Abstract
Swarm robotics, inspired by the collective behaviors found in nature, plays a vital role in enhancing scalability, resilience, and efficiency in multi-robot systems. A major challenge in deploying swarm robotics on a large scale is enabling robots to determine their neighbors' relative positions using onboard sensors, mimicking the spatial awareness observed in animal groups. Current onboard methods, such as SLAM, require intensive computation and are not ideal for decoding neighbor information. On the other hand, combining artificial neural networks with computer vision can be effective when trained on large high-quality datasets, but collecting such datasets remains the primary bottleneck. In this seminar, I propose a general pipeline that simplifies the collection of large training datasets and enables detection with lightweight neural networks to estimate the neighbor's relative position with minimum manual work. As a demonstration, we deploy seven robots equipped with onboard cameras and Raspberry Pi 4B units, using a motion capture system to label neighbors' relative positions synchronized with the onboard images. By collecting more than 10,000 images in just 10 minutes, we train and compare three neural networks to estimate the neighbor's relative position. Our pipeline highlights the feasibility of onboard perception and control with scalable large swarm robotics, offering promising prospects for deployment beyond the lab environment.
About the speaker
TBD