Swarm-Gen: Fast Generation of Diverse Feasible Swarm Behaviors
Simon Idoko, B.Bhanu Teja, K.Madhava Krishna, Arun Kumar Singh

TL;DR
Swarm-Gen introduces a scalable method combining generative models and safety filters to rapidly produce diverse, feasible swarm behaviors, enhancing the control and coordination of robot swarms.
Contribution
It presents a novel approach integrating generative models with a safety filter and a neural network-based initialization to generate diverse swarm trajectories efficiently.
Findings
Generated diverse trajectories within tens of milliseconds.
VQ-VAE offers better diversity-computation trade-offs.
Initialization network accelerates safety filter convergence.
Abstract
Coordination behavior in robot swarms is inherently multi-modal in nature. That is, there are numerous ways in which a swarm of robots can avoid inter-agent collisions and reach their respective goals. However, the problem of generating diverse and feasible swarm behaviors in a scalable manner remains largely unaddressed. In this paper, we fill this gap by combining generative models with a safety-filter (SF). Specifically, we sample diverse trajectories from a learned generative model which is subsequently projected onto the feasible set using the SF. We experiment with two choices for generative models, namely: Conditional Variational Autoencoder (CVAE) and Vector-Quantized Variational Autoencoder (VQ-VAE). We highlight the trade-offs these two models provide in terms of computation time and trajectory diversity. We develop a custom solver for our SF and equip it with a neural network…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsEvolutionary Algorithms and Applications · Gene Regulatory Network Analysis · Genetics, Bioinformatics, and Biomedical Research
MethodsSparse Evolutionary Training
