SwordRiding: A Unified Navigation Framework for Quadrotors in Unknown Complex Environments via Online Guiding Vector Fields

2025-11-26

AI Summary

Quadrotor UAVs exhibit weak disturbance rejection and poor real-time adaptability to wind gusts and dynamic obstacles in unknown, complex environments due to conventional open-loop trajectory planning. Method: This paper proposes a closed-loop navigation framework based on an online-generated Guidance Vector Field (GVF). It directly maps discrete reference paths—produced by standard global planners—into an adaptive, continuous GVF, enabling rigorous closed-loop control. The framework integrates onboard perception, Euclidean Signed Distance Field (ESDF) mapping, B-spline trajectory optimization, and real-time GVF generation into an end-to-end system. Contribution/Results: The system achieves millisecond-level responsiveness to environmental changes. Extensive experiments demonstrate significantly improved robustness and safety under wind disturbances and dynamic obstacle conditions. Both simulation and real-world flight tests outperform state-of-the-art methods in tracking accuracy, collision avoidance, and computational efficiency.

Technology Category

• Planning, Routing, and Scheduling: Replanning and Plan Repair
• Intelligent Robots: State Estimation
• Multiagent Systems: Adversarial Agents

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Experiences and lessons learnt from Web-based algorithms and system deployments
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Although quadrotor navigation has achieved high performance in trajectory planning and control, real-time adaptability in unknown complex environments remains a core challenge. This difficulty mainly arises because most existing planning frameworks operate in an open-loop manner, making it hard to cope with environmental uncertainties such as wind disturbances or external perturbations. This paper presents a unified real-time navigation framework for quadrotors in unknown complex environments, based on the online construction of guiding vector fields (GVFs) from discrete reference path points. In the framework, onboard perception modules build a Euclidean Signed Distance Field (ESDF) representation of the environment, which enables obstacle awareness and path distance evaluation. The system first generates discrete, collision-free path points using a global planner, and then parameterizes them via uniform B-splines to produce a smooth and physically feasible reference trajectory. An adaptive GVF is then synthesized from the ESDF and the optimized B-spline trajectory. Unlike conventional approaches, the method adopts a closed-loop navigation paradigm, which significantly enhances robustness under external disturbances. Compared with conventional GVF methods, the proposed approach directly accommodates discretized paths and maintains compatibility with standard planning algorithms. Extensive simulations and real-world experiments demonstrate improved robustness against external disturbances and superior real-time performance.

Problem

• Develops a real-time navigation framework for quadrotors in unknown complex environments.
• Enhances adaptability to environmental uncertainties like wind disturbances via closed-loop control.
• Integrates online guiding vector fields with discrete path points for improved robustness.

Innovation

• Online guiding vector fields for closed-loop navigation
• ESDF-based obstacle awareness with B-spline trajectory parameterization
• Real-time adaptive framework for unknown complex environments