Self-organizing Internal Representation in Learning of Navigation: A Physical Experiment by the Mobile Robot YAMABICO
✍ Scribed by Jun Tani; Naohiro Fukumura
- Publisher
- Elsevier Science
- Year
- 1997
- Tongue
- English
- Weight
- 623 KB
- Volume
- 10
- Category
- Article
- ISSN
- 0893-6080
No coin nor oath required. For personal study only.
✦ Synopsis
Z7dspaper discusses a novel schemefor sensory-bosednavigation of a mobile robot. In our previous work (Tani & Fukumura, 1994, Neural Networks, 7(3), 553-563), weformulated the problem of goal-directed navigation as an embealiing problem of dynamical systems: desired trajectories in a task space should be embedded in an oakquate sensory-based internal state space so that a unique mappingfrom the internal state space to the motor command could be established. In the current formulation a recurrent neural network k employed, which shows that an adequate internal state space can be self-organized, throughsupervised training with serrsorimotor sequences. The experiment was conducted using a real mobile robot equipped with a laser range sensor, demonstrating the valtiity of the presented scheme by working in a noisy real-world environment.