论文信息 - Learing Fine Motion by Using the Hierarchical Extended Kohonen Map

Learing Fine Motion by Using the Hierarchical Extended Kohonen Map

A Hierarchical Extended Kohonen Map (HEKM) learns to associate actions to perceptions under the supervision of a planner: they cooperate to solve path finding problems. We argue for the utility of using the hierarchical version of the KM instead of the “flat” KM. We measure the benefits of cooperative learning due to the interaction of neighboring neurons in the HEKM. We highlight a beneficial side-effect obtained by transferring motion skill from the planner to the HEKM, namely, smoothness of motion.

Luca Maria Gambardella | Cristina Versino

[1] Helge J. Ritter,et al. Neural computation and self-organizing maps - an introduction , 1992, Computation and neural systems series.

[2] Bernardo A. Huberman. Computation: The Micro and the Macro View , 1992 .

[3] Tad Hogg,et al. Cooperative Problem solving , 1992, Computation: The Micro and the Macro View.

[4] José del R. Millán,et al. Reinforcement learning of goal-directed obstacle-avoiding reaction strategies in an autonomous mobile robot , 1995, Robotics Auton. Syst..

[5] Erkki Oja,et al. From Situations to Actions: Motion Behavior Learning by Self-Organization , 1993 .

[6] Luca Maria Gambardella,et al. Learning high-level navigation strategies from sensor information and planner experience , 1994, Proceedings of PerAc '94. From Perception to Action.

[7] Bernd Fritzke,et al. A Growing Neural Gas Network Learns Topologies , 1994, NIPS.

[8] Joost N. Kok,et al. Robot motion planning in unknown environments using Neural Networks , 1996 .