ParkourFormer：予測的監督と系列モデリングをパルクール移動に統合する
ParkourFormer: Integrating Predictive Supervision and Sequence Modeling into Parkour Locomotion
ヒューマノイドのパルクール移動を未来条件付き意思決定問題として再構成し、Transformerベースの系列モデリングで将来の身体状態を予測して行動生成に活用するフレームワークを提案。シミュレーションと実機で高い成功率を達成した。
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: Yanheng Mai, Wenhao Xu, Zirui Huang, Yifei Fu, Shengwei Dong, Xinjue Wang, Kailun Huang, Yanzhe Xie, Renjing Xu
分類: cs.RO
原文アブストラクト
Humanoid parkour requires locomotion policies to coordinate whole-body dynamics across rapidly changing terrains such as stairs, gaps, slopes, and obstacles. Existing reinforcement learning policies are largely reactive, mapping observations directly to actions without explicitly modeling future body states. Such modeling becomes critical in agile locomotion tasks where successful motion execution depends strongly on anticipating upcoming contact transitions and body dynamics. We present ParkourFormer, a Transformer-based sequence modeling framework that reformulates humanoid locomotion as a future-conditioned decision-making problem. The current robot state queries historical sensorimotor trajectories through cross-attention, while a lightweight prediction head forecasts short-horizon future proprioceptive states. The predicted future states, trained with supervised signals, are fused with temporal features to generate actions, enabling the policy to jointly reason over motion history and anticipated future dynamics. We evaluate ParkourFormer on a diverse multi-terrain humanoid parkour benchmark including stairs, gaps, slopes, rough terrain, and obstacle traversal. Experiments in simulation and on a real humanoid robot show that ParkourFormer achieves a 93.85% average traversal success rate on highly challenging terrains, with improvements of up to 47.12% over strong MLP, MoE-based MLP, and vanilla Transformer baselines, while maintaining a single unified policy across all terrain types. These results demonstrate that explicit future-state modeling significantly improves robustness and generalization for agile whole-body locomotion.
