Research

Robotic systems have the potential to enhance our way of life and solve some of the world’s most difficult problems—but in doing so they encounter situations unanticipated by the robot designer and software developer. Robots need to be equipped with mechanisms that allow them to respond to the unknown reliably to guarantees their success.

We are interested in discovering principles for robots to adapt and learn in real-time through negotiating and responding to their environment. Specifically, our research seeks to analyze and discover principled methods that enable robots to curiously explore, interact, and learn in novel scenarios with minimal data, compute, and with strong performance and reliability guarantees.

Publications

2024

Time-optimal ergodic search: Multiscale coverage in minimum time

Dayi Ethan Dong, Henry Berger, Ian Abraham

The International Journal of Robotics Research   ·   08 Oct 2024   ·   doi:10.1177/02783649241273597

Scale-Invariant Specifications for Human–Swarm Systems

Joel Meyer, Ahalya Prabhakar, Allison Pinosky, Ian Abraham, Annalisa Taylor, ..., Giovani Diniz, Brendan Teich, Borislava Simidchieva, Shane Clark, Todd Murphey

IEEE Transactions on Field Robotics   ·   01 Jan 2024   ·   doi:10.55417/fr.2023011

multi-robot ergodic control ergodicitys human-robot interaction

Scale-Invariant Specifications for Human–Swarm Systems

Joel Meyer, Ahalya Prabhakar, Allison Pinosky, Ian Abraham, Annalisa Taylor, ..., Giovani Diniz, Brendan Teich, Borislava Simidchieva, Shane Clark, Todd Murphey

IEEE Transactions on Field Robotics   ·   01 Jan 2024   ·   doi:10.1109/TFR.2024.3494721

2023

A Pareto-Optimal Local Optimization Framework for Multiobjective Ergodic Search

Zhongqiang Ren, Akshaya Kesarimangalam Srinivasan, Bhaskar Vundurthy, Ian Abraham, Howie Choset

IEEE Transactions on Robotics   ·   01 Oct 2023   ·   doi:10.1109/TRO.2023.3284358

optimization multi-objective optimization ergodic search ergodicity

Time Optimal Ergodic Search

Dayi Dong, Henry Berger, Ian Abraham

Robotics: Science and Systems XIX   ·   13 Jul 2023   ·   doi:10.15607/RSS.2023.XIX.082

In this paper, we investigate solutions to the time-optimal ergodic search problem for fast and adaptive robotic search and exploration.

Code

RSS Talk

time optimal coverage ergodicity ergodic control

Learning Stable Models for Prediction and Control

Giorgos Mamakoukas, Ian Abraham, Todd D. Murphey

IEEE Transactions on Robotics   ·   01 Jun 2023   ·   doi:10.1109/TRO.2022.3228130

Koopman operator theory optimal control learning

2022

Hybrid control for combining model-based and model-free reinforcement learning

Allison Pinosky, Ian Abraham, Alexander Broad, Brenna Argall, Todd D Murphey

The International Journal of Robotics Research   ·   02 Jun 2022   ·   doi:10.1177/02783649221083331

Learning Cooperative Multi-Agent Policies With Partial Reward Decoupling

Benjamin Freed, Aditya Kapoor, Ian Abraham, Jeff Schneider, Howie Choset

IEEE Robotics and Automation Letters   ·   01 Apr 2022   ·   doi:10.1109/LRA.2021.3135930

2021

An Ergodic Measure for Active Learning From Equilibrium

Ian Abraham, Ahalya Prabhakar, Todd D. Murphey

IEEE Transactions on Automation Science and Engineering   ·   01 Jul 2021   ·   doi:10.1109/TASE.2020.3043636

2020

Model-Based Generalization Under Parameter Uncertainty Using Path Integral Control

Ian Abraham, Ankur Handa, Nathan Ratliff, Kendall Lowrey, Todd D. Murphey, Dieter Fox

IEEE Robotics and Automation Letters   ·   01 Apr 2020   ·   doi:10.1109/LRA.2020.2972836

2019

Active Learning of Dynamics for Data-Driven Control Using Koopman Operators

Ian Abraham, Todd D. Murphey

IEEE Transactions on Robotics   ·   01 Oct 2019   ·   doi:10.1109/TRO.2019.2923880

2018

Decentralized Ergodic Control: Distribution-Driven Sensing and Exploration for Multiagent Systems

Ian Abraham, Todd D. Murphey

IEEE Robotics and Automation Letters   ·   01 Oct 2018   ·   doi:10.1109/LRA.2018.2849588

Real-Time Area Coverage and Target Localization Using Receding-Horizon Ergodic Exploration

Anastasia Mavrommati, Emmanouil Tzorakoleftherakis, Ian Abraham, Todd D. Murphey

IEEE Transactions on Robotics   ·   01 Feb 2018   ·   doi:10.1109/TRO.2017.2766265