微分可能な空間計画のためのTransformer
Differentiable Spatial Planning using Transformers
障害物マップから長距離の空間依存を考慮して経路計画を学習するTransformerベースのプランナSPTを提案し、操作・ナビゲーションタスクで既存の微分可能プランナを7〜19%上回った。
著者: Devendra Singh Chaplot, Deepak Pathak, Jitendra Malik
分類: cs.LG, cs.AI, cs.CV, cs.RO
原文アブストラクト
We consider the problem of spatial path planning. In contrast to the classical solutions which optimize a new plan from scratch and assume access to the full map with ground truth obstacle locations, we learn a planner from the data in a differentiable manner that allows us to leverage statistical regularities from past data. We propose Spatial Planning Transformers (SPT), which given an obstacle map learns to generate actions by planning over long-range spatial dependencies, unlike prior data-driven planners that propagate information locally via convolutional structure in an iterative manner. In the setting where the ground truth map is not known to the agent, we leverage pre-trained SPTs in an end-to-end framework that has the structure of mapper and planner built into it which allows seamless generalization to out-of-distribution maps and goals. SPTs outperform prior state-of-the-art differentiable planners across all the setups for both manipulation and navigation tasks, leading to an absolute improvement of 7-19%.
