Physics-Informed Neural Mapping and Motion Planning in Unknown Environments

2024-10-13

IEEE Transactions on robotics

AI Summary

To address the high computational overhead and poor real-time performance caused by decoupled mapping and motion planning in unknown environments, this paper introduces arrival time fields as a novel neural implicit map representation that directly encodes spatiotemporal information of optimal paths. Methodologically, we propose the first online coupling of physics-informed neural networks (PINNs) with Eikonal equation solving, enabling unified perception, mapping, and planning without reliance on labeled data or prior models. The framework supports end-to-end, real-time, model-free active exploration and navigation. Extensive evaluations in simulation and real-world settings—on both differential-drive robots and 6-DOF robotic arms—demonstrate significant improvements over state-of-the-art methods, validating the approach’s superior real-time capability, robustness to environmental uncertainty, and strong cross-platform generalization.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Intelligent Robots: Motion and Path Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

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 article, 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 article introduces a new approach called active neural time fields, 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 six-degree-of-freedom robot manipulator.

Problem

• Develop arrival time fields for efficient robot motion planning
• Create physics-informed neural framework for unknown environments
• Solve Eikonal equation without expert data using neural networks

Innovation

• Physics-informed neural framework for mapping
• Arrival time fields solve Eikonal equation
• Active NTFields enable real-time motion planning