Occlusion-Based Coordination Protocol Design for Autonomous Robotic Shepherding Tasks

Abstract

The robotic shepherding problem has earned significant research interest over the last few decades due to its potential application in precision agriculture. In this paper, we first modeled the sheep flocking behavior using adaptive protocols and artificial potential field methods. Then we designed a coordination algorithm for the robotic dogs. An occlusion-based motion control strategy was proposed to herd the sheep to the desired location. Compared to formation based techniques, the proposed control strategy provides more flexibility and efficiency when herding a large number of sheep. Simulation and labbased experiments, using real robots and global vision-based tracking system, were carried out to validate the effectiveness of the proposed approach.

Voronoi-Based Multi-Robot Autonomous Exploration in Unknown Environments via Deep Reinforcement Learning

“…to hardware faults, adaptability to environmental changes and cost-effectiveness. Therefore, multi-robot systems have many potential applications, such as object transportation [1], security surveillance [2], disaster detection [3], formation coordination [4], [5], vehicle-assisted wireless communication networks [6], autonomous shepherding [7], connected vehicle platoons [8], [9], etc. As an important component in multi-robot coordination, cooperative exploration techniques have been widely used in search and rescue missions and mapping of unknown environments, which motivates the need to develop more efficient and feasible solutions.…”

Collaborative Overtaking of Multi-Vehicle Systems in Dynamic Environments: A Distributed Artificial Potential Field Approach

“…In this section, we develop a novel distributed control protocol based on artificial potential field method. Different from the traditional artificial potential field method which is suitable for tracking static targets [24], in this work, we modify the traditional artificial potential field such that it can be used to track dynamic targets. In addition, the tracking algorithm is improved to solve the problem of unreachable target in the artificial potential field method.…”

Robust Formation Coordination of Robot Swarms With Nonlinear Dynamics and Unknown Disturbances: Design and Experiments

“…Swarm robotic systems are usually distinguished by the following features: i) communication of each robot is limited in the sense that only neighboring agents communicate among themselves, ii) all robots in a swarm follow the same set of rules and work in unison to achieve a common goal, and iii) stability of a swarm system will not be affected significantly if some of the agents leave the network [2]. Swarm robotics is being applied in a variety of real-world problems, for instance, autonomous shepherding [3], dynamic mapping [4], cooperative planetary exploration [5], etc.…”