Neural Fields in Robotics: A Survey

TL;DR

Neural Fields are revolutionizing 3D scene understanding in robotics by enabling high-fidelity, real-time perception and interaction through differentiable, memory-efficient neural representations, as comprehensively reviewed in this survey.

Contribution

This survey categorizes key Neural Fields frameworks and applications in robotics, providing a comprehensive overview of their strengths, limitations, and future research directions.

Findings

Neural Fields enable accurate 3D reconstruction and semantics from 2D data.

They improve robot perception, planning, and control in various domains.

Current limitations include computational cost and data requirements.

Abstract

Neural Fields have emerged as a transformative approach for 3D scene representation in computer vision and robotics, enabling accurate inference of geometry, 3D semantics, and dynamics from posed 2D data. Leveraging differentiable rendering, Neural Fields encompass both continuous implicit and explicit neural representations enabling high-fidelity 3D reconstruction, integration of multi-modal sensor data, and generation of novel viewpoints. This survey explores their applications in robotics, emphasizing their potential to enhance perception, planning, and control. Their compactness, memory efficiency, and differentiability, along with seamless integration with foundation and generative models, make them ideal for real-time applications, improving robot adaptability and decision-making. This paper provides a thorough review of Neural Fields in robotics, categorizing applications across various domains and evaluating their strengths and limitations, based on over 200 papers. First, we present four key Neural Fields frameworks: Occupancy Networks, Signed Distance Fields, Neural Radiance Fields, and Gaussian Splatting. Second, we detail Neural Fields' applications in five major robotics domains: pose estimation, manipulation, navigation, physics, and autonomous driving, highlighting key works and discussing takeaways and open challenges. Finally, we outline the current limitations of Neural Fields in robotics and propose promising directions for future research. Project page: https://robonerf.github.io