RA-Nav: A Risk-Aware Navigation System Based on Semantic Segmentation for Aerial Robots in Unpredictable Environments

2026-02-19

AI Summary

This work addresses the challenge that existing aerial robot navigation systems struggle to handle sudden movements of ostensibly static obstacles due to a lack of semantic understanding and awareness of potential environmental dynamics. To this end, we propose RA-Nav, a novel framework that employs a lightweight multi-scale semantic segmentation network to classify obstacles in real time into three categories: static, transiently static, and dynamic. Leveraging these semantic labels, we design a category-aware risk estimation function to construct a local risk map, enabling risk-aware path planning and trajectory optimization. Our approach is the first to integrate semantic segmentation with risk modeling, introducing a classification-based risk model and a risk-guided search mechanism tailored for scenarios involving abrupt state changes. Extensive simulations demonstrate that RA-Nav significantly outperforms baseline methods in such dynamic environments, achieving higher task success rates, with further validation on real-world data-driven simulations confirming its effectiveness.

Technology Category

• Intelligent Robots: Localization, Mapping, and Navigation
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Natural Language Processing: Safety and Robustness

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Existing aerial robot navigation systems typically plan paths around static and dynamic obstacles, but fail to adapt when a static obstacle suddenly moves. Integrating environmental semantic awareness enables estimation of potential risks posed by suddenly moving obstacles. In this paper, we propose RA- Nav, a risk-aware navigation framework based on semantic segmentation. A lightweight multi-scale semantic segmentation network identifies obstacle categories in real time. These obstacles are further classified into three types: stationary, temporarily static, and dynamic. For each type, corresponding risk estimation functions are designed to enable real-time risk prediction, based on which a complete local risk map is constructed. Based on this map, the risk-informed path search algorithm is designed to guarantee planning that balances path efficiency and safety. Trajectory optimization is then applied to generate trajectories that are safe, smooth, and dynamically feasible. Comparative simulations demonstrate that RA-Nav achieves higher success rates than baselines in sudden obstacle state transition scenarios. Its effectiveness is further validated in simulations using real- world data.

Problem

• aerial robot navigation
• sudden obstacle movement
• risk awareness
• semantic segmentation
• unpredictable environments

Innovation

• risk-aware navigation
• semantic segmentation
• aerial robots
• dynamic obstacle prediction
• real-time risk mapping