MoMaGen: Generating Demonstrations under Soft and Hard Constraints for Multi-Step Bimanual Mobile Manipulation
This work addresses the costly data collection problem for robot imitation learning in complex mobile manipulation tasks, offering an incremental improvement over prior static methods.
The paper tackles the challenge of generating diverse demonstrations for multi-step bimanual mobile manipulation by introducing MoMaGen, which formulates data generation as a constrained optimization problem to address reachability and visibility issues, resulting in policies trained from a single demonstration and fine-tuned with as few as 40 real-world demonstrations for deployment.
Imitation learning from large-scale, diverse human demonstrations has proven effective for training robots, but collecting such data is costly and time-consuming. This challenge is amplified for multi-step bimanual mobile manipulation, where humans must teleoperate both a mobile base and two high-degree-of-freedom arms. Prior automated data generation frameworks have addressed static bimanual manipulation by augmenting a few human demonstrations in simulation, but they fall short for mobile settings due to two key challenges: (1) determining base placement to ensure reachability, and (2) positioning the camera to provide sufficient visibility for visuomotor policies. To address these issues, we introduce MoMaGen, which formulates data generation as a constrained optimization problem that enforces hard constraints (e.g., reachability) while balancing soft constraints (e.g., visibility during navigation). This formulation generalizes prior approaches and provides a principled foundation for future methods. We evaluate MoMaGen on four multi-step bimanual mobile manipulation tasks and show that it generates significantly more diverse datasets than existing methods. Leveraging this diversity, MoMaGen can train successful imitation learning policies from a single source demonstration, and these policies can be fine-tuned with as few as 40 real-world demonstrations to achieve deployment on physical robotic hardware. More details are available at our project page: momagen.github.io.