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

2022/05/03 by Michael Pantic, Pantic, Michael, César Cadena +5 · 1 citation
Computer Science · Engineering · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Robot Manipulation and Learning #Robotic Path Planning Algorithms #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2205.01389

openalex publication_date 2022/05/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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). Using backward differentiation of the augmented network, we obtain an obstacle gradient that is integrated into an obstacle avoidance policy based on the Riemannian Motion Policies (RMP) framework. Thus, our findings allow for very fast sampling-free obstacle avoidance planning in the implicit representation.

Cited by

• Unified Linear Parametric Map Modeling and Perception-aware Trajectory Planning for Mobile Robotics

Related

• UNeRF: Time and Memory Conscious U-Shaped Network for Training Neural Radiance Fields
• NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds
• Preconditioners for the Stochastic Training of Neural Fields
• CDFlow: Generative Gradient Flows for Configuration Space Distance Fields via Neural ODEs
• Geometric Neural Distance Fields for Learning Human Motion Priors