C4.5: programs for machine learning
C4.5: programs for machine learning
Noise modelling and evaluating learning from examples
Artificial Intelligence
Using Machine Learning Techniques in Real-World Mobile Robots
IEEE Expert: Intelligent Systems and Their Applications
Incremental Induction of Decision Trees
Machine Learning
Decision Tree Induction Based on Efficient Tree Restructuring
Decision Tree Induction Based on Efficient Tree Restructuring
A Kolmogorov-Smirnoff Metric for Decision Tree Induction
A Kolmogorov-Smirnoff Metric for Decision Tree Induction
Improved use of continuous attributes in C4.5
Journal of Artificial Intelligence Research
Hi-index | 0.00 |
This paper presents a new approach to the intelligent navigation of a mobile robot. The hybrid controlarchitecture described combines properties of purely reactive and behaviour-based systems, providing the ability both tolearn automatically behaviours from inception, and to capture these in a distributed hierarchy of decision tree networks. Therobot is first trained in the simplest world which has no obstacles, and is then trained in successively more complex worlds,using the knowledge acquired in the previous worlds. Each world representing the perceptual space is thus directly mappedon a unique rule layer which represents in turn the robot action space encoded in a distinct decision tree. A major advantageof the current implementation, compared with the previous work, is that the generated rules are easily understood by humanusers. The paper demonstrates that the proposed behavioural decomposition approach provides efficient management ofcomplex knowledge, and that the learning mechanism is able to cope with noise and uncertainty in sensory data.