Extended Neural Contractive Dynamical Systems: On Multiple Tasks and Riemannian Safety Regions
This work addresses stability and safety challenges in autonomous robotics, though it is incremental, building on prior NCDS research.
The paper extends Neural Contractive Dynamical Systems (NCDS) to handle multiple tasks and ensure safety via Riemannian regions, achieving stability guarantees for autonomous robots while maintaining neural network flexibility.
Stability guarantees are crucial when ensuring that a fully autonomous robot does not take undesirable or potentially harmful actions. We recently proposed the Neural Contractive Dynamical Systems (NCDS), which is a neural network architecture that guarantees contractive stability. With this, learning-from-demonstrations approaches can trivially provide stability guarantees. However, our early work left several unanswered questions, which we here address. Beyond providing an in-depth explanation of NCDS, this paper extends the framework with more careful regularization, a conditional variant of the framework for handling multiple tasks, and an uncertainty-driven approach to latent obstacle avoidance. Experiments verify that the developed system has the flexibility of ordinary neural networks while providing the stability guarantees needed for autonomous robotics.