arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2610.36825cs.RO
收藏

HC2Robot:用于多地形人形跑酷的带预测前瞻的超连接Transformer

HC2Robot: Hyper-Connection Transformers with Predicted Foresight for Multi-Terrain Humanoid Parkour

The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));CL-TECH;South China Agricultural University(华南农业大学);Southern University of Science and Technology(南方科技大学)

Wenhao Xu, Yanheng Mai, Yifei Fu, Nan Zheng, Yanbo Zhou, Zirui Huang, Mingsheng Ling, Xinjue Wang, Renjing Xu

AI总结:

该研究提出HC2Robot框架,含PFM和HC Transformer,解决人形跑酷的信息不对称问题,在多地形模拟中成功率达97.60%,安全落脚点率优于基线。

摘要:

人形跑酷要求机器人对高度不连续地形上的未来落脚点和全身运动进行推理。我们重新审视了感知人形运动的非对称演员-评论家学习中的信息不对称问题:评论家在训练期间利用特权模拟器信号,而可部署的演员仅依靠机载感知。我们认为关键不是向演员暴露特权信息,而是学习其可部署的近似表示,以缩小训练与部署之间的信息差距。我们提出了HC2Robot,这是一个可部署的感知人形跑酷框架,由预测前瞻模块(PFM)和超连接(HC)Transformer组成。PFM从可部署观测中预测每只脚下一次触地事件的策略条件时间、位置和支撑质量,将特权监督转换为可部署的潜在表示,为演员提供预测的触地信息,而无需特权运行时感知。HC Transformer通过可学习的多流路由进一步增强时间推理,同时未来运动预测头提供短视距运动先验用于正则化。在楼梯、间隙、高台和斜坡上,HC2Robot的平均模拟 traversal 成功率为97.60%,且比强大的感知运动基线始终更高的安全落脚点率,支持在可部署感知下提高 traversal 性能和几何落脚点支撑。

英文摘要:

Humanoid parkour requires robots to reason about future footholds and whole-body motions over highly discontinuous terrain. We revisit the information asymmetry in asymmetric actor-critic learning for perceptive humanoid locomotion: the critic exploits privileged simulator signals during training, whereas the deployable actor operates solely from onboard perception. We argue that the key is not exposing privileged information to the actor, but learning a deployable approximation of it to narrow the information gap between training and deployment. We present HC2Robot, a deployable perceptive humanoid parkour framework consisting of a Predicted Foresight Module (PFM) and a Hyper-Connection (HC) Transformer. PFM predicts from deployable observations the policy-conditioned timing, location, and support quality of each foot's next touchdown event, converting privileged supervision into a deployable latent representation that provides the actor with predicted touchdown information without privileged runtime sensing. The HC Transformer further enhances temporal reasoning through learnable multi-stream routing, while a future motion prediction head provides short-horizon motion priors for regularization. Across stairs, gaps, high platforms, and slopes, HC2Robot achieves a mean simulated traversal success rate of 97.60% and consistently higher safe foothold rates than strong perceptive locomotion baselines, supporting improved traversal performance and geometric foothold support under deployable sensing.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑