Impedance control improves robot handling of hinged and sliding objects
Constraint-Decomposed Impedance Control from Generative Policy for Articulated Object Manipulation
Robotics
Summary
Robots often struggle with objects that have moving parts, like doors or drawers, because they must move in specific ways to avoid damage. This paper presents a new method for robots to learn how to move their tools while respecting these movement constraints. The approach uses many example movements to find safe directions and tunes the robot’s control system accordingly. This helps robots reduce forces that could harm the object while still accomplishing tasks.
What this means in practice
- •For industrial robot integrators: Improve robot arm control for tasks like door opening and drawer pulling by reducing damaging contact forces using constraint-aware impedance settings.
- •For robotic system designers: Design control policies that adapt impedance gains from policy-generated motion samples, enabling safer articulated object manipulation without complex force-position separation.
Authors
Kyungseo Park, Byeongdo Lim, Jungbin Lim, Minseok Choi, Frank C. Park
Abstract
Articulated object manipulation tasks such as opening doors, tightening bolts, and pulling drawers impose kinematic constraints on a robot end-effector's motion that neural policies may fail to satisfy. Unlike hybrid force-position control that strictly separates force and position control into orthogonal subspaces, impedance control modulates a mechanical impedance system in the form of a virtual inertia, damping, and stiffness. However, selecting task-appropriate impedance gains remains challenging for robot policies. In this paper, we address this problem for the case of manipulating articulated objects. Our constraint-decomposed impedance control method uses the sampling diversity of a generative policy to estimate the feasible motion directions in twist space. The key idea is to infer the feasible and constrained subspaces of twists from an ensemble of trajectories generated by the policy from the same observation. Principal component analysis (PCA) of the end-effector twists determines the feasible twist subspace, which is then used to form 6x6 impedance gain matrices. For many common articulated objects, the feasible twist subspace is independent of the object configuration, so the subspace and resulting gains are estimated once and held fixed during manipulation, minimizing computational overhead. For less common cases where this independence does not hold, we instead estimate a configuration-independent twist subspace of higher dimension that contains the local feasible subspaces, allowing the same fixed-gain strategy to be used. Experiments across simulated and real-world single- and multi-DoF objects show that the proposed method consistently reduces constraint-violating contact loads relative to isotropic impedance control while maintaining task execution.