Robust Multi-Agent Task Assignment in Failure-Prone and Adversarial Environments

The problem of assigning agents to tasks is a central computational challenge in many multi-agent autonomous systems. However, in the real world, agents are not always perfect and may fail due to a number of reasons. A motivating application is where the agents are robots that operate in the physical world and are susceptible to failures. This paper studies the problem of Robust Multi-Agent Task Assignment, which seeks to find an assignment that maximizes overall system performance while accounting for potential failures of the agents. We investigate both, stochastic and adversarial failures under this framework. For both cases, we present efficient algorithms that yield optimal or near-optimal results.

Combining Geometric and Information-Theoretic Approaches for Multi-Robot Exploration

We present an algorithm to explore an orthogonal polygon using a team of $p$ robots. This algorithm combines ideas from information-theoretic exploration algorithms and computational geometry based exploration algorithms. We show that the exploration time of our algorithm is competitive (as a function of $p$) with respect to the offline optimal exploration algorithm. The algorithm is based on a single-robot polygon exploration algorithm, a tree exploration algorithm for higher level planning and a submodular orienteering algorithm for lower level planning. We discuss how this strategy can be adapted to real-world settings to deal with noisy sensors. In addition to theoretical analysis, we investigate the performance of our algorithm through simulations for multiple robots and experiments with a single robot.

Robust Multiple-Path Orienteering Problem: Securing Against Adversarial Attacks

The multiple-path orienteering problem asks for paths for a team of robots that maximize the total reward collected while satisfying budget constraints on the path length. This problem models many multi-robot routing tasks such as exploring unknown environments and information gathering for environmental monitoring. In this paper, we focus on how to make the robot team robust to failures when operating in adversarial environments. We introduce the Robust Multiple-path Orienteering Problem (RMOP) where we seek worst-case guarantees against an adversary that is capable of attacking at most $\alpha$ robots. Our main contribution is a general approximation scheme with bounded approximation guarantee that depends on $\alpha$ and the approximation factor for single robot orienteering. In particular, we show that the algorithm yields a (i) constant-factor approximation when the cost function is modular; (ii) $\log$ factor approximation when the cost function is submodular; and (iii) constant-factor approximation when the cost function is submodular but the robots are allowed to exceed their path budgets by a bounded amount. In addition to theoretical analysis, we perform simulation study for an ocean monitoring application to demonstrate the efficacy of our approach.

Evaluation of Cross-View Matching to Improve Ground Vehicle Localization with Aerial Perception

Cross-view matching refers to the problem of finding the closest match to a given query ground-view image to one from a database of aerial images. If the aerial images are geotagged, then the closest matching aerial image can be used to localize the query ground-view image. Recently, due to the success of deep learning methods, a number of cross-view matching techniques have been proposed. These techniques perform well for the matching of isolated query images. In this paper, we evaluate cross-view matching for the task of localizing a ground vehicle over a longer trajectory. We use the cross-view matching module as a sensor measurement fused with a particle filter. We evaluate the performance of this method using a city-wide dataset collected in photorealistic simulation using five parameters: height of aerial images, the pitch of the aerial camera mount, field-of-view of ground camera, measurement model and resampling strategy for the particles in the particle filter.

Risk-Aware Planning and Assignment for Ground Vehicles using Uncertain Perception from Aerial Vehicles

We propose a risk-aware framework for multi-robot, multi-demand assignment and planning in unknown environments. Our motivation is disaster response and search-and-rescue scenarios where ground vehicles must reach demand locations as soon as possible. We consider a setting where the terrain information is available only in the form of an aerial, georeferenced image. Deep learning techniques can be used for semantic segmentation of the aerial image to create a cost map for safe ground robot navigation. Such segmentation may still be noisy. Hence, we present a joint planning and perception framework that accounts for the risk introduced due to noisy perception. Our contributions are two-fold: (i) we show how to use Bayesian deep learning techniques to extract risk at the perception level; and (ii) use a risk-theoretical measure, CVaR, for risk-aware planning and assignment. The pipeline is theoretically established, then empirically analyzed through two datasets. We find that accounting for risk at both levels produces quantifiably safer paths and assignments.

Risk-Aware Submodular Optimization for Multi-Robot Coordination

We study the problem of incorporating risk while making combinatorial decisions under uncertainty. We formulate a discrete submodular maximization problem for selecting a set using Conditional-Value-at-Risk (CVaR), a risk metric commonly used in financial analysis. While CVaR has recently been used in optimization of linear cost functions in robotics, we take the first step towards extending this to discrete submodular optimization and provide several positive results. Specifically, we propose the Sequential Greedy Algorithm that provides an approximation guarantee on finding the maxima of the CVaR cost function under a matroidal constraint. The approximation guarantee shows that the solution produced by our algorithm is within a constant factor of the optimal and an additive term that depends on the optimal. Our analysis uses the curvature of the submodular set function, and proves that the algorithm runs in polynomial time. This formulates a number of combinatorial optimization problems that appear in robotics. We use two such problems, vehicle assignment under uncertainty for mobility-on-demand and sensor selection with failures for environmental monitoring, as case studies to demonstrate the efficacy of our formulation. In particular, for the mobility-on-demand study, we propose an online triggering assignment algorithm that triggers a new assignment only can potentially lead to reducing the waiting time at demand locations. We verify the performance of the Sequential Greedy Algorithm and the online triggering assignment algorithm through simulations.

Experimental Evaluation of a Pseudo-Doppler Direction-Finding System for Localizing Radio Tags

We present the design of a radio antenna system for obtaining instantaneous bearing measurements towards a radio emitter. Our work is motivated by applications where robots are used for localizing and tracking radio-tagged wildlife. The traditional method is to use directional antennas that need to be rotated in order find the bearing which is time consuming. Instead, we present a low-cost system capable of finding bearing measurements almost instantaneously using an antenna array. This is particularly appealing for wildlife tracking with Unmanned Aerial Systems (UASs) where remaining stationary can be challenging and energy consuming, in addition to being slow. The proposed system uses existing open source hardware and software systems and leverages principles of pseudo Doppler direction-finding. The resulting system was tested in an anechoic chamber and in outdoor settings. The outdoor tests with particle filtering show that the resulting system is capable of localizing radio tags within 5 meter accuracy starting with an initial estimate of 200m x 200m.

Recreating Bat Behavior on Quad-rotor UAVs-A Simulation Approach

We develop an effective computer model to simulate sensing environments that consist of natural trees. The simulated environments are random and contain full geometry of the tree foliage. While this simulated model can be used as a general platform for studying the sensing mechanism of different flying species, our ultimate goal is to build bat-inspired Quad-rotor UAVs- UAVs that can recreate bat's flying behavior (e.g., obstacle avoidance, path planning) in dense vegetation. To this end, we also introduce an foliage echo simulator that can produce simulated echoes by mimicking bat's biosonar. In our current model, a few realistic model choices or assumptions are made. First, in order to create natural looking trees, the branching structures of trees are modeled by L-systems, whereas the detailed geometry of branches, sub-branches and leaves is created by randomizing a reference tree in a CAD object file. Additionally, the foliage echo simulator is simplified so that no shading effect is considered. We demonstrate our developed model by simulating real-world scenarios with multiple trees and compute the corresponding impulse responses along a Quad-rotor trajectory.

Crop Height and Plot Estimation from Unmanned Aerial Vehicles using 3D LiDAR

In this paper, we present techniques to measure crop heights using a 3D LiDAR mounted on an Unmanned Aerial Vehicle (UAV). Knowing the height of plants is crucial to monitor their overall health and growth cycles, especially for high-throughput plant phenotyping. We present a methodology for extracting plant heights from 3D LiDAR point clouds, specifically focusing on row-crop environments. The key steps in our algorithm are clustering of LiDAR points to semi-automatically detect plots, local ground plane estimation, and height estimation. The plot detection uses a k--means clustering algorithm followed by a voting scheme to find the bounding boxes of individual plots. We conducted a series of experiments in controlled and natural settings. Our algorithm was able to estimate the plant heights in a field with 112 plots within +-5.36%. This is the first such dataset for 3D LiDAR from an airborne robot over a wheat field. The developed code can be found on the GitHub repository located at https://github.com/hsd1121/PointCloudProcessing.

Distributed Attack-Robust Submodular Maximization for Multi-Robot Planning

We aim to guard swarm-robotics applications against denial-of-service (DoS) failures/attacks that result in withdrawals of robots. We focus on applications requiring the selection of actions for each robot, among a set of available ones, e.g., which trajectory to follow. Such applications are central in large-scale robotic/control applications, e.g., multi-robot motion planning for target tracking. But the current attack-robust algorithms are centralized, and scale quadratically with the problem size (e.g., number of robots). Thus, in this paper, we propose a general-purpose distributed algorithm towards robust optimization at scale, with local communications only. We name it distributed robust maximization (DRM). DRM proposes a divide-and-conquer approach that distributively partitions the problem among K cliques of robots. The cliques optimize in parallel, independently of each other. That way, DRM also offers significant computational speed-ups up to 1/K^2 the running time of its centralized counterparts. K depends on the robots' communication range, which is given as input to DRM. DRM also achieves a close-to-optimal performance, equal to the guaranteed performance of its centralized counterparts. We demonstrate DRM's performance in both Gazebo and MATLAB simulations, in scenarios of active target tracking with swarms of robots. We observe DRM achieves significant computational speed-ups (it is 3 to 4 orders faster) and, yet, nearly matches the tracking performance of its centralized counterparts.