TamedPUMA: safe and stable imitation learning with geometric fabrics
This work addresses safety and constraint fulfillment in imitation learning for robotics, representing an incremental improvement by blending existing methods.
The paper tackles the problem of ensuring safety and physical constraints in imitation learning for robots by introducing TamedPUMA, an algorithm that combines imitation learning with geometric fabrics. The result is a stable imitation learning strategy that seamlessly integrates constraints like collision avoidance and joint limits, demonstrated in simulated and real-world tasks with a 7-DoF manipulator.
Using the language of dynamical systems, Imitation learning (IL) provides an intuitive and effective way of teaching stable task-space motions to robots with goal convergence. Yet, IL techniques are affected by serious limitations when it comes to ensuring safety and fulfillment of physical constraints. With this work, we solve this challenge via TamedPUMA, an IL algorithm augmented with a recent development in motion generation called geometric fabrics. As both the IL policy and geometric fabrics describe motions as artificial second-order dynamical systems, we propose two variations where IL provides a navigation policy for geometric fabrics. The result is a stable imitation learning strategy within which we can seamlessly blend geometrical constraints like collision avoidance and joint limits. Beyond providing a theoretical analysis, we demonstrate TamedPUMA with simulated and real-world tasks, including a 7-DoF manipulator.