Long-horizon humanoid navigation planning using traversability estimates and previous experience

Humanoids' abilities to navigate stairs and uneven terrain make them well-suited for disaster response efforts. However, humanoid navigation in such environments is currently limited by the capabilities of navigation planners. Such planners typically consider only footstep locations, but planning with palm contacts may be necessary to cross a gap, avoid an obstacle, or maintain balance. However, considering palm contacts greatly increases the branching factor of the search, leading to impractical planning times for large environments. Planning a contact transition sequence in a large environment is important because it verifies that the robot will be able to reach a given goal. In previous work we explored using library-based methods to address difficult navigation planning problems requiring palm contacts, but such methods are not efficient when navigating an easy-to-traverse part of the environment. To maximize planning efficiency, we would like to use discrete planners when an area is easy to traverse and switch to the library-based method only when traversal becomes difficult. Thus, in this paper we present a method that (1) Plans a torso guiding path which accounts for the difficulty of traversing the environment as predicted by learned regressors; and (2) Decomposes the guiding path into a set of segments, each of which is assigned a motion mode (i.e. a set of feet and hands to use) and a planning method. Easily-traversable segments are assigned a discrete-search planner, while other segments are assigned a library-based method that fits existing motion plans to the environment near the given segment. Our results suggest that the proposed approach greatly outperforms standard discrete planning in success rate and planning time. We also show an application of the method to a real robot in a mock disaster scenario.

Automated summary

This paper presents a method for efficient navigation planning by incorporating palm contacts, considering the difficulty of traversing the environment and using a combination of discrete planners and library-based methods. The results show that this approach greatly outperforms standard discrete planning in success rate and planning time.