Multi-goal Trajectory Planning with Motion Primitives for Hexapod Walking Robot

摘要

This paper presents our early results on multi-goal trajectory planning with motion primitives for a hexapod walking robot. We propose to use an on-line unsupervised learning method to simultaneously find a solution of the underlying traveling salesman problem together with particular trajectories between the goals. Using this technique, we avoid pre-computation of all possible trajectories between the goals for a graph based heuristic solvers for the traveling salesman problem. The proposed approach utilizes principles of self-organizing map to steer the randomized sampling of configuration space in promising areas regarding the multi-goal trajectory. The presented results indicate the proposed steering mechanism provides a feasible multi-goal trajectory in a less number of samples than an approach based on a priori known sequence of the goals visits.