HOME /

News

Sensor information from wireless signals used for multi-robot PGO.

Our paper on distributed learning for POMDP in a sequential repair setting with Dimitri Bertsekas has been accepted for publication in RAL 2020!

February 11, 2020

Reinforcement Learning for POMDP: Partitioned Rollout and Policy Iteration with Application to Autonomous Sequential Repair Problems

Sushmita Bhattacharya, Sahil Badyal, Thomas Wheeler, Stephanie Gil, Dimitri Bertsekas 

Abstract

In this paper we consider infinite horizon discounted dynamic programming...

Read more about Our paper on distributed learning for POMDP in a sequential repair setting with Dimitri Bertsekas has been accepted for publication in RAL 2020!
function for static (left col) and time varying (right) spoofed node input. Convergence of consensus using our protocol and switching

Our paper “Switching Topology for Resilient Consensus using Wi-Fi Signals” gets accepted to ICRA 2019!

May 20, 2019

Switching Topology for Resilient Consensus using Wi-Fi Signals

Thomas Wheeler and Ezhil Bharathi and Stephanie Gil

Abstract

 

Securing multi-robot teams against malicious ac- tivity is crucial as these systems accelerate towards widespread societal integration. This emerging class of “physical networks” requires new security methods that exploit their physical nature. This paper derives a...

Read more about Our paper “Switching Topology for Resilient Consensus using Wi-Fi Signals” gets accepted to ICRA 2019!
Sensor information from wireless signals used for multi-robot PGO.

REACT Lab presents new work on sequential decision making for POMDP at the MIT Learning for Decision and Control workshop in May 2019

May 1, 2019

Reinforcement Learning for POMDP: Rollout and Policy Iteration with Application to Sequential Repair

Sushmita Bhattacharya, Thomas Wheeler
advised by Stephanie Gil, Dimitri P. Bertsekas

Abstract

We study rollout algorithms which combine limited lookahead and terminal cost function...

Read more about REACT Lab presents new work on sequential decision making for POMDP at the MIT Learning for Decision and Control workshop in May 2019
Resilient consensus algorithm for the case of flocking with 7 legitimate nodes (black) and 2 spoofed nodes (red) and true average (green).

Our paper “Resilient Multi-Agent Consensus Using Wi-Fi Signals” gets accepted to IEEE Control Systems Letters (L-CSS) 2018!

January 1, 2019

Resilient Multi-Agent Consensus Using Wi-Fi Signals

Stephanie Gil, Cenk Baykal, Daniela Rus

Abstract

Consensus is an important capability at the heart of many multi-agent systems. Unfortunately the ability to reach consensus can be easily disrupted by the presence of an adversarial agent that spawns or spoofs malicious nodes in the network in order to gain a disproportionate influence on the converged value of the...

Read more about Our paper “Resilient Multi-Agent Consensus Using Wi-Fi Signals” gets accepted to IEEE Control Systems Letters (L-CSS) 2018!
Our paper “Plug-and-play supervisory control using muscle and brain signals for real-time gesture and error detection” gets accepted to RSS 2018!

Our paper “Plug-and-play supervisory control using muscle and brain signals for real-time gesture and error detection” gets accepted to RSS 2018!

June 26, 2018

Plug-and-play supervisory control using muscle and brain signals for real-time gesture and error detection

Joseph DelPreto, Andres F. Salazar-Gomez, Stephanie Gil, Ramin M. Hasani, Frank H. Guenther, and Daniela Rus

Abstract

Control of robots in safety-critical tasks and situations where costly errors may occur is paramount for realizing the vision of pervasive human-robot collaborations. For these cases, the...

Read more about Our paper “Plug-and-play supervisory control using muscle and brain signals for real-time gesture and error detection” gets accepted to RSS 2018!