ELLIPSE: ロバストなウェイポイントと不確実性のための証拠学習
ELLIPSE: Evidential Learning for Robust Waypoints and Uncertainties
移動ロボットのウェイポイント予測を、多変量深層証拠回帰と軽量なデータ拡張、および等調再較正を用いてロバスト化し、不確実性の信頼性を高める手法を提案した。
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: Zihao Dong, Chanyoung Chung, Dong-Ki Kim, Mukhtar Maulimov, Xiangyun Meng, Harmish Khambhaita, Ali-akbar Agha-mohammadi, Amirreza Shaban
分類: cs.RO
原文アブストラクト
Robust waypoint prediction is crucial for mobile robots operating in open-world, safety-critical settings. While Imitation Learning (IL) methods have demonstrated great success in practice, they are susceptible to distribution shifts: the policy can become dangerously overconfident in unfamiliar states. In this paper, we present \textit{ELLIPSE}, a method building on multivariate deep evidential regression to output waypoints and multivariate Student-t predictive distributions in a single forward pass. To reduce covariate-shift-induced overconfidence under viewpoint and pose perturbations near expert trajectories, we introduce a lightweight domain augmentation procedure that synthesizes plausible viewpoint/pose variations without collecting additional demonstrations. To improve uncertainty reliability under environment/domain shift (e.g., unseen staircases), we apply a post-hoc isotonic recalibration on probability integral transform (PIT) values so that prediction sets remain plausible during deployment. We ground the discussion and experiments in staircase waypoint prediction, where obtaining robust waypoint and uncertainty is pivotal. Extensive real world evaluations show that \textit{ELLIPSE} improves both task success rate and uncertainty coverage compared to baselines.
