CAP：通过学习去噪实现连续自适应感知缺失的人形机器人 locomotion
CAP: Continuously Adaptive Perception-Blind Humanoid Locomotion via Learned Denoising
- Fudan University（复旦大学）
- TARS Robotics（TARS机器人公司）
- Shanghai Innovation Institute（上海创新研究院）
- Harbin Institute of Technology（哈尔滨工业大学）
- Shanghai Jiao Tong University（上海交通大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对人形机器人外部感知不可靠问题，提出单阶段策略 CAP，用学习去噪恢复损坏深度并融合本体感觉，在仿真和 Unitree G1 上实现感知鲁棒 locomotion。
AI中文摘要：
在复杂地形上的人形机器人 locomotion 需要前瞻性的外部感知来预判障碍，然而在现实部署中该信号并不可靠，会部分且间歇性地失效。现有感知策略通常假设深度观测保持干净且分布内，而近期统一感知与盲控制的尝试通常在不同子策略之间进行路由或切换，未能利用部分损坏深度中可恢复的信息。我们提出 CAP，一种单阶段人形机器人 locomotion 策略，通过一个感知世界模型编码器（训练为学习型去噪器，从损坏输入重建干净深度）恢复该信号，并配以一个共激活的本体感觉变分编码器，提供无深度身体状态信息。一种耦合训练方案将世界模型输入上的深度噪声课程与策略面向潜在特征上的世界模型特征丢弃相结合，使策略暴露于整个感知质量谱的失败中。在仿真中，当深度保持信息性时，CAP 匹配或优于感知基线，且随着感知恶化，其退化比二元切换基线更平滑。在 Unitree G1 上，对照试验和室内外部署证明了在间歇性遮挡、真实传感器损坏和室外深度伪影下的感知鲁棒 locomotion。
英文摘要：
Humanoid locomotion across complex terrain demands forward-looking exteroception to anticipate obstacles, yet this signal is unreliable in real-world deployment, failing partially and intermittently. Existing perceptive policies often assume that depth observations remain clean and in-distribution, while recent attempts to unify perceptive and blind control typically route or switch between separate sub-policies, leaving recoverable information in partially corrupted depth unexploited. We instead propose CAP, a single-stage humanoid locomotion policy that recovers this signal with a perceptive world-model encoder trained as a learned denoiser to reconstruct clean depth from a corrupted input, together with a co-active proprioceptive variational encoder that supplies depth-free body-state information. A coupled training recipe pairs a depth-noise curriculum on the world-model input with world-model feature dropout on the policy-facing latent, exposing the policy to failures across the entire perception-quality spectrum. In simulation, CAP matches or improves upon perceptive baselines when depth remains informative, and degrades more smoothly than a binary-switching baseline as perception worsens. On the Unitree G1, controlled trials and indoor-outdoor deployments demonstrate perception-robust locomotion under intermittent occlusion, real-sensor corruption, and outdoor depth artifacts.
