衝突を考慮した非重複パラメータ学習による統一予測と計画
Unified Prediction and Planning via Conflict-Aware Disjoint Parameter Training
混雑環境でのロボットナビゲーションにおいて、予測と計画を同時に行う統一モデルで生じる表現の衝突(スキル競合)を特定し、タスクごとに重要なパラメータを分離して学習・マージする新しいフレームワークDPT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: Taewon Seo, Seonae Jeon, Giwon Lee, Kuk-Jin Yoon, Daehee Park
分類: cs.RO, cs.CV
原文アブストラクト
Accurate motion prediction of surrounding agents and safe motion planning are two closely coupled key tasks for social robot navigation in crowded environments. Deploying these systems on resource-constrained edge devices necessitates compact, unified models that can perform both tasks simultaneously. However, within these compact shared encoders, recent unified models often overlook severe representational conflicts that arise from the distinct objectives of predicting neighbor behaviors versus ego-centric safety planning. To address this issue, we first identify the Skill Conflict$\unicode{x2014}$a phenomenon where overlapping parameter assignments cause distinct tasks to compete for the same weights, preventing the model from fully specializing in individual skills. To resolve this, we propose a novel model-merging-based framework, Disjoint Parameter Training (DPT). DPT mitigates performance degradation caused by Skill Conflict through distributed parameter learning, which separates the key parameter regions of each task while preserving their core capabilities prior to merging. In addition, we observe that sparse merging, which selectively integrates only the most influential parameters for each task rather than combining all task-specific parameters, yields optimal performance by preventing interference among adjacent features and concentrating representational capacity. DPT can be applied in parallel with a variety of merging methods. Evaluated on standard crowd navigation benchmarks (JRDB and JTA), our framework demonstrates superior performance, validating its versatility and effectiveness for safe, resource-efficient robot navigation.
