Selected Publications

2021
Michal Yemini, Angelia Nedic ́, Andrea Goldsmith, and Stephanie Gil. 2021. “Characterizing Trust and Resilience in Distributed Consensus for Cyberphysical Systems.” Transactions on Robotics Journal. Publisher's VersionAbstract
This work considers the problem of resilient consensus where stochastic values of trust between agents are available. Specifically, we derive a unified mathematical framework to characterize convergence, deviation of the consensus from the true consensus value, and expected convergence rate, when there exists additional information of trust between agents. We show that under certain conditions on the stochastic trust values and consensus protocol: 1) almost sure convergence to a common limit value is possible even when malicious agents constitute more than half of the network connectivity, 2) the deviation of the converged limit, from the case where there is no attack, i.e., the true consensus value, can be bounded with probability that approaches 1 exponentially, and 3) correct classification of malicious and legitimate agents can be attained in finite time almost surely. Further, the expected convergence rate decays exponentially with the quality of the trust observations between agents.
characterizing_trust.pdf
Frederik Mallmann-Trenn, Matthew Cavorsi, and Stephanie Gil. 2021. “Crowd Vetting: Rejecting Adversaries via Collaboration--with Application to Multi-Robot Flocking.” Transactions on Robotics Journal.Abstract
We characterize the advantage of using a robot's neighborhood to find and eliminate adversarial robots in the presence of a Sybil attack. We show that by leveraging the opinions of its neighbors on the trustworthiness of transmitted data, robots can detect adversaries with high probability. We characterize a number of communication rounds required to achieve this result to be a function of the communication quality and the proportion of legitimate to malicious robots. This result enables increased resiliency of many multi-robot algorithms. Because our results are finite time and not asymptotic, they are particularly well-suited for problems with a time critical nature. We develop two algorithms, \emph{FindSpoofedRobots} that determines trusted neighbors with high probability, and \emph{FindResilientAdjacencyMatrix} that enables distributed computation of graph properties in an adversarial setting. We apply our methods to a flocking problem where a team of robots must track a moving target in the presence of adversarial robots. We show that by using our algorithms, the team of robots are able to maintain tracking ability of the dynamic target.
crowd_vetting-_rejecting_adversaries_via_collaboration_with_application_to_multi-robot_flocking.pdf
2020
Andrea Goldsmith, Stephanie Gil, and Michal Yemini. 12/7/2020. “Exploiting Local and Cloud Sensor Fusion in Intermittently Connected Sensor Networks.” In GLOBECOM 2020 - 2020 IEEE Global Communications Conference. Taipei, Taiwan: IEEE.Abstract
We consider a detection problem where sensors experience noisy measurements and intermittent communication opportunities to a centralized fusion center (or cloud). The objective of the problem is to arrive at the correct estimate of event detection in the environment. The sensors may communicate locally with other sensors (local clusters) where they fuse their noisy sensor data to estimate the detection of an event locally. In addition, each sensor cluster can intermittently communicate to the cloud, where a centralized fusion center fuses estimates from all sensor clusters to make a final determination regarding the occurrence of the event across the deployment area. We refer to this hybrid communication scheme as a cloud-cluster architecture. Minimizing the expected loss function of networks where noisy sensors are intermittently connected to the cloud, as in our hybrid communication scheme, has not been investigated to our knowledge. We leverage recently improved concentration inequalities to arrive at an optimized decision rule for each cluster and we analyze the expected detection performance resulting from our hybrid scheme. Our analysis shows that clustering the sensors provides resilience to noise in the case of low communication probability with the cloud. For larger clusters, a steep improvement in detection performance is possible even for a low communication probability by using our cloud-cluster architecture.
exploiting_local_and_cloud_sensor_fusion.pdf
Sushmita Bhattacharya, Siva Kailas, Sahil Badyal, Stephanie Gil, and Dimitri Bertsekas. 11/9/2020. “Multiagent Rollout and Policy Iteration for POMDP with Application to Multi-Robot Repair Problems”. Publisher's VersionAbstract
In this paper we consider infinite horizon discounted dynamic programming problems with finite state and control spaces, partial state observations, and a multiagent structure. We discuss and compare algorithms that simultaneously or sequentially optimize the agents' controls by using multistep lookahead, truncated rollout with a known base policy, and a terminal cost function approximation. Our methods specifically address the computational challenges of partially observable multiagent problems. In particular: 1) We consider rollout algorithms that dramatically reduce required computation while preserving the key cost improvement property of the standard rollout method. The per-step computational requirements for our methods are on the order of O(Cm) as compared with O(Cm) for standard rollout, where C is the maximum cardinality of the constraint set for the control component of each agent, and m is the number of agents. 2) We show that our methods can be applied to challenging problems with a graph structure, including a class of robot repair problems whereby multiple robots collaboratively inspect and repair a system under partial information. 3) We provide a simulation study that compares our methods with existing methods, and demonstrate that our methods can handle larger and more complex partially observable multiagent problems (state space size 1037 and control space size 107, respectively). Finally, we incorporate our multiagent rollout algorithms as building blocks in an approximate policy iteration scheme, where successive rollout policies are approximated by using neural network classifiers. While this scheme requires a strictly off-line implementation, it works well in our computational experiments and produces additional significant performance improvement over the single online rollout iteration method.
multiagent_rollout_and_policy_iteration_for_pomdp_with_application_to_multi-robot_repair_problems.pdf
Ramin Hasani, Andres F. Salazar-Gomez, Stephanie Gil, Joseph DelPreto, Frank H. Guenther, and Daniela Rus. 8/9/2020. “Plug-and-Play Supervisory Control Using Muscle and Brain Signals for Real-Time Gesture and Error Detection.” Autonomous Robots, 44, Pp. 1303–1322. Publisher's VersionAbstract
Effective human supervision of robots can be key for ensuring correct robot operation in a variety of potentially safety-critical scenarios. This paper takes a step towards fast and reliable human intervention in supervisory control tasks by combining two streams of human biosignals: muscle and brain activity acquired via EMG and EEG, respectively. It presents continuous classification of left and right hand-gestures using muscle signals, time-locked classification of error-related potentials using brain signals (unconsciously produced when observing an error), and a framework that combines these pipelines to detect and correct robot mistakes during multiple-choice tasks. The resulting hybrid system is evaluated in a “plug-and-play” fashion with 7 untrained subjects supervising an autonomous robot performing a target selection task. Offline analysis further explores the EMG classification performance, and investigates methods to select subsets of training data that may facilitate generalizable plug-and-play classifiers.
plug-and-play_supervisory_control_using_muscle_and_brain_signals_for_real-time_gesture_and_error_detection.pdf
Sensor information from wireless signals used for multi-robot PGO.
Sushmita Bhattacharya, Sahil Badyal, Thomas Wheeler, Stephanie Gil, and Dimitri Bertsekas. 1/23/2020. “Reinforcement Learning for POMDP: Partitioned Rollout and Policy Iteration with Application to Autonomous Sequential Repair Problems.” In RAL 1/23/2020. Abstract
—In this paper we consider infinite horizon discounted
dynamic programming problems with finite state and control
spaces, and partial state observations. We discuss an algorithm
that uses multistep lookahead, truncated rollout with a known
base policy, and a terminal cost function approximation. This
algorithm is also used for policy improvement in an approximate
policy iteration scheme, where successive policies are approximated by using a neural network classifier. A novel feature of
our approach is that it is well suited for distributed computation
through an extended belief space formulation and the use of a
partitioned architecture, which is trained with multiple neural
networks. We apply our methods in simulation to a class of
sequential repair problems where a robot inspects and repairs
a pipeline with potentially several rupture sites under partial
information about the state of the pipeline.
Reinforcement Learning for POMDP: Partitioned Rollout and Policy Iteration with Application to Autonomous Sequential Repair Problems
Ninad Jadhav, Weiying Wang, Diana Zhang, Oussama Khatib, Swarun Kumar, and Stephanie Gil. 2020. “WSR: A WiFi Sensor for Collaborative Robotics”. Publisher's VersionAbstract
In this paper we derive a new capability for robots to measure relative direction, or Angle-of-Arrival (AOA), to other robots operating in non-line-of-sight and unmapped environments with occlusions, without requiring external infrastructure. We do so by capturing all of the paths that a WiFi signal traverses as it travels from a transmitting to a receiving robot, which we term an AOA profile. The key intuition is to "emulate antenna arrays in the air" as the robots move in 3D space, a method akin to Synthetic Aperture Radar (SAR). The main contributions include development of i) a framework to accommodate arbitrary 3D trajectories, as well as continuous mobility all robots, while computing AOA profiles and ii) an accompanying analysis that provides a lower bound on variance of AOA estimation as a function of robot trajectory geometry based on the Cramer Rao Bound. This is a critical distinction with previous work on SAR that restricts robot mobility to prescribed motion patterns, does not generalize to 3D space, and/or requires transmitting robots to be static during data acquisition periods. Our method results in more accurate AOA profiles and thus better AOA estimation, and formally characterizes this observation as the informativeness of the trajectory; a computable quantity for which we derive a closed form. All theoretical developments are substantiated by extensive simulation and hardware experiments. We also show that our formulation can be used with an off-the-shelf trajectory estimation sensor. Finally, we demonstrate the performance of our system on a multi-robot dynamic rendezvous task.
wsr-_a_wifi_sensor_for_collaborative_robotics.pdf
2019
Sensor information from wireless signals used for multi-robot PGO.
Weiying Wang, Ninad Jadhav, Paul Vohs, Nathan Hughes, Mark Mazumder, and Stephanie Gil. 12/29/2019. “Active Rendezvous for Multi-Robot Pose Graph Optimization using Sensing over Wi-Fi.” In International Symposium on Robotics Research (ISRR). Hanoi.Abstract

We present a novel framework for collaboration amongst a team of robots performing Pose Graph Optimization (PGO) that addresses two important challenges for multi-robot SLAM: i) that of enabling information exchange “on-demand” via Active Rendezvous without using a map or the robot’s location, and ii) that of rejecting outlying measurements. Our key insight is to exploit relative position data present in the communication channel between robots to improve groundtruth accuracy of PGO. We develop an algorithmic and experimental framework for integrating Channel State Information (CSI) with multi-robot PGO; it is distributed, and applicable in low-lighting or featureless environments where traditional sensors often fail. We present extensive experimental results on actual robots and observe that using Active Rendezvous results in a 64% reduction in ground truth pose error and that using CSI observations to aid outlier rejection reduces ground truth pose error by 32%. These results show the potential of integrating communication as a novel sensor for SLAM.

Active Rendezvous for Multi-Robot Pose Graph Optimization using Sensing over Wi-Fi
Switching Topology for Resilient Consensus using Wi-Fi Signals
Thomas Wheeler, Ezhil Bharathi, and Stephanie Gil. 5/20/2019. “Switching Topology for Resilient Consensus using Wi-Fi Signals.” In IEEE International Conference on Robotics and Automation (ICRA).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 theoretical framework for securing multi-agent consensus against the Sybil attack by using the physical properties of wireless transmissions. Our framework uses information extracted from the wireless channels to de- sign a switching signal that stochastically excludes potentially untrustworthy transmissions from the consensus. Intuitively, this amounts to selectively ignoring incoming communications from untrustworthy agents, allowing for consensus to the true average to be recovered with high probability after a certain observation time T0. This paper allows for arbitrary malicious node values and is insensitive to the initial topology of the network so long as a connected topology over legitimate nodes in the network is feasible. We show that our algorithm will recover consensus, and the true graph over the system of legitimate agents, with an error rate that vanishes exponentially with time.
Switching Topology for Resilient Consensus using Wi-Fi Signals
Reinforcement Learning for POMDP: Rollout and Policy Iteration with Application to Sequential Repair
Dimitri P. Bertsekas, Stephanie Gil, Sushmita Bhattacharya, and Thomas Wheeler. 5/1/2019. “Reinforcement Learning for POMDP: Rollout and Policy Iteration with Application to Sequential Repair”.Abstract
We study rollout algorithms which combine limited lookahead and terminal cost function approximation in the context of POMDP. We demonstrate their effectiveness in the context of a sequential pipeline repair problem, which also arises in other contexts of search and rescue. We provide performance bounds and empirical validation of the methodology, in both cases of a single rollout iteration, and multiple iterations with intermediate policy space approximations.
Reinforcement Learning for POMDP: Rollout and Policy Iteration with Application to Sequential Repair
Resilient Multi-Agent Consensus Using Wi-Fi Signals
Stephanie Gil, Cenk Baykal, and Daniela Rus. 1/1/2019. “Resilient Multi-Agent Consensus Using Wi-Fi Signals .” In IEEE Control Systems Letters (L-CSS) 2018.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 system as a whole. In this letter, we present a light-weight approach for spoof-resiliency with provable guarantees that solely utilizes information from wireless signals. Unlike prior approaches, our method requires no additional protocol or data storage beyond signals that are already present in the network. We establish an analytical, probabilistic bound on the influence of spoofed nodes in the system on the converged consensus value. We present results of our Wi-Fi based resilient consensus algorithm and demonstrate its effectiveness for different consensus problems such as flocking and rendezvous.
Resilient Multi-Agent Consensus Using Wi-Fi Signals
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. 6/26/2018. “Plug-and-play supervisory control using muscle and brain signals for real-time gesture and error detection.” In RSS 2018: Robotics: Science and Systems. RSS 6/26/2018. 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 ability to use human cognition in the loop can be key for recuperating safe robot operation. This paper combines two streams of human biosignals, electrical muscle and brain activity via EMG and EEG, respectively, to achieve fast and accurate human intervention in a supervisory control task. In particular, this paper presents an end-to-end system for continuous rollingwindow classification of gestures that allows the human to actively correct the robot on demand, discrete classification of Error-Related Potential signals (unconsciously produced by the human supervisor’s brain when observing a robot error), and a framework that integrates these two classification streams for fast and effective human intervention. The system also allows “plug-and-play” operation, demonstrating accurate performance even with new users whose biosignals have not been used for training the classifiers. The resulting hybrid control system for safety-critical situations is evaluated with 7 untrained human subjects in a supervisory control scenario where an autonomous robot performs a multi-target selection task.
Plug-and-play supervisory control using muscle and brain signals for real-time gesture and error detection
2017
Correcting robot mistakes in real time using EEG signals
A.F. Salazar-Gomez, J DelPreto, S. Gil, F.H. Guenther, and D. Rus. 5/29/2017. “Correcting robot mistakes in real time using EEG signals.” In IEEE International Conference on Robotics and Automation (ICRA). Singapore.Abstract
Communication with a robot using brain activity from a human collaborator could provide a direct and fast feedback loop that is easy and natural for the human, thereby enabling a wide variety of intuitive interaction tasks. This paper explores the application of EEG-measured error-related potentials (ErrPs) to closed-loop robotic control. ErrP signals are particularly useful for robotics tasks because they are naturally occurring within the brain in response to an unexpected error. We decode ErrP signals from a human operator in real time to control a Rethink Robotics Baxter robot during a binary object selection task. We also show that utilizing a secondary interactive error-related potential signal generated during this closed-loop robot task can greatly improve classification performance, suggesting new ways in which robots can acquire human feedback. The design and implementation of the complete system is described, and results are presented for realtime closed-loop and open-loop experiments as well as offline analysis of both primary and secondary ErrP signals. These experiments are performed using general population subjects that have not been trained or screened. This work thereby demonstrates the potential for EEG-based feedback methods to facilitate seamless robotic control, and moves closer towards the goal of real-time intuitive interaction.
Correcting robot mistakes in real time using EEG signals
Guaranteeing spoof-resilient multi-robot networks
Stephanie Gil, Swarun Kumar, Mark Mazumder, Dina Katabi, and Daniela Rus. 2/28/2017. “Guaranteeing spoof-resilient multi-robot networks .” In .Abstract
Multi-robot networks use wireless communication to provide wide-ranging services such as aerial surveillance and unmanned delivery. However, effective coordination between multiple robots requires trust, making them particularly vulnerable to cyber-attacks. Specifically, such networks can be gravely disrupted by the Sybil attack, where even a single malicious robot can spoof a large number of fake clients. This paper proposes a new solution to defend against the Sybil attack, without requiring expensive cryptographic key-distribution. Our core contribution is a novel algorithm implemented on commercial Wi-Fi radios that can “sense” spoofers using the physics of wireless signals. We derive theoretical guarantees on how this algorithm bounds the impact of the Sybil Attack on a broad class of multi-robot problems, including locational coverage and unmanned delivery. We experimentally validate our claims using a team of AscTec quadrotor servers and iRobot Create ground clients, and demonstrate spoofer detection rates over 96%.
Guaranteeing spoof-resilient multi-robot networks
2015
Guaranteeing Spoof-Resilient Multi-Robot Networks
S. Gil, S. Kumar, D. Katabi, and D. Rus. 7/13/2015. “Guaranteeing Spoof-Resilient Multi-Robot Networks.” In Robotics Science and Systems (RSS). Rome, Italy.Abstract
Multi-robot networks use wireless communication to provide wide-ranging services such as aerial surveillance and unmanned delivery. However, effective coordination between multiple robots requires trust, making them particularly vulnerable to cyber-attacks. Specifically, such networks can be gravely disrupted by the Sybil attack, where even a single malicious robot can spoof a large number of fake clients. This paper proposes a new solution to defend against the Sybil attack, without requiring expensive cryptographic key-distribution. Our core contribution is a novel algorithm implemented on commercial Wi-Fi radios that can “sense” spoofers using the physics of wireless signals. We derive theoretical guarantees on how this algorithm bounds the impact of the Sybil Attack on a broad class of multi-robot problems, including locational coverage and unmanned delivery. We experimentally validate our claims using a team of AscTec quadrotor servers and iRobot Create ground clients, and demonstrate spoofer detection rates over 96%.
Guaranteeing spoof-resilient multi-robot networks
Adaptive Communication in Multi-Robot Teams using Directionality of Signal Strength
S. Gil, S. Kumar, D. Katabi, and D. Rus. 3/18/2015. “Adaptive Communication in Multi-Robot Teams using Directionality of Signal Strength.” International Journal on Robotics Research, 34, 7, Pp. 946-968.Abstract
We consider the problem of satisfying communication demands in a multi-agent system where several robots cooperate on a task and a fixed subset of the agents act as mobile routers. Our goal is to position the team of robotic routers to provide communication coverage to the remaining client robots. We allow for dynamic environments and variable client demands, thus necessitating an adaptive solution. We present an innovative method that calculates a mapping between a robot’s current position and the signal strength that it receives along each spatial direction, for its wireless links to every other robot. We show that this information can be used to design a simple positional controller that retains a quadratic structure, while adapting to wireless signals in real-world environments. Notably, our approach does not necessitate stochastic sampling along directions that are counter-productive to the overall coordination goal, nor does it require exact client positions, or a known map of the environment.
Adaptive Communication in Multi-Robot Teams using Directionality of Signal Strength
2014
Accurate Indoor Localization with Zero Startup Cost
S. Kumar, S. Gil, D. Rus, and D. Katabi. 9/7/2014. “Accurate Indoor Localization with Zero Startup Cost.” In ACM Conference on Mobile Computing and Networking (MobiCom).Abstract
Recent years have seen the advent of new RF-localization systems that demonstrate tens of centimeters of accuracy. However, such systems require either deployment of new infrastructure, or extensive fingerprinting of the environment through training or crowdsourcing, impeding their wide-scale adoption. We present Ubicarse, an accurate indoor localization system for commodity mobile devices, with no specialized infrastructure or fingerprinting. Ubicarse enables handheld devices to emulate large antenna arrays using a new formulation of Synthetic Aperture Radar (SAR). Past work on SAR requires measuring mechanically controlled device movement with millimeter precision, far beyond what commercial accelerometers can provide. In contrast, Ubicarse’s core contribution is the ability to perform SAR on handheld devices twisted by their users along unknown paths. Ubicarse is not limited to localizing RF devices; it combines RF localization with stereo-vision algorithms to localize common objects with no RF source attached to them. We implement Ubicarse on a HP SplitX2 tablet and empirically demonstrate a median error of 39 cm in 3-D device localization and 17 cm in object geotagging in complex indoor settings.
Accurate Indoor Localization with Zero Startup Cost
2013
Adaptive Communication in Multi-Robot Systems Using Directionality of Signal Strength
S. Gil, S. Kumar, D. Katabi, and D. Rus. 12/16/2013. “Adaptive Communication in Multi-Robot Systems Using Directionality of Signal Strength.” In International Symposium on Robotics Research (ISRR). Singapore.Abstract
We consider the problem of satisfying communication demands in a multi-agent system where several robots cooperate on a task and a fixed subset of the agents act as mobile routers. Our goal is to position the team of robotic routers to provide communication coverage to the remaining client robots. We allow for dynamic environments and variable client demands, thus necessitating an adaptive solution. We present an innovative method that calculates a mapping between a robot’s current position and the signal strength that it receives along each spatial direction, for its wireless links to every other robot. We show that this information can be used to design a simple positional controller that retains a quadratic structure, while adapting to wireless signals in real-world environments. Notably, our approach does not necessitate stochastic sampling along directions that are counter-productive to the overall coordination goal, nor does it require exact client positions, or a known map of the environment.
Adaptive Communication in Multi-Robot Teams using Directionality of Signal Strength
Communication coverage for independently moving robots
S. Gil, D. Feldman, and D. Rus. 11/3/2013. “Communication coverage for independently moving robots.” In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). Tokyo, Japan.Abstract
We consider the task of providing communication coverage to a group of sensing robots (sensors) moving independently to collect data. We provide communication via controlled placement of router vehicles that relay messages from any sensor to any other sensor in the system under the assumptions of 1) no cooperation from the sensors, and 2) only sensor-router or routerrouter communication over a maximum distance of R is reliable. We provide a formal framework and design provable exact and approximate (faster) algorithms for finding optimal router vehicle locations that are updated according to sensor movement. Using vehicle limitations, such as bounded control effort and maximum velocities of the sensors, our algorithm approximates areas that each router can reach while preserving connectivity and returns an expiration time window over which these positions are guaranteed to maintain communication of the entire system. The expiration time is compared against computation time required to update positions as a decision variable for choosing either the exact or approximate solution for maintaining connectivity with the sensors on-line.
Communication coverage for independently moving robots
K-robots clustering of moving sensors using clustering
D. Feldman, S. Gil, B. Julian, R. Knepper, and D. Rus. 5/6/2013. “K-robots clustering of moving sensors using clustering .” In IEEE International Conference on Robotics and Automation (ICRA). Sing.Abstract
We present an approach to position k servers (e.g. mobile robots) to provide a service to n independently moving clients; for example, in mobile ad-hoc networking applications where inter-agent distances need to be minimized, connectivity constraints exist between servers, and no a priori knowledge of the clients' motion can be assumed. Our primary contribution is an algorithm to compute and maintain a small representative set, called a kinematic coreset, of the n moving clients.We prove that, in any given moment, the maximum distance between the clients and any set of k servers is approximated by the coreset up to a factor of (1 ± ε), where ε > 0 is an arbitrarily small constant. We prove that both the size of our coreset and its update time is polynomial in k log(n)/ε. Although our optimization problem is NP-hard (i.e., takes time exponential in the number of servers to solve), solving it on the small coreset instead of the original clients results in a tractable controller. The approach is validated in a small scale hardware experiment using robot servers and human clients, and in a large scale numerical simulation using thousands of clients.
K-robots clustering of moving sensors using clustering

Pages