인간형 로봇의 고속 스프린팅과 선회 동작 학습, 7 m/s 초과 달성
Push the Limit: Learning High-Speed Sprinting and Aggressive Cornering on a Full-Scale Humanoid
- 매체
- arXiv
- 게시
- 중요도
- 2/5
- 화제 지수
- —
한국어 요약
이족 인간형 로봇이 7 m/s 이상의 스프린팅과 몸 기울임 25도의 고속 선회 동작을 학습하는 프레임워크를 제시했다. 고속에서 발생하는 고주파 요 진동을 명시적으로 모델링하기 위해 인과적 멀티헤드 어텐션을 도입하고, 요 각속도 대신 저주파 속도 방향 보상을 설계해 자연스러운 보행 진동을 유지하면서 민첩한 회전이 가능하도록 했다. 시뮬레이션과 실제 로봇 배치에서 안정적인 고속 스프린팅과 공격적 선회를 입증했다.
원문 발췌 · English
We present a learning-based framework that enables a full-scale bipedal humanoid to sprint at over 7 m/s with motion-prior-guided gait and perform aggressive cornering at high speed with a pronounced trunk lean of up to $25^\circ$. Achieving this combination is challenging: above approximately 4 m/s, periodic foot impacts induce severe, high-frequency yaw-rate oscillations intrinsic to high-speed gaits. This high-frequency temporal structure corrupts the history of proprioceptive feedback that flat-MLP policies rely on, while rendering conventional yaw-rate tracking rewards counterproductive, as they fight against the robot's natural oscillatory dynamics. Moreover, a single style prior shared across skills cannot tell which skill is commanded and inherently compromises the low-speed skill fidelity. To overcome these limitations, we adopt a causal multi-head attention (MHA) module to explicitly model the high-frequency temporal feedback. In place of the oscillatory yaw rate, we design a heading-direction reward that supervises only the low-frequency velocity direction, allowing agile turning at high speed without suppressing natural gait oscillations. We further introduce skill-conditioned multi-adversarial-motion-prior (MAMP) discriminators that condition the style reward on the commanded skill. Ablation experiments confirm that each mechanism is essential: replacing structured temporal encoding with a flat-history MLP caps the top speed; reverting to yaw-rate tracking prevents high-speed turning; and a single shared discriminator makes in-place turning collapse into a quasi-static stance. Our framework bridges the gap between raw sprinting speed and reference-motion fidelity, demonstrating stable high-speed sprinting and aggressive cornering in both simulation and real-robot deployment.