Problem
Research questions and friction points this paper is trying to address.
Human-Object Interaction
Learning from Demonstration
Humanoid Robots
Motion Retargeting
HOI-Retarget: Contact-Centric Retargeting for Human-Object Interaction
🤖 AI Summary
This study addresses the challenge of learning human-object interaction skills from demonstrations for humanoid robots, which is hindered by the lack of compatible reference data. To overcome this, it proposes a contact-centric windowed trajectory optimization method that retargets human interactions to robots. Under kinematic constraints, the approach jointly optimizes body tracking, foot support, and trajectory smoothness while targeting contact reconstruction. Notably, it introduces the first contact-centric retargeting mechanism based on windowed trajectory optimization, enabling single-demonstration augmentation across varying object sizes and extension to multi-robot collaboration. The method successfully transfers complex human-object interaction motions to humanoid platforms. Furthermore, the authors release both the source code and a large-scale retargeted motion dataset to facilitate future research in this domain.
📝 Abstract
Learning from demonstration (LfD) has enabled humanoid robots to acquire diverse whole-body skills, but extending this paradigm to human-object interaction (HOI) is limited by the availability of robot-compatible interaction references. We present HOI-Retarget, a contact-centric retargeting method that transfers HOI onto a humanoid robot for large-scale motion-data generation. Its windowed trajectory optimization uses every labeled contact as a target in the object frame, balancing body tracking, foot support and smoothness under the robot's kinematic limits. The method can augment a single demonstration across object sizes, absorb contacts reconstructed from monocular video, and extend to several robots manipulating one object. We publicly release the code and the retargeted motion dataset.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Human-Object Interaction
Contact-Centric Retargeting
Windowed Trajectory Optimization
Learning from Demonstration
Humanoid Robot
🔎 Similar Papers
No similar papers found.
