Incremental learning from basic reflexes in an autonomous mobile robot
This paper proposes a learning system for an autonomous mobile robot that must navigate in its environment through its own sensors. The system consists of two main components: first, simple basic reflexes are used to determine suitable actions for new situations that the robot has not observed before; second, the system uses a dynamical self-organising map (DSOM) to construct a mapping from different sensory situations to appropriate actions. The DSOM was developed to fulfil the requirements of real time operation and on-line learning during navigation. The viability of the proposed control strategy for autonomous mobile robots is demonstrated with a simulated Nomad 200 mobile robot that learns safely and quickly to navigate in its environments, minimising the need for human guidance during learning and operating.
Bibliographic Reference: Paper presented: International Conference on Engineering Applications of Neural Networks, Espoo (FI), August 21-23, 1995
Availability: Available from (1) as Paper EN 39235 ORA
Record Number: 199511237 / Last updated on: 1995-10-13
Original language: en
Available languages: en