arXiv subjects

Ryan K. Williams

Publications and source records attributed to Ryan K. Williams.

15 recordsLinked to original sources

arXiv2022

Probabilistically Resilient Multi-Robot Informative Path Planning

In this paper, we solve a multi-robot informative path planning (MIPP) task under the influence of uncertain communication and adversarial attackers. The goal is to create a multi-robot system that can learn and unify its knowledge of an unknown environment despite the presence of corrupted robots sharing malicious information. We use a Gaussian Process (GP) to model our unknown environment and define informativeness using the metric of mutual information. The objectives of our MIPP task is to maximize the amount of information collected by the team while maximizing the probability of resilience to attack. Unfortunately, these objectives are at odds especially when exploring large environments which necessitates disconnections between robots. As a result, we impose a probabilistic communication constraint that allows robots to meet intermittently and resiliently share information, and then act to maximize collected information during all other times. To solve our problem, we select meeting locations with the highest probability of resilience and use a sequential greedy algorithm to optimize paths for robots to explore. Finally, we show the validity of our results by comparing the learning ability of well-behaving robots applying resilient vs. non-resilient MIPP algorithms.

cs.RO↗

arXiv2022

A Fast Algorithm for Robust Action Selection in Multi-Agent Systems

In this paper, we consider a robust action selection problem in multi-agent systems where performance must be guaranteed when the system suffers a worst-case attack on its agents. Specifically, agents are tasked with selecting actions from a common ground set according to individualized objective functions, and we aim to protect the system against attacks. In our problem formulation, attackers attempt to disrupt the system by removing an agent's contribution after knowing the system solution and thus can attack perfectly. To protect the multi-agent system against such attacks, we aim to maximize the minimum performance of all agents' individual objective functions under attacks. Thus, we propose a fast algorithm with tunable parameters for balancing complexity and performance, yielding substantially improved time complexity and performance compared to recent methods. Finally, we provide Monte Carlo simulations to demonstrate the performance of the proposed algorithm.

cs.MA↗

arXiv2021

Towards Computational Awareness in Autonomous Robots: An Empirical Study of Computational Kernels

The potential impact of autonomous robots on everyday life is evident in emerging applications such as precision agriculture, search and rescue, and infrastructure inspection. However, such applications necessitate operation in unknown and unstructured environments with a broad and sophisticated set of objectives, all under strict computation and power limitations. We therefore argue that the computational kernels enabling robotic autonomy must be scheduled and optimized to guarantee timely and correct behavior, while allowing for reconfiguration of scheduling parameters at run time. In this paper, we consider a necessary first step towards this goal of computational awareness in autonomous robots: an empirical study of a base set of computational kernels from the resource management perspective. Specifically, we conduct a data-driven study of the timing, power, and memory performance of kernels for localization and mapping, path planning, task allocation, depth estimation, and optical flow, across three embedded computing platforms. We profile and analyze these kernels to provide insight into scheduling and dynamic resource management for computation-aware autonomous robots. Notably, our results show that there is a correlation of kernel performance with a robot's operational environment, justifying the notion of computation-aware robots and why our work is a crucial step towards this goal.

cs.RO↗

arXiv2021

A Predictive Autonomous Decision Aid for Calibrating Human-Autonomy Reliance in Multi-Agent Task Assignment

In this work, we develop a game-theoretic modeling of the interaction between a human operator and an autonomous decision aid when they collaborate in a multi-agent task allocation setting. In this setting, we propose a decision aid that is designed to calibrate the operator's reliance on the aid through a sequence of interactions to improve overall human-autonomy team performance. The autonomous decision aid employs a long short-term memory (LSTM) neural network for human action prediction and a Bayesian parameter filtering method to improve future interactions, resulting in an aid that can adapt to the dynamics of human reliance. The proposed method is then tested against a large set of simulated human operators from the choice prediction competition (CPC18) data set, and shown to significantly improve human-autonomy interactions when compared to a myopic decision aid that only suggests predicted human actions without an understanding of reliance.

cs.MA↗

arXiv2021

Distributed Adaptive and Resilient Control of Multi-Robot Systems with Limited Field of View Interactions

In this paper, we consider two coupled problems for distributed multi-robot systems (MRSs) coordinating with limited field of view (FOV) sensors: adaptive tuning of interaction gains and rejection of sensor attacks. First, a typical shortcoming of distributed control frameworks (e.g., potential fields) is that the overall system behavior is highly sensitive to the gain assigned to relative interactions. Second, MRSs with limited FOV sensors can be more susceptible to sensor attacks aimed at their FOVs, and therefore must be resilient to such attacks. Based on these shortcomings, we propose a comprehensive solution that combines efforts in adaptive gain tuning and attack resilience to the problem of topology control for MRSs with limited FOVs. Specifically, we first derive an adaptive gain tuning scheme based on satisfying nominal pairwise interactions, which yields a dynamic balancing of interaction strengths in a robot's neighborhood. We then model additive sensor and actuator attacks (or faults) and derive H infinity control protocols by employing a static output-feedback technique, guaranteeing bounded L2 gains of the error induced by the attack (fault) signals. Finally, simulation results using ROS Gazebo are provided to support our theoretical findings.

cs.RO↗

arXiv2021

Intermittent Deployment for Large-Scale Multi-Robot Forage Perception: Data Synthesis, Prediction, and Planning

Monitoring the health and vigor of grasslands is vital for informing management decisions to optimize rotational grazing in agriculture applications. To take advantage of forage resources and improve land productivity, we require knowledge of pastureland growth patterns that is simply unavailable at state of the art. In this paper, we propose to deploy a team of robots to monitor the evolution of an unknown pastureland environment to fulfill the above goal. To monitor such an environment, which usually evolves slowly, we need to design a strategy for rapid assessment of the environment over large areas at a low cost. Thus, we propose an integrated pipeline comprising of data synthesis, deep neural network training and prediction along with a multi-robot deployment algorithm that monitors pasturelands intermittently. Specifically, using expert-informed agricultural data coupled with novel data synthesis in ROS Gazebo, we first propose a new neural network architecture to learn the spatiotemporal dynamics of the environment. Such predictions help us to understand pastureland growth patterns on large scales and make appropriate monitoring decisions for the future. Based on our predictions, we then design an intermittent multi-robot deployment policy for low-cost monitoring. Finally, we compare the proposed pipeline with other methods, from data synthesis to prediction and planning, to corroborate our pipeline's performance.

cs.RO↗

arXiv2021

Monitoring Over the Long Term: Intermittent Deployment and Sensing Strategies for Multi-Robot Teams

In this paper, we formulate and solve the intermittent deployment problem, which yields strategies that couple \emph{when} heterogeneous robots should sense an environmental process, with where a deployed team should sense in the environment. As a motivation, suppose that a spatiotemporal process is slowly evolving and must be monitored by a multi-robot team, e.g., unmanned aerial vehicles monitoring pasturelands in a precision agriculture context. In such a case, an intermittent deployment strategy is necessary as persistent deployment or monitoring is not cost-efficient for a slowly evolving process. At the same time, the problem of where to sense once deployed must be solved as process observations yield useful feedback for determining effective future deployment and monitoring decisions. In this context, we model the environmental process to be monitored as a spatiotemporal Gaussian process with mutual information as a criterion to measure our understanding of the environment. To make the sensing resource-efficient, we demonstrate how to use matroid constraints to impose a diverse set of homogeneous and heterogeneous constraints. In addition, to reflect the cost-sensitive nature of real-world applications, we apply budgets on the cost of deployed heterogeneous robot teams. To solve the resulting problem, we exploit the theories of submodular optimization and matroids and present a greedy algorithm with bounds on sub-optimality. Finally, Monte Carlo simulations demonstrate the correctness of the proposed method.

cs.RO↗

arXiv2021

Submodular Optimization for Coupled Task Allocation and Intermittent Deployment Problems

In this paper, we demonstrate a formulation for optimizing coupled submodular maximization problems with provable sub-optimality bounds. In robotics applications, it is quite common that optimization problems are coupled with one another and therefore cannot be solved independently. Specifically, we consider two problems coupled if the outcome of the first problem affects the solution of a second problem that operates over a longer time scale. For example, in our motivating problem of environmental monitoring, we posit that multi-robot task allocation will potentially impact environmental dynamics and thus influence the quality of future monitoring, here modeled as a multi-robot intermittent deployment problem. The general theoretical approach for solving this type of coupled problem is demonstrated through this motivating example. Specifically, we propose a method for solving coupled problems modeled by submodular set functions with matroid constraints. A greedy algorithm for solving this class of problem is presented, along with sub-optimality guarantees. Finally, practical optimality ratios are shown through Monte Carlo simulations to demonstrate that the proposed algorithm can generate near-optimal solutions with high efficiency.

cs.RO↗

arXiv2021

Distributed Resilient Submodular Action Selection in Adversarial Environments

In this letter, we consider a distributed submodular maximization problem for multi-robot systems when attacked by adversaries. One of the major challenges for multi-robot systems is to increase resilience against failures or attacks. This is particularly important for distributed systems under attack as there is no central point of command that can detect, mitigate, and recover from attacks. Instead, a distributed multi-robot system must coordinate effectively to overcome adversarial attacks. In this work, our distributed submodular action selection problem models a broad set of scenarios where each robot in a multi-robot system has multiple action selections that may fulfill a global objective, such as exploration or target tracking. To increase resilience in this context, we propose a fully distributed algorithm to guide each robot's action selection when the system is attacked. The proposed algorithm guarantees performance in a worst-case scenario where up to a portion of the robots malfunction due to attacks. Importantly, the proposed algorithm is also consistent, as it is shown to converge to the same solution as a centralized method. Finally, a distributed resilient multi-robot exploration problem is presented to confirm the performance of the proposed algorithm.

cs.RO↗

arXiv2020

Distributed Adaptive and Resilient Control of Multi-Robot Systems with Limited Field of View Interactions using Q-Learning

In this paper, we consider the problem of dynamically tuning gains for multi-robot systems (MRS) under potential based control design framework where the MRS team coordinates to maintain a connected topology while equipped with limited field of view sensors. Applying the potential-based control framework and assuming robot interaction is encoded by a triangular geometry, we derive a distributed control law in order to achieve the topology control objective. A typical shortcoming of potential-based control in distributed networks is that the overall system behavior is highly sensitive to gain-tuning. To overcome this limitation, we propose a distributed and adaptive gain controller that preserves a designed pairwise interaction strength, independent of the network size. Over that, we implement a control scheme that enables the MRS to be resilient against exogenous attacks on on-board sensors or actuator of the robots in MRS. In this regard, we model additive sensor and actuator faults which are induced externally to render the MRS unstable. However, applying $H_{\infty}$ control protocols by employing a static output-feedback design technique guarantees bounded $L_2$ gains of the error induced by the sensor and actuator fault signals. Finally, we apply policy iteration based Q-Learning to solve for adaptive gains for the discrete-time MRS. Simulation results are provided to support the theoretical findings.

eess.SY↗

arXiv2020

Anticipatory Human-Robot Path Planning for Search and Rescue

In this work, our goal is to extend the existing search and rescue paradigm by allowing teams of autonomous unmanned aerial vehicles (UAVs) to collaborate effectively with human searchers on the ground. We derive a framework that includes a simulated lost person behavior model, as well as a human searcher behavior model that is informed by data collected from past search tasks. These models are used together to create a probabilistic heatmap of the lost person's position and anticipated searcher trajectories. We then use Gaussian processes with a Gibbs' kernel to accurately model a limited field-of-view (FOV) sensor, e.g., thermal cameras, from which we derive a risk metric that drives UAV path optimization. Our framework finally computes a set of search paths for a team of UAVs to autonomously complement human searchers' efforts.

cs.RO↗

arXiv2019

Distributed Assignment with Limited Communication for Multi-Robot Multi-Target Tracking

We study the problem of tracking multiple moving targets using a team of mobile robots. Each robot has a set of motion primitives to choose from in order to collectively maximize the number of targets tracked or the total quality of tracking. Our focus is on scenarios where communication is limited and the robots have limited time to share information with their neighbors. As a result, we seek distributed algorithms that can find solutions in bounded amount of time. We present two algorithms: (1) a greedy algorithm that is guaranteed finds a $2$-approximation to the optimal (centralized) solution albeit requiring $|R|$ communication rounds in the worst-case, where $|R|$ denotes the number of robots; and (2) a local algorithm that finds a $\mathcal{O}\left((1+ε)(1+1/h)\right)$-approximation algorithm in $\mathcal{O}(h\log 1/ε)$ communication rounds. Here, $h$ and $ε$ are parameters that allow the user to trade-off the solution quality with communication time. In addition to theoretical results, we present empirical evaluation including comparisons with centralized optimal solutions.

cs.RO↗

arXiv2019

Intelligent Knowledge Distribution: Constrained-Action POMDPs for Resource-Aware Multi-Agent Communication

This paper addresses a fundamental question of multi-agent knowledge distribution: what information should be sent to whom and when, with the limited resources available to each agent? Communication requirements for multi-agent systems can be rather high when an accurate picture of the environment and the state of other agents must be maintained. To reduce the impact of multi-agent coordination on networked systems, e.g., power and bandwidth, this paper introduces two concepts for partially observable Markov decision processes (POMDPs): 1) action-based constraints which yield constrained-action POMDPs (CA-POMDPs); and 2) soft probabilistic constraint satisfaction for the resulting infinite-horizon controllers. To enable constraint analysis over an infinite horizon, an unconstrained policy is first represented as a Finite State Controller (FSC) and optimized with policy iteration. The FSC representation then allows for a combination of Markov chain Monte Carlo and discrete optimization to improve the probabilistic constraint satisfaction of the controller while minimizing the impact to the value function. Within the CA-POMDP framework we then propose Intelligent Knowledge Distribution (IKD) which yields per-agent policies for distributing knowledge between agents subject to interaction constraints. Finally, the CA-POMDP and IKD concepts are validated using an asset tracking problem where multiple unmanned aerial vehicles (UAVs) with heterogeneous sensors collaborate to localize a ground asset to assist in avoiding unseen obstacles in a disaster area. The IKD model was able to maintain asset tracking through multi-agent communications while only violating soft power and bandwidth constraints 3% of the time, while greedy and naive approaches violated constraints more than 60% of the time.

cs.MA↗

arXiv2018

Distributed Simultaneous Action and Target Assignment for Multi-Robot Multi-Target Tracking

We study a multi-robot assignment problem for multi-target tracking. The proposed problem can be viewed as the mixed packing and covering problem. To deal with a limitation on both sensing and communication ranges, a distributed approach is taken into consideration. A local algorithm gives theoretical bounds on both the running time and approximation ratio to an optimal solution. We employ a local algorithm of max-min linear programs to solve the proposed task. Simulation result shows that a local algorithm is an effective solution to the multi-robot task allocation.

cs.RO↗

arXiv2014

Route Swarm: Wireless Network Optimization through Mobility

In this paper, we demonstrate a novel hybrid architecture for coordinating networked robots in sensing and information routing applications. The proposed INformation and Sensing driven PhysIcally REconfigurable robotic network (INSPIRE), consists of a Physical Control Plane (PCP) which commands agent position, and an Information Control Plane (ICP) which regulates information flow towards communication/sensing objectives. We describe an instantiation where a mobile robotic network is dynamically reconfigured to ensure high quality routes between static wireless nodes, which act as source/destination pairs for information flow. The ICP commands the robots towards evenly distributed inter-flow allocations, with intra-flow configurations that maximize route quality. The PCP then guides the robots via potential-based control to reconfigure according to ICP commands. This formulation, deemed Route Swarm, decouples information flow and physical control, generating a feedback between routing and sensing needs and robotic configuration. We demonstrate our propositions through simulation under a realistic wireless network regime.

eess.SY↗