Dynamic object goal pushing with mobile manipulators through model-free constrained reinforcement learning
arXiv:2502.01546 · doi:10.1109/ICRA55743.2025.11128166
Abstract
Non-prehensile pushing to move and reorient objects to a goal is a versatile loco-manipulation skill. In the real world, the object's physical properties and friction with the floor contain significant uncertainties, which makes the task challenging for a mobile manipulator. In this paper, we develop a learning-based controller for a mobile manipulator to move an unknown object to a desired position and yaw orientation through a sequence of pushing actions. The proposed controller for the robotic arm and the mobile base motion is trained using a constrained Reinforcement Learning (RL) formulation. We demonstrate its capability in experiments with a quadrupedal robot equipped with an arm. The learned policy achieves a success rate of 91.35% in simulation and at least 80% on hardware in challenging scenarios. Through our extensive hardware experiments, we show that the approach demonstrates high robustness against unknown objects of different masses, materials, sizes, and shapes. It reactively discovers the pushing location and direction, thus achieving contact-rich behavior while observing only the pose of the object. Additionally, we demonstrate the adaptive behavior of the learned policy towards preventing the object from toppling.
presented at ICRA 2025, Video: https://youtu.be/wGAdPGVf9Ws?si=pi83ONWofHHqbFG0
References in corpus (9)
- Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
- Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments
- Whole-Body MPC for a Dynamically Stable Mobile Manipulator
- Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation
- Versatile Multi-Contact Planning and Control for Legged Loco-Manipulation
- Transferring Dexterous Manipulation from GPU Simulation to a Remote Real-World TriFinger
- Whole-body MPC for highly redundant legged manipulators: experimental evaluation with a 37 DoF dual-arm quadruped
- Trajectory Optimization for Quadruped Mobile Manipulators that Carry Heavy Payload
- Force Push: Robust Single-Point Pushing with Force Feedback