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.

翻译：人形机器人跑酷需要运动策略在楼梯、间隙、坡道、障碍物等快速变化地形上协调全身动力学。现有强化学习策略主要基于反应式控制，直接将观测映射为动作，未显式建模未来身体状态。在敏捷运动任务中，此类建模至关重要——成功执行动作高度依赖对即将到来的接触转换和身体动态的预判。本文提出ParkourFormer，一种基于Transformer的序列建模框架，将人形机器人运动重构成一个未来状态条件化的决策问题。当前机器人状态通过交叉注意力查询历史感觉运动轨迹，同时轻量级预测头输出短时域未来本体感受状态。经监督信号训练的未来状态与时序特征融合生成动作，使策略能够联合推理运动历史与预期未来动态。我们在包含楼梯、间隙、坡道、粗糙地形及障碍穿越的多地形人形机器人跑酷基准上评估ParkourFormer。仿真与实物人形机器人实验表明，在极具挑战性地形上，ParkourFormer平均穿越成功率达93.85%，相比强MLP、基于MoE的MLP及原生Transformer基线，性能提升最高达47.12%，同时所有地形类型仅维持单一统一策略。这些结果表明，显式未来状态建模显著提升了敏捷全身运动的鲁棒性与泛化能力。