失敗から学べる世界へ:ナビゲーションエージェントのためのポリシー条件付き環境生成
From Failures to Learnable Worlds: Policy-Conditioned Environment Generation for Navigation Agents
事前学習済みナビゲーションエージェントの失敗モードをLLMで分析し、その弱点を狙った訓練環境を自動生成することで、適応性能を向上させるフレームワークWEDGE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: Yue Zhang, Han Lin, Zun Wang, Yidong Huang, Zaid Khan, Mohit Bansal
分類: cs.RO, cs.AI, cs.CV
原文アブストラクト
Simulated environments enable scalable training data generation for embodied agents, but more data does not necessarily provide what a particular agent needs to learn. Existing environment-generation pipelines largely optimize generic properties such as realism, diversity, or task coverage, while different pretrained policies can fail for different environmental reasons. We therefore introduce WEDGE, a framework for weakness-guided navigation learning in which the failure modes of a pretrained agent guide the generation of training environments at each adaptation round. Given a pretrained policy, WEDGE uses an LLM to propose executable weakness features from contrasting successful and failed rollouts, automatically validates them on the diagnostic set, and selects the strongest validated weakness based on its success-rate gap. The validated weaknesses are then mapped to the environmental factors that control them. WEDGE varies these factors to construct environments in the difficulty regimes where the policy struggles, producing targeted training experience for adaptation. Across three navigation agents with different adaptation mechanisms, we find that policies exhibit distinct weakness profiles and benefit from different training environments. Weakness-conditioned adaptation consistently outperforms matched random and hard-example alternatives on ProcTHOR, while the resulting gains for Uni-NaVid and Gemini also extend to HM3D after ProcTHOR adaptation. Iterative re-diagnosis further shows that dominant weaknesses can persist or shift as the policy improves, providing updated guidance for subsequent environment construction. Together, these results show that policy failures are not only diagnostic signals, but actionable guidance for constructing training environments that target a policy's current weaknesses.
関連論文
- HM3D-M3: マルチエージェント・マルチモーダル・マルチオブジェクト目標ナビゲーションのベンチマークナビゲーション
- GS-PRM: ガウスビジュアルロードマップによる画像ゴールナビゲーションナビゲーション
- S³-Nav: 言語誘導ロボットナビゲーションのための構造化空間-意味意思決定ナビゲーション
- 幾何学的候補モードを用いたマルチモーダル実演からのナビゲーション学習ナビゲーション
- 有界外乱下における複数障害物間の安全な一輪車ナビゲーション:学習拡張型CLF-CBFアプローチナビゲーション
- DR-VLA: 一人称視点のWeb動画からドメイン不変なシーン表現を介して人間らしい四足歩行ナビゲーションを学習ナビゲーション