Improved training via incremental learning
Proceedings of the sixth international workshop on Machine learning
Niching methods for genetic algorithms
Niching methods for genetic algorithms
Lazy learning
Decision Tree Induction Based on Efficient Tree Restructuring
Machine Learning
An algorithm for planning collision-free paths among polyhedral obstacles
Communications of the ACM
Introduction to AI Robotics
Robot Motion Planning
Intelligent Adaptive Mobile Robot Navigation
Journal of Intelligent and Robotic Systems
Design of an unmanned ground vehicle, bearcat III, theory and practice
Journal of Robotic Systems - Intelligent Ground Vehicle Competition (IGVC) 2003 Special Issue (Part 2)
Evolutionary Route Planner for Unmanned Air Vehicles
IEEE Transactions on Robotics
On the behavior-based architectures of autonomous agency
IEEE Transactions on Systems, Man, and Cybernetics, Part C: Applications and Reviews
Adaptive evolutionary planner/navigator for mobile robots
IEEE Transactions on Evolutionary Computation
Fitness sharing and niching methods revisited
IEEE Transactions on Evolutionary Computation
A layered goal-oriented fuzzy motion planning strategy for mobile robot navigation
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Adaptive behavior navigation of a mobile robot
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans
Evolutionary learning of fuzzy logic controllers and their adaptation through perpetual evolution
IEEE Transactions on Fuzzy Systems
Algorithms and performance analysis for path navigation of Ackerman-steered autonomous robots
PerMIS '08 Proceedings of the 8th Workshop on Performance Metrics for Intelligent Systems
Hi-index | 0.00 |
In this paper we propose a novel waypoint-based robot navigation method that combines reactive and deliberative actions. The approach uses reactive exploration to generate waypoints that can then be used by a deliberative system to plan future movements through the same environment. The waypoints are used largely to provide the interface between reactive and deliberative navigation and a range of methods could be used for either type of navigation. In the current work, an incremental decision tree method is used to navigate the robot reactively from the specified initial position to its destination avoiding obstacles in its path and a genetic algorithm method is used to perform the deliberative navigation. The new method is shown to have a number of practical advantages. Firstly, in contrast with many deliberative approaches, complete knowledge of the environment is not required, nor is it necessary to make assumptions regarding the geometry of obstacles. Secondly, the presence of a reactive navigator means it is always possible to continue directed movements in unknown or changing environments or when time constraints become particularly demanding. Thirdly, the use of waypoints allows escape from certain obstacle configurations that would normally trap robots navigated under the control of purely reactive methods. In addition, the results presented in this paper from a number of realistic simulated environments show that the adoption of waypoints significantly reduces the time to calculate a deliberative path.