Sampling-free obstacle gradients and reactive planning in Neural Radiance Fields
Metadata only
Date
2022-05-27Type
- Conference Paper
ETH Bibliography
yes
Altmetrics
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. Show more
Publication status
publishedPublisher
Stanford UniversityEvent
Organisational unit
03737 - Siegwart, Roland Y. / Siegwart, Roland Y.02284 - NFS Digitale Fabrikation / NCCR Digital Fabrication
More
Show all metadata
ETH Bibliography
yes
Altmetrics