Extended Neural Contractive Dynamical Systems: On Multiple Tasks and Riemannian Safety Regions

TL;DR

This paper extends Neural Contractive Dynamical Systems (NCDS) to handle multiple tasks and safety regions, providing stability guarantees crucial for autonomous robots, with experiments confirming its flexibility and safety benefits.

Contribution

The paper introduces a conditional NCDS framework for multi-task learning and an uncertainty-driven obstacle avoidance method, enhancing stability guarantees in autonomous robotics.

Findings

System maintains stability while handling multiple tasks

Enhanced regularization improves model robustness

Experiments confirm safety and flexibility in robotic applications

Abstract

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.