Differentiable Composite Neural Signed Distance Fields for Robot Navigation in Dynamic Indoor Environments

TL;DR

This paper introduces a compositional neural SDF framework for robot navigation in dynamic indoor environments, enabling efficient updates and improved trajectory optimization using onboard RGB-D sensors.

Contribution

The proposed dual mode neural SDF approach allows real-time scene updates and better navigation performance without extensive re-training.

Findings

Achieved 98% success rate in navigation tasks.

Outperformed baseline methods by 14.4%.

Demonstrated effectiveness in real-world scenarios.

Abstract

Neural Signed Distance Fields (SDFs) provide a differentiable environment representation to readily obtain collision checks and well-defined gradients for robot navigation tasks. However, updating neural SDFs as the scene evolves entails re-training, which is tedious, time consuming, and inefficient, making it unsuitable for robot navigation with limited field-of-view in dynamic environments. Towards this objective, we propose a compositional framework of neural SDFs to solve robot navigation in indoor environments using only an onboard RGB-D sensor. Our framework embodies a dual mode procedure for trajectory optimization, with different modes using complementary methods of modeling collision costs and collision avoidance gradients. The primary stage queries the robot body's SDF, swept along the route to goal, at the obstacle point cloud, enabling swift local optimization of trajectories. The secondary stage infers the visible scene's SDF by aligning and composing the SDF representations of its constituents, providing better informed costs and gradients for trajectory optimization. The dual mode procedure combines the best of both stages, achieving a success rate of 98%, 14.4% higher than baseline with comparable amortized plan time on iGibson 2.0. We also demonstrate its effectiveness in adapting to real-world indoor scenarios.