceleration constraints, secondly ensuing the convergence of the PSO by carrying first and second order stability analysis. Experiments have been carried out to evaluate and validate the efficacy of the proposed coordination schemes by changing the number of robots under hundred different scenarios each, and the founded results demonstrate the efficacy of the proposed schemes.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available