Physics-informed Neural Mapping and Motion Planning in Unknown Environments

TL;DR

This paper introduces Active Neural Time Fields, a physics-informed neural framework that maps environment arrival times and guides robot motion planning without requiring expert data, demonstrating superior performance in simulations and real-world tests.

Contribution

The paper presents a novel neural approach that directly solves the Eikonal equation for environment mapping and robot navigation, eliminating the need for traditional, computationally expensive planning methods.

Findings

Outperforms state-of-the-art mapping and planning methods.

Works effectively in both simulated and real-world environments.

Does not require expert data for training.

Abstract

Mapping and motion planning are two essential elements of robot intelligence that are interdependent in generating environment maps and navigating around obstacles. The existing mapping methods create maps that require computationally expensive motion planning tools to find a path solution. In this paper, we propose a new mapping feature called arrival time fields, which is a solution to the Eikonal equation. The arrival time fields can directly guide the robot in navigating the given environments. Therefore, this paper introduces a new approach called Active Neural Time Fields (Active NTFields), which is a physics-informed neural framework that actively explores the unknown environment and maps its arrival time field on the fly for robot motion planning. Our method does not require any expert data for learning and uses neural networks to directly solve the Eikonal equation for arrival time field mapping and motion planning. We benchmark our approach against state-of-the-art mapping and motion planning methods and demonstrate its superior performance in both simulated and real-world environments with a differential drive robot and a 6 degrees-of-freedom (DOF) robot manipulator. The supplementary videos can be found at https://youtu.be/qTPL5a6pRKk, and the implementation code repository is available at https://github.com/Rtlyc/antfields-demo.