Safe Whole-Body Loco-Manipulation via Combined Model and Learning-based Control

TL;DR

A whole-body controller that combines a model-based admittance control for the manipulator arm with a Reinforcement Learning (RL) policy for legged locomotion, allowing for compliant behavior and safe, reliable performance in dynamic settings is proposed.

Abstract

Simultaneous locomotion and manipulation enables robots to interact with their environment beyond the constraints of a fixed base. However, coordinating legged locomotion with arm manipulation, while considering safety and compliance during contact interaction remains challenging. To this end, we propose a whole-body controller that combines a model-based admittance control for the manipulator arm with a Reinforcement Learning (RL) policy for legged locomotion. The admittance controller maps external wrenches--such as those applied by a human during physical interaction--into desired end-effector velocities, allowing for compliant behavior. The velocities are tracked jointly by the arm and leg controllers, enabling a unified 6-DoF force response. The model-based design permits accurate force control and safety guarantees via a Reference Governor (RG), while robustness is further improved by a Kalman filter enhanced with neural networks for reliable base velocity estimation. We validate our approach in both simulation and hardware using the Unitree Go2 quadruped robot with a 6-DoF arm and wrist-mounted 6-DoF Force/Torque sensor. Results demonstrate accurate tracking of interaction-driven velocities, compliant behavior, and safe, reliable performance in dynamic settings.

Figures (6)

• Figure 1: We present a combined model and learning-based whole-body controller that enables safe collaboration between a human and a quadruped robot with manipulator arm in both simulation and hardware.
• Figure 2: Our framework architecture that combines neural/AI methods with Model Based Designs (MBD) for safe human-robot collaboration.
• Figure 3: Maximal Output Admissible Set for the sample trajectory shown in Fig. \ref{['fig:ref_governor_results']}.
• Figure 4: Velocity tracking results during human-robot collaboration task. Tracking results of the command end-effector linear velocity in $x/y$ directions is shown on the left, of linear and angular velocity in the $z$ direction in the middle, and of angular velocity in the $x/y$ directions on the right. The command linear and angular velocities are generated directly from the output admittance controller, which takes as input 6-DoF Force/Torque information.
• Figure 5: Example trajectory demonstrating the effect of the Reference Governor towards safety and constraint satisfaction.