Extended Q-learning algorithm for path-planning of a mobile robot

Authors:
Indrani Goswami;Pradipta Kumar Das;Amit Konar;R. Janarthanan
Affiliations:
ETCE Department, Jadavpur University, Kolkata, India;Dhaneswar Rath Institute of Engineering and Management Studies, Tangi, Cuttack, Orissa;ETCE Department, Jadavpur University, Kolkata, India;Jaya Engineering College, Tamilnadu
Venue:
SEAL'10 Proceedings of the 8th international conference on Simulated evolution and learning
Year:
2010

Citing 5
Cited 0

Technical Note: \cal Q-Learning

Machine Learning
Computational Intelligence: Principles, Techniques and Applications

Computational Intelligence: Principles, Techniques and Applications
Cooperative multi-robot path planning using differential evolution

Journal of Intelligent & Fuzzy Systems: Applications in Engineering and Technology - Theoretical advances of intelligent paradigms
Reinforcement Learning and Dynamic Programming Using Function Approximators

Reinforcement Learning and Dynamic Programming Using Function Approximators
Adaptive evolutionary planner/navigator for mobile robots

IEEE Transactions on Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we study the path planning for Khepera II mobile robot in a grid map environment using an extended Q-learning algorithm. The extension offers an additional benefit of avoiding unnecessary computations involved to update the Q-table. A flag variable is used to keep track of the necessary updating in the entries of the Q-table. The validation of the algorithm is studied through real time execution on Khepera-II platform. An analysis reveals that there is a significant saving in time- and space- complexity of the proposed algorithm with respect to classical Q-learning.