The multi-robot coverage problem is an essential building block for systems that perform tasks like inspection or search and rescue. We discretize the coverage problem to induce a spatial graph of locations and represent robots as nodes in the graph. Then, we train a Graph Neural Network controller that leverages the spatial equivariance of the task to imitate an expert open-loop routing solution. This approach generalizes well to much larger maps and larger teams that are intractable for the expert. In particular, the model generalizes effectively to a simulation of ten quadrotors and dozens of buildings. We also demonstrate the GNN controller can surpass planning-based approaches in an exploration task.

No abstract

Bacterial biofilms are the primary cause of infections in medical implants and catheters. Delayed detection of biofilm infections contributes to the widespread use of high doses of antibiotics, leading to the emergence of antibiotic-resistant bacterial strains. Accordingly, there is an urgent need for systems that can rapidly detect and treat biofilm infections in situ. As a step toward this goal, in this work we have developed for the first time a threshold-activated feedback-based impedance sensor-treatment system for combined real-time detection and treatment of biofilms. Specifically, we demonstrate the use of impedimetric sensing to accurately monitor the growth of Escherichia coli biofilms in microfluidic flow cells by measuring the fractional relative change (FRC) in absolute impedance. Furthermore, we demonstrate the use of growth measurements as a threshold-activated trigger mechanism to initiate successful treatment of biofilms using bioelectric effect (BE), applied through the same sensing electrode array. This was made possible through a custom program that (a) monitored the growth and removal of biofilms within the microfluidic channels in real-time and (b) enabled the threshold-based activation of BE treatment. Such BE treatment resulted in a ∼74.8 % reduction in average biofilm surface coverage as compared to the untreated negative control. We believe that this smart microsystem for integrated biofilm sensing and treatment will enable future development of autonomous biosensors optimized for accurate real-time detection of the onset of biofilms and their in situ treatment, directly on the surfaces of medical implants.

No abstract

No abstract

No abstract

Dynamical systems comprised of autonomous agents arise in many relevant problems such as multi-agent robotics, smart grids, or smart cities. Controlling these systems is of paramount importance to guarantee a successful deployment. Optimal centralized controllers are readily available but face limitations in terms of scalability and practical implementation. Optimal decentralized controllers, on the other hand, are difficult to find. In this paper, we propose a framework using graph neural networks (GNNs) to learn decentralized controllers from data. While GNNs are naturally distributed architectures, making them perfectly suited for the task, we adapt them to handle delayed communications as well. Furthermore, they are equivariant and stable, leading to good scalability and transferability properties. The problem of flocking is explored to illustrate the potential of GNNs in learning decentralized controllers.

We present a reinforcement learning algorithm for learning sparse non-parametric controllers in a Reproducing Kernel Hilbert Space. We improve the sample complexity of this approach by imposing a structure of the state-action function through a normalized advantage function (NAF). This representation of the policy enables efficiently composing multiple learned models without additional training samples or interaction with the environment. We demonstrate the performance of this algorithm on learning obstacle-avoidance policies in multiple simulations of a robot equipped with a laser scanner while navigating in a 2D environment. We apply the composition operation to various policy combinations and test them to show that the composed policies retain the performance of their components. We also transfer the composed policy directly to a physical platform operating in an arena with obstacles in order to demonstrate a degree of generalization.