CoRL 2020, Spotlight Talk 442: Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps

CoRL 2020

CoRL 2020, Spotlight Talk 442: Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps

Dec 16, 2020
|
28 views
Details
"**Hierarchical Robot Navigation in Novel Environments using Rough 2-D Maps** Chengguang Xu (Northeastern University)*; Christopher Amato (Northeastern University); Lawson Wong (Northeastern University) Publication: http://corlconf.github.io/paper_442/ **Abstract** In robot navigation, generalizing quickly to unseen environments is essential. Hierarchical methods inspired by human navigation have been proposed, typically consisting of a high-level landmark proposer and a low-level controller. However, these methods either require precise high-level information to be given in advance, or need to construct such guidance from extensive interaction with the environment. In this work, we propose an approach that leverages a rough 2-D map of the environment to navigate in novel environments without requiring further learning. In particular, we introduce a dynamic topological map that can be initialized from the rough 2-D map along with a high-level planning approach for proposing reachable 2-D map patches of the intermediate landmarks between the start and goal locations. To use proposed 2-D patches, we train a deep generative model to generate intermediate landmarks in observation space which are used as subgoals by low-level goal-conditioned reinforcement learning. Importantly, because the low-level controller is only trained with local behaviors (e.g. go across the intersection, turn left at a corner) on existing environments, this framework allows us to generalize to novel environments given only a rough 2-D map, without requiring further learning. Experimental results demonstrate the effectiveness of the proposed framework in both seen and novel environments."

Comments
loading...