The Composite Visual-Laser Navigation Method Applied in Indoor Poultry Farming Environments

TL;DR

This work tackles the challenge of autonomous navigation in indoor poultry farming where uneven lighting and floor moisture undermine single-sensor methods. It proposes a composite visual-laser navigation system that fuses vision and LiDAR yaw estimates through online reliability weighting to produce a fused yaw angle, removing the need for fixed ground navigation lines. Key contributions include a visual navigation line extraction pipeline that resists illumination changes, a precise yaw-angle computation for both visual and laser modalities, and a reliability-based fusion strategy that adapts to environmental conditions. Experimental validation in real poultry houses shows that the fused approach improves navigation accuracy and robustness under strong light and water accumulation, offering a practical route to more reliable inspection robotics in complex indoor settings.

Abstract

Indoor poultry farms require inspection robots to maintain precise environmental control, which is crucial for preventing the rapid spread of disease and large-scale bird mortality. However, the complex conditions within these facilities, characterized by areas of intense illumination and water accumulation, pose significant challenges. Traditional navigation methods that rely on a single sensor often perform poorly in such environments, resulting in issues like laser drift and inaccuracies in visual navigation line extraction. To overcome these limitations, we propose a novel composite navigation method that integrates both laser and vision technologies. This approach dynamically computes a fused yaw angle based on the real-time reliability of each sensor modality, thereby eliminating the need for physical navigation lines. Experimental validation in actual poultry house environments demonstrates that our method not only resolves the inherent drawbacks of single-sensor systems, but also significantly enhances navigation precision and operational efficiency. As such, it presents a promising solution for improving the performance of inspection robots in complex indoor poultry farming settings.

Figures (7)

• Figure 1: The actual environment in an indoor poultry farm, where uneven lighting and water accumulation coexist, poses significant challenges. Under these conditions, navigation based on a single sensor fails to deliver satisfactory performance.
• Figure 2: Framework of composite vision-laser navigation.
• Figure 3: Visual Navigation Flowchart. The actual image captured by the camera is first processed to correct brightness, then the aisle edge lines are extracted using a straight-line detection algorithm, and finally, the navigation lines are drawn.
• Figure 4: Calculation of yaw angle. (a) Laser yaw angle, which is determined by applying a static coordinate transformation between the map and world coordinate systems; (b) Visual yaw angle, which is obtained from the visual navigation line.
• Figure 5: Schematic representation of the two experimental environments in a real chicken coop. We conducted navigation experiments under bright light and in standing water, respectively.