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

S. Talha Bukhari, Daniel Lawson, Ahmed H. Qureshi
Department of Computer Science, Purdue University
IEEE International Conference on Robotics and Automation (ICRA) 2025
arXiv Paper Code (releasing soon)
Paper teaser

We present a framework for trajectory optimization to navigate mobile robots in dynamic indoor environments. Our proposal uses robot-centric RGB-D information combined with prior knowledge to infer composite SDF-based representa- tions, which are queried to obtain collision costs and gradients to generate collision-free trajectories.

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.

Dual Mode Neural SDF Pipeline for Trajectory Optimization

Pipeline steps

Execution of the proposed pipelines is demonstrated for a given object placement at time step t and after a displacement at time step t+1. The Robot SDF pipeline queries the robot body’s SDF at the obstacle point cloud (black) to guide trajectory optimization. The Scene SDF pipeline assigns point cloud regions to each object instance, and then infers the mapping from the robot’s workspace to the domain of each object’s SDF representation. This mapping enables inferring the full SDF of the visible scene used to guide trajectory optimization.

Video Demonstrations

Citation

@inproceedings{bukhari25icra,
  title={Differentiable Composite Neural Signed Distance Fields for Robot Navigation in Dynamic Indoor Environments},
  author={Bukhari, S. Talha and Lawson, Daniel and Qureshi, Ahmed H.},
  booktitle={2025 International Conference on Robotics and Automation (ICRA)},
  year={2025},
  organization={IEEE}
}