Sampling-free obstacle gradients and reactive planning in Neural Radiance Fields

Abstract

This work investigates the use of Neural implicit representations, specifically Neural Radiance Fields (NeRF), for geometrical queries and motion planning. We show that by adding the capacity to infer occupancy in a radius to a pre trained NeRF we are effectively learning an approximation to a Euclidean Signed Distance Field (ESDF). Even more, using backward differentiation of the network, we readily obtain the obstacle gradients that are integrated into policies for a Riemannian Motion Policies (RMP) framework. Thus, our findings allow for a sampling-free obstacle avoidance planning method in the implicit representation.