Reactive Navigation of a Mobile Robot Using a Hierarchical Set of Learning Agents

Frédéric Davesne (1) , Claude Barret (1)

1 CEMIF-SC - Groupe Systèmes Complexes

Within the context of learning sequences of basic tasks to build a complex behavior, a method is proposed which uses a hierarchical set of incrementally learning agents. Each one has to respect a particular perceptive constraint. To do so, an agent must choose either to execute basic tasks or to call another agent in order to use its decision-making competences, according to its perception. The learning procedure of each agent is achieved by a reinforcement learning inspired algorithm based on an heuristic which does not need internal parameters. A validation of the method is given, using a simulated Khepera robot. A hierarchical set of 4 agents is created. Each one is dedicated to the exploitation of particular perceptive data. They use 5 basic tasks in order to achieve a goal-reaching behavior which is formulated by a high level strategy composed of logical rules using perceptive primitives.

Keywords: constraint based learning; reinforcement learning; reactive navigation

Domains: Machine Learning [cs.LG]; Robotics [cs.RO]

Frédéric Davesne, Claude Barret. Reactive Navigation of a Mobile Robot Using a Hierarchical Set of Learning Agents. Intelligent Robots and Systems conference (IROS '99), Oct 1999, Kyongju, South Korea. pp.482--487, ⟨10.1109/IROS.1999.813050⟩. ⟨hal-00343201⟩