A2VISR: An Active and Adaptive Ground-Aerial Localization System Using Visual Inertial and Single-Range Fusion

TL;DR

<3-5 sentence high-level summary> The paper tackles robust ground-aerial localization for flying robots in cluttered and degraded environments. It introduces A2VISR, a framework that fuses active ground-based vision with single-range, visual-inertial, and optical-flow data, complemented by an adaptive sliding-confidence mechanism and a dimension-reduced sliding-window estimator. The active vision subsystem expands the observation field and improves re-capture reliability, while the adaptive weighting handles sensor degradation in real time. Experimental results show an average RMSE around 0.09 m across diverse scenarios and strong resilience to visual loss and long-range operation, underscoring practical viability for autonomous aerial localization with minimal infrastructure.

Abstract

It's a practical approach using the ground-aerial collaborative system to enhance the localization robustness of flying robots in cluttered environments, especially when visual sensors degrade. Conventional approaches estimate the flying robot's position using fixed cameras observing pre-attached markers, which could be constrained by limited distance and susceptible to capture failure. To address this issue, we improve the ground-aerial localization framework in a more comprehensive manner, which integrates active vision, single-ranging, inertial odometry, and optical flow. First, the designed active vision subsystem mounted on the ground vehicle can be dynamically rotated to detect and track infrared markers on the aerial robot, improving the field of view and the target recognition with a single camera. Meanwhile, the incorporation of single-ranging extends the feasible distance and enhances re-capture capability under visual degradation. During estimation, a dimension-reduced estimator fuses multi-source measurements based on polynomial approximation with an extended sliding window, balancing computational efficiency and redundancy. Considering different sensor fidelities, an adaptive sliding confidence evaluation algorithm is implemented to assess measurement quality and dynamically adjust the weighting parameters based on moving variance. Finally, extensive experiments under conditions such as smoke interference, illumination variation, obstacle occlusion, prolonged visual loss, and extended operating range demonstrate that the proposed approach achieves robust online localization, with an average root mean square error of approximately 0.09 m, while maintaining resilience to capture loss and sensor failures.

Figures (9)

• Figure 1: The ground-aerial localization framework. (For an extended period, the prior estimates, active visual feedback, IMU, optical, and distance measurements are acquired. Subsequently, an augmented dimension-reduced estimator is reformulated to perform polynomial approximation.)
• Figure 2: Coordinate transformations are defined among the aerial robot (body frame $\mathcal{F}_{B}$), the ground vehicle (ground frame $\mathcal{F}_{G}$), and the ground vehicle's initial frame $\mathcal{F}_{G_0}$. The ground vehicle and the aerial robot are controlled using reference commands expressed in the initial frame.
• Figure 3: Experiment setup for the ground-aerial localization system. Subfigure (a) shows indoor Testbeds in clear scenario; subfigure (b) shows Testbeds in harsh scenario.
• Figure 4: Comparison of relative localization for different visual detection strategies. Subfigure (a) illustrates the 3D estimated trajectory using the proposed method in a clear scenario. Subfigure (b) compares the proposed active-view based relative localization with a fixed-view system under the same conditions. The shaded regions indicate the time intervals of data loss.
• Figure 5: The typical visual detection failures for different trails and their corresponding experimental scenarios. The first-person view from the infrared camera is displayed in the bottom right corner of the figure.