Diffeomorphic Obstacle Avoidance for Contractive Dynamical Systems via Implicit Representations
This work addresses safety and robustness for robots in cluttered environments, representing an incremental improvement by integrating existing techniques like SDFs and flow-based diffeomorphisms.
The paper tackled the challenge of ensuring safety and robustness in dynamic robot skills learned from demonstrations by developing a framework that combines neural contractive dynamical systems with diffeomorphic transforms for obstacle avoidance, resulting in outperformance over state-of-the-art methods in synthetic and real-world kitchen tasks.
Ensuring safety and robustness of robot skills is becoming crucial as robots are required to perform increasingly complex and dynamic tasks. The former is essential when performing tasks in cluttered environments, while the latter is relevant to overcome unseen task situations. This paper addresses the challenge of ensuring both safety and robustness in dynamic robot skills learned from demonstrations. Specifically, we build on neural contractive dynamical systems to provide robust extrapolation of the learned skills, while designing a full-body obstacle avoidance strategy that preserves contraction stability via diffeomorphic transforms. This is particularly crucial in complex environments where implicit scene representations, such as Signed Distance Fields (SDFs), are necessary. To this end, our framework called Signed Distance Field Diffeomorphic Transform, leverages SDFs and flow-based diffeomorphisms to achieve contraction-preserving obstacle avoidance. We thoroughly evaluate our framework on synthetic datasets and several real-world robotic tasks in a kitchen environment. Our results show that our approach locally adapts the learned contractive vector field while staying close to the learned dynamics and without introducing highly-curved motion paths, thus outperforming several state-of-the-art methods.