Search for: All records

Given a swarm of limited-capability robots, we seek to automatically discover the set of possible emergent behaviors. Prior approaches to behavior discovery rely on human feedback or hand-crafted behavior metrics to represent and evolve behaviors and only discover behaviors in simulation, without testing or considering the deployment of these new behaviors on real robot swarms. In this work, we present Real2Sim2Real Behavior Discovery via Self-Supervised Representation Learning, which combines representation learning and novelty search to discover possible emergent behaviors automatically in simulation and enable direct controller transfer to real robots. First, we evaluate our method in simulation and show that our proposed self-supervised representation learning approach outperforms previous hand-crafted metrics by more accurately representing the space of possible emergent behaviors. Then, we address the reality gap by incorporating recent work in sim2real transfer for swarms into our lightweight simulator design, enabling direct robot deployment of all behaviors discovered in simulation on an open-source and low-cost robot platform. 

This paper proposes and analyzes a stochastic Susceptible-Exposed-Infected-Removed (SEIR) spreading model on networks. Imagine a nursing home housing 28 seniors and 7 staff workers, in which one of the staff has tested positive for COVID-19. Unfortunately, the results of this test are 3 days late and the infected person had not been quarantining while waiting for their test results. What is now the individual risk to the different people living in this nursing home? If the home has access to two rapid COVID-19 viral tests, who should they be given to and why? In order to answer questions like this, we need to study stochastic models rather than deterministic ones. Unlike the vast majority of works that analyze various deterministic models, stochastic models are required when analyzing the risk of COVID-19 to individual people rather than tracking aggregate numbers in a given region. More specifically, this paper compares the results provided by analyzing stochastic and deterministic models and investigating when it is suitable to use the different models. In particular, we show why it is not suitable to use deterministic models when analyzing the spread in small communities and how these questions can be better addressed using stochastic ones. Finally, we show the added complications that arise due to the relatively long incubation period of COVID-19, and how it can be addressed. A simulated case study of the spread of COVID-19 in a 35-person nursing home is used to help illustrate our results. 

This paper considers a planar multi-agent coordination problem. Unlike other related works, we explicitly consider a globally shared wireless communication channel where individual agents must choose both a frequency and power to transmit their messages at. This problem is motivated by the pressing need for algorithms that are able to efficiently and reliably operate on overcrowded wireless networks or otherwise poor-performing RF environments. We develop a self-triggered coordination algorithm that guarantees convergence to the desired set of states with probability 1. The algorithm is developed by using ideas from event/self-triggered coordination and allows agents to autonomously decide for themselves when to broadcast information, at which frequency and power, and how to move based on information received from other agents in the network. Simulations illustrate our results.