1 code implementation • 3 Feb 2024 • Karthik Elamvazhuthi, Darshan Gadginmath, Fabio Pasqualetti
We learn to control a dynamical system in reverse such that the terminal state belongs to the target set.
no code implementations • 13 Dec 2023 • Karthik Elamvazhuthi, Samet Oymak, Fabio Pasqualetti
We use a control theoretic perspective by posing the approximation of the reverse process as a trajectory tracking problem.
no code implementations • 30 Aug 2023 • Karthik Elamvazhuthi, Spring Berman
We relax this assumption on the ellipticity of the generator of the stochastic processes, and consider the more practical case of the stabilization problem for a swarm of agents whose dynamics are given by a controllable driftless control-affine system.
no code implementations • 15 May 2023 • Karthik Elamvazhuthi, Xuechen Zhang, Samet Oymak, Fabio Pasqualetti
To address this shortcoming, in this paper we study a class of neural ordinary differential equations that, by design, leave a given manifold invariant, and characterize their properties by leveraging the controllability properties of control affine systems.
no code implementations • 18 May 2022 • Karthik Elamvazhuthi, Bahman Gharesifard, Andrea Bertozzi, Stanley Osher
As a corollary to this result, we establish that the continuity equation of the neural ODE is approximately controllable on the set of compactly supported probability measures that are absolutely continuous with respect to the Lebesgue measure.
no code implementations • 25 Feb 2022 • Katy Craig, Karthik Elamvazhuthi, Matt Haberland, Olga Turanova
As a consequence of our convergence result, we identify conditions on the target function and data distribution for which convexity of the energy landscape emerges in the continuum limit.
no code implementations • 20 Sep 2020 • Aniket Shirsat, Karthik Elamvazhuthi, Spring Berman
The simulations demonstrate that all robots achieve consensus in finite time with the proposed search strategy over a range of robot densities in the environment.
Robotics Multiagent Systems
no code implementations • 29 Jun 2020 • Zahi M. Kakish, Karthik Elamvazhuthi, Spring Berman
In this paper, we present a reinforcement learning approach to designing a control policy for a "leader" agent that herds a swarm of "follower" agents, via repulsive interactions, as quickly as possible to a target probability distribution over a strongly connected graph.