Lessons Learned in Quadruped Deployment in Livestock Farming

TL;DR

The paper investigates deploying quadruped robots in extensive livestock farming to address labor, animal welfare, and sustainability challenges. It presents the SELF-AIR project, combining two quadruped platforms (Unitree A1 and Ghost Vision 60) with a ROS 2/MERLIN2-based cognitive architecture, multimodal sensing (cameras, LiDAR, GNSS), SLAM/visual SLAM, and YOLO-based animal and predator recognition, validated through field tests on private and research farms. The experiments demonstrate the feasibility of autonomous monitoring, real-time flock tracking with drone support, and data-driven insights into herd behavior, with both advantages and practical challenges discussed in the lessons learned. The findings highlight potential efficiency gains, improved welfare, and scalable deployment pathways for precision livestock farming using field robotics.

Abstract

The livestock industry faces several challenges, including labor-intensive management, the threat of predators and environmental sustainability concerns. Therefore, this paper explores the integration of quadruped robots in extensive livestock farming as a novel application of field robotics. The SELF-AIR project, an acronym for Supporting Extensive Livestock Farming with the use of Autonomous Intelligent Robots, exemplifies this innovative approach. Through advanced sensors, artificial intelligence, and autonomous navigation systems, these robots exhibit remarkable capabilities in navigating diverse terrains, monitoring large herds, and aiding in various farming tasks. This work provides insight into the SELF-AIR project, presenting the lessons learned.

Figures (3)

• Figure 1: SELF-AIR project requirements (first iteration) .
• Figure 2: Ghost Vision-60 (left) and Unitree A1 (right).
• Figure 3: Google Maps view of four farms visited on this research.