Veeramani, Satheeshkumar and Muthuswamy, Sreekumar 2020. Reinforcement learning based path planning of the mobile agents with constrained locomotion for the material handling applications. Presented at: 4th Conference on Information & Communication Technology (CICT), Chennai, India, 3-5 Dec 2020. Proceedings: Conference on Information and Communication Technology (CICT). IEEE, 10.1109/cict51604.2020.9311923 |
Abstract
This paper presents the intelligent path planning model of the mobile base agent of SwarmItFIX robot with novel Swing and Dock (SaD) locomotion for material handling/transfer applications. In this work, the Markov Decision Process (MDP) path planning problem of SaD agent is solved using two Reinforcement Learning (RL) based dynamic programming methods viz Policy Iteration (PI), and Value Iteration (VI). Being tested with 16 different test cases, both the algorithms return the optimal sequence of steps with reduced makespan for the mobile agents to reach the goal positions positively. The results of both the methods were compared with each other in the section V, and found to be convincing. Hence the proposed control scheme is being implemented in the SwarmItFIX setup available at the University of Genova, Italy.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Date Type: | Publication |
Status: | Published |
Schools: | Engineering |
Publisher: | IEEE |
ISBN: | 9780738124476 |
Last Modified: | 10 Jun 2023 01:35 |
URI: | https://orca.cardiff.ac.uk/id/eprint/147582 |
Citation Data
Cited 2 times in Scopus. View in Scopus. Powered By Scopus® Data
Actions (repository staff only)
![]() |
Edit Item |