Real-time robot path planning around complex obstacle patterns through learning and transferring options

摘要

We consider the problem of path planning in an initially unknown environment where a robot does not have an a priori map of its environment but has access to prior information accumulated by itself from navigation in similar but not identical environments. To address the navigation problem, we propose a novel, machine learning-based algorithm called Semi-Markov Decision Process with Unawareness and Transfer (SMDPU-T) where a robot records a sequence of its actions around obstacles as action sequences called options which are then reused by it to learn suitable, collision-free maneuvers around more complex obstacles in future. Our results illustrate that SMDPU-T takes 24% planning time and 39% total time to solve same navigation tasks as compared to a recent, sampling-based path planner.