Safe Whole-Body Loco-Manipulation via Combined Model and Learning-based Control
Authors: Alexander Schperberg, Yeping Wang, Stefano Di Cairano
Organizations: Mitsubishi Electric Research Laboratories (MERL), Cambridge, MA, 02139, USA. · Yeping Wang was with Mitsubishi Electric Research Laboratories (MERL) during part of the work of this paper, Cambridge, MA, 02139, USA.
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 & tables
Fig. 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.
Fig. 2: Our framework architecture that combines neural/AI methods with Model Based Designs (MBD) for safe human-robot collaboration.
Reward
Expression
Velocity Tracking
End-Effector Lin Vel Tracking
ϕ(vee′w−veew)
End-Effector Ang Vel Tracking
ϕ(ωee′w−ωeew)
Energy Saving
Joint Torque (Penalty)
∥u∥+∣u∣
Action Rate (Penalty)
∥at−at−1∥2
TABLE I: Reward Functions
Fig. 3: Maximal Output Admissible Set for the sample trajectory shown in Fig. 5 .
Fig. 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.
Fig. 5: Example trajectory demonstrating the effect of the Reference Governor towards safety and constraint satisfaction.
Metric
ωx (rad/s)
ωy (rad/s)
ωz (rad/s)
MAE
0.0031
0.0013
0.0009
RMSE
0.0035
0.0017
0.0013
STD
0.0018
0.0015
0.0013
Metric
vx (m/s)
vy (m/s)
vz (m/s)
MAE
0.0385
0.0235
0.0202
RMSE
0.0564
0.0297
0.0273
TABLE II: Kalman Filter with Neural Network: Estimation Error Statistics
Real-world humanoid tasks involve physical interaction with objects and humans, yet current controllers either reject external forces as disturbances or restrict compliance to limited body links while ignoring angular effects. We present LAC, a general whole-body controller that simultaneously realizes commanded Linear and Angular Compliance for wrenches applied to the upper body. First, we synthesize whole-body compliant responses into a large-scale augmented dataset. Sampled force and couple events are imposed on contact frames extracted from human interaction data. At each contact link, the external force and a virtual torque from the passively yielding kinematic chain drive a virtual admittance under the commanded stiffness. Subsequently, teacher-student reinforcement learning trains a single policy to track the compliant motions under external wrenches. Finally, extensive simulation and real-world experiments demonstrate whole-body compliant responses to wrenches across the upper body, monotonic modulation over the full range of both stiffness commands, and applicability to teleoperated loco-manipulation tasks. Project website: https://lac-humanoid.github.io/
Yang Liu, Zhongkai Gu, Wei Zhu +1
Neuro-Robotics Laboratory, Tohoku University, Japan
Bipedal loco-manipulation enables robots to interact with objects beyond the nominal workspace of their arms by coordinating locomotion and manipulation. Realizing this capability requires a low-level whole-body controller that translates task-level manipulation goals into coordinated arm and leg motions while maintaining balance. We present a unified whole-body controller trained with reinforcement learning that directly maps 6-DoF end-effector targets to coordinated actions for the bipedal base and robotic arm. Given only an end-effector target, the learned controller autonomously coordinates reaching, postural adaptation, and stepping without explicit base-velocity or footstep commands. A reward-gating strategy regulates the trade-offs among end-effector tracking, locomotion, and balance during training, while a temporal context estimator combines windowed Transformer encoding, recurrent GRU memory, and auxiliary dynamics prediction to extract dynamics-relevant information from observation history. Real-robot experiments demonstrate that the same controller supports reaching, postural adaptation, and stepping under commands from VR teleoperation, a learned diffusion policy, and scripted trajectories, providing a common end-effector interface for diverse manipulation tasks.
Legged robots equipped with manipulators offer promising capabilities for loco-manipulation tasks in unstructured environments. However, achieving task-consistent end-effector behavior during locomotion remains challenging due to terrain-induced disturbances and the strong coupling between locomotion and manipulation, particularly for small-scale quadruped platforms. A reinforcement-learning based whole-body control framework is proposed for quadruped loco-manipulation on complex terrain. The proposed framework combines a hybrid task representation with task-prioritized whole-body learning to coordinate locomotion and manipulation while preserving task-consistent end-effector behavior. A lightweight quadruped manipulator platform is further developed to validate the proposed framework on a small-scale quadruped system. Real-world experiments demonstrate successful deployment on complex terrains such as slopes up to 30 degrees, stairs, and deformable terrain. These results demonstrate the feasibility of deploying learned whole-body control policy for quadruped loco-manipulation in real-world environments and highlight the importance of task-consistent whole-body coordination for terrain-adaptive loco-manipulation.
Yanzhou Jin, Fei Suo, Chang Liu +5
Graduate School of Engineering, The University of Tokyo, Japan. · Department of Micro-Nano Mechanical Science and Engineering, Nagoya University, Nagoya, 464-8603, Japan. · Department of Mathematics and Informatics, Ecole Centrale de Lyon, France.