OpenHEART: Opening Heterogeneous Articulated Objects with a Legged Manipulator
This work provides a more robust and sample-efficient method for legged manipulators to interact with heterogeneous articulated objects, which is a common challenge for mobile manipulation in unstructured environments.
This paper addresses the challenge of legged manipulators opening diverse articulated objects by proposing a framework that uses a compact low-dimensional representation of object geometry and an estimator for articulation information. The framework was successfully deployed on various objects in both simulation and real-world robot systems.
Legged manipulators offer high mobility and versatile manipulation. However, robust interaction with heterogeneous articulated objects, such as doors, drawers, and cabinets, remains challenging because of the diverse articulation types of the objects and the complex dynamics of the legged robot. Existing reinforcement learning (RL)-based approaches often rely on high-dimensional sensory inputs, leading to sample inefficiency. In this paper, we propose a robust and sample-efficient framework for opening heterogeneous articulated objects with a legged manipulator. In particular, we propose Sampling-based Abstracted Feature Extraction (SAFE), which encodes handle and panel geometry into a compact low-dimensional representation, improving cross-domain generalization. Additionally, Articulation Information Estimator (ArtIEst) is introduced to adaptively mix proprioception with exteroception to estimate opening direction and range of motion for each object. The proposed framework was deployed to manipulate various heterogeneous articulated objects in simulation and real-world robot systems. Videos can be found on the project website: https://openheart-icra.github.io/OpenHEART/