Partial Motion Imitation for Learning Cart Pushing with Legged Manipulators
This work addresses the problem of mobile manipulation for legged robots, but it is incremental as it builds on existing imitation learning methods for specific tasks.
The paper tackles the challenge of learning robust loco-manipulation skills for legged robots by proposing a partial imitation learning approach that transfers locomotion style to cart pushing, achieving more stable and accurate behaviors in IsaacLab and MuJoCo simulations.
Loco-manipulation is a key capability for legged robots to perform practical mobile manipulation tasks, such as transporting and pushing objects, in real-world environments. However, learning robust loco-manipulation skills remains challenging due to the difficulty of maintaining stable locomotion while simultaneously performing precise manipulation behaviors. This work proposes a partial imitation learning approach that transfers the locomotion style learned from a locomotion task to cart loco-manipulation. A robust locomotion policy is first trained with extensive domain and terrain randomization, and a loco-manipulation policy is then learned by imitating only lower-body motions using a partial adversarial motion prior. We conduct experiments demonstrating that the learned policy successfully pushes a cart along diverse trajectories in IsaacLab and transfers effectively to MuJoCo. We also compare our method to several baselines and show that the proposed approach achieves more stable and accurate loco-manipulation behaviors.