ゼロショット汎化可能な動作計画のためのニューラルナビゲーション関数
Neural Navigation Functions for Zero-Shot Generalizable Motion Planning
学習したナビゲーション関数を構造化された楕円型プランナーに組み込み、未知の環境形状に対してゼロショットで転移可能な衝突回避動作を生成する手法を提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Benjamin D. Shaffer, Pei-An Hsieh, Brooks Kinch, Nathaniel Trask, M. Ani Hsieh
分類: cs.RO, cs.LG
原文アブストラクト
We introduce Neural Navigation Functions (Neural-NF), a learned reactive navigation function capable of zero-shot transfer across unseen environment geometries. Neural-NF places data-driven adaptation within a structured elliptic planner, where the navigation objective is learned while planner structure is preserved by construction. Specifically, intrinsic Laplacian-derived features are mapped to local PDE coefficients, and solving the resulting boundary value problem produces a globally consistent value function on each target domain. For every admissible learned model, the resulting policy is collision-free, provides monotonic descent and a global minimum at the goal by construction. This admits a linearly-solvable optimal-control interpretation for any parameter setting. Empirically, Neural-NF achieves strong zero-shot transfer across diverse geometries and outperforms learned planners that directly predict the value function by up to a $5\times$ improvement.
