Dynamic path planning of a mobile robot with improved Q-learning algorithm
Authors:
- 1 August 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 409-414
Abstract
Path planning of a mobile robot under dynamic environment is a difficult part of robot navigation. In this paper, a new path planning method based on improved Q-learning (IQL) algorithm and some heuristic searching strategies is proposed for mobile robot in dynamic environment. A new exploration strategy which combines ε-greedy exploration with Boltzmann exploration is used in IQL. In addition, the heuristic searching strategies are provided to reduce the search space and limit the variation range of orientation angle. From simulations, the better performance of the proposed method was certified in terms of time taken and optimal path comparison with classical Q-learning (CQL) and other planning methods. Meanwhile, the reduction in orientation angle and path length has significance in the robotics literature of the energy consumption.Keywords
This publication has 15 references indexed in Scilit:
- SmartPATH: An Efficient Hybrid ACO-GA Algorithm for Solving the Global Path Planning Problem of Mobile RobotsInternational Journal of Advanced Robotic Systems, 2014
- Dynamic robot path planning using an enhanced simulated annealing approachApplied Mathematics and Computation, 2013
- A Deterministic Improved Q-Learning for Path Planning of a Mobile RobotIEEE Transactions on Systems, Man, and Cybernetics: Systems, 2013
- Robot path planning in uncertain environment using multi-objective particle swarm optimizationNeurocomputing, 2013
- Real-Time Robot Path Planning Based on a Modified Pulse-Coupled Neural Network ModelIEEE Transactions on Neural Networks, 2009
- Information-Driven Sensor Path Planning by Approximate Cell DecompositionIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2009
- A minimum-time trajectory planning method for two robotsIEEE Transactions on Robotics and Automation, 1992
- Q-learningMachine Learning, 1992
- Path planning for a mobile robotIEEE Transactions on Systems, Man, and Cybernetics, 1992
- Motion planning in a plane using generalized Voronoi diagramsIEEE Transactions on Robotics and Automation, 1989