arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.06035cs.CVcs.GRcs.RO
收藏

InterPrior:为基于物理的人-物体交互扩展生成控制

InterPrior: Scaling Generative Control for Physics-Based Human-Object Interactions

University of Illinois Urbana-Champaign(伊利诺伊大学厄巴纳-香槟分校);Amazon(亚马逊)

Sirui Xu, Samuel Schulter, Morteza Ziyadi, Xialin He, Xiaohan Fei, Yu-Xiong Wang, Liangyan Gui

AI总结:

InterPrior通过大规模模仿预训练和强化学习微调,扩展生成控制以实现人形机器人在多样环境下泛化移动-操作技能。

摘要:

人类很少在显式的全身运动层面规划与物体的全身交互。高层次意图,如可能性,定义了目标,而协调的平衡、接触和操作可以自然地从底层的物理和运动先验中产生。扩展此类先验是使人形机器人能够在多样化的上下文中组合和泛化移动-操作技能,同时保持物理上一致的全身协调的关键。为此,我们介绍了InterPrior,一个可扩展的框架,通过大规模模仿预训练和后训练强化学习学习统一的生成控制器。InterPrior首先将完整的模仿专家蒸馏成一个多功能、目标条件的变分策略,该策略从多模态观察和高层次意图中重建运动。虽然蒸馏的策略能够重建训练行为,但由于大规模人-物体交互的配置空间广阔,它无法可靠地泛化。为了解决这一问题,我们应用数据增强与物理扰动,并随后进行强化学习微调,以提高在未见目标和初始条件上的能力。这些步骤将重建的潜在技能整合到一个有效的流形中,产生一个能够超越训练数据的运动先验,例如,它可以纳入新的行为,如与未见物体的交互。我们进一步展示了其在用户交互控制中的有效性及其在真实机器人部署中的潜力。

英文摘要:

Humans rarely plan whole-body interactions with objects at the level of explicit whole-body movements. High-level intentions, such as affordance, define the goal, while coordinated balance, contact, and manipulation can emerge naturally from underlying physical and motor priors. Scaling such priors is key to enabling humanoids to compose and generalize loco-manipulation skills across diverse contexts while maintaining physically coherent whole-body coordination. To this end, we introduce InterPrior, a scalable framework that learns a unified generative controller through large-scale imitation pretraining and post-training by reinforcement learning. InterPrior first distills a full-reference imitation expert into a versatile, goal-conditioned variational policy that reconstructs motion from multimodal observations and high-level intent. While the distilled policy reconstructs training behaviors, it does not generalize reliably due to the vast configuration space of large-scale human-object interactions. To address this, we apply data augmentation with physical perturbations, and then perform reinforcement learning finetuning to improve competence on unseen goals and initializations. Together, these steps consolidate the reconstructed latent skills into a valid manifold, yielding a motion prior that generalizes beyond the training data, e.g., it can incorporate new behaviors such as interactions with unseen objects. We further demonstrate its effectiveness for user-interactive control and its potential for real robot deployment.

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。

↑