Spring Berman

Karthik Elamvazhuthi, Hendrik Kuiper, Matthias Kawski et al.

In this paper, we investigate the exact controllability properties of an advection-diffusion equation on a bounded domain, using time- and space-dependent velocity fields as the control parameters. This partial differential equation (PDE) is the Kolmogorov forward equation for a reflected diffusion process that models the spatiotemporal evolution of a swarm of agents. We prove that if a target probability density has bounded first-order weak derivatives and is uniformly bounded from below by a positive constant, then it can be reached in finite time using control inputs that are bounded in space and time. We then extend this controllability result to a class of advection-diffusion-reaction PDEs that corresponds to a hybrid-switching diffusion process (HSDP), in which case the reaction parameters are additionally incorporated as the control inputs. Our proof for controllability of the advection-diffusion equation is constructive and is based on linear operator semigroup theoretic arguments and spectral properties of the multiplicatively perturbed Neumann Laplacian. For the HSDP, we first constructively prove controllability of the associated continuous-time Markov chain (CTMC) system, in which the state space is finite. Then we show that our controllability results for the advection-diffusion equation and the CTMC can be combined to establish controllability of the forward equation of the HSDP. Lastly, we provide constructive solutions to the problem of asymptotically stabilizing an HSDP to a target non-negative stationary distribution using time-independent state feedback laws, which correspond to spatially-dependent coefficients of the associated system of PDEs.

Karthik Elamvazhuthi, Chase Adams, Spring Berman

In this paper, we consider stochastic coverage of bounded domains by a diffusing swarm of robots that take local measurements of an underlying scalar field. We introduce three control methodologies with diffusion, advection, and reaction as independent control inputs. We analyze the diffusion-based control strategy using standard operator semigroup-theoretic arguments. We show that the diffusion coefficient can be chosen to be dependent only on the robots' local measurements to ensure that the swarm density converges to a function proportional to the scalar field. The boundedness of the domain precludes the need to impose assumptions on decaying properties of the scalar field at infinity. Moreover, exponential convergence of the swarm density to the equilibrium follows from properties of the spectrum of the semigroup generator. In addition, we use the proposed coverage method to construct a time-inhomogenous diffusion process and apply the observability of the heat equation to reconstruct the scalar field over the entire domain from observations of the robots' random motion over a small subset of the domain. We verify our results through simulations of the coverage scenario on a 2D domain and the field estimation scenario on a 1D domain.

Karthik Elamvazhuthi, Piyush Grover, Spring Berman

This paper considers the relaxed version of the transport problem for general nonlinear control systems, where the objective is to design time-varying feedback laws that transport a given initial probability measure to a target probability measure under the action of the closed-loop system. To make the problem analytically tractable, we consider control laws that are stochastic, i.e., the control laws are maps from the state space of the control system to the space of probability measures on the set of admissible control inputs. Under some controllability assumptions on the control system as defined on the state space, we show that the transport problem, considered as a controllability problem for the lifted control system on the space of probability measures, is well-posed for a large class of initial and target measures. We use this to prove the well-posedness of a fixed-endpoint optimal control problem defined on the space of probability measures, where along with the terminal constraints, the goal is to optimize an objective functional along the trajectory of the control system. This optimization problem can be posed as an infinite-dimensional linear programming problem. This formulation facilitates numerical solutions of the transport problem for low-dimensional control systems, as we show in two numerical examples.

Shenbagaraj Kannapiran, Nalin Bendapudi, Ming-Yuan Yu et al.

Robust feature matching forms the backbone for most Visual Simultaneous Localization and Mapping (vSLAM), visual odometry, 3D reconstruction, and Structure from Motion (SfM) algorithms. However, recovering feature matches from texture-poor scenes is a major challenge and still remains an open area of research. In this paper, we present a Stereo Visual Odometry (StereoVO) technique based on point and line features which uses a novel feature-matching mechanism based on an Attention Graph Neural Network that is designed to perform well even under adverse weather conditions such as fog, haze, rain, and snow, and dynamic lighting conditions such as nighttime illumination and glare scenarios. We perform experiments on multiple real and synthetic datasets to validate the ability of our method to perform StereoVO under low visibility weather and lighting conditions through robust point and line matches. The results demonstrate that our method achieves more line feature matches than state-of-the-art line matching algorithms, which when complemented with point feature matches perform consistently well in adverse weather and dynamic lighting conditions.

Karthik Elamvazhuthi, Hendrik Kuiper, Spring Berman

We consider the problem of controlling the spatiotemporal probability distribution of a robotic swarm that evolves according to a reflected diffusion process, using the space- and time-dependent drift vector field parameter as the control variable. In contrast to previous work on control of the Fokker-Planck equation, a zero-flux boundary condition is imposed on the partial differential equation that governs the swarm probability distribution, and only bounded vector fields are considered to be admissible as control parameters. Under these constraints, we show that any initial probability distribution can be transported to a target probability distribution under certain assumptions on the regularity of the target distribution. In particular, we show that if the target distribution is (essentially) bounded, has bounded first-order and second-order partial derivatives, and is bounded from below by a strictly positive constant, then this distribution can be reached exactly using a drift vector field that is bounded in space and time. Our proof is constructive and based on classical linear semigroup theoretic concepts.

Rakshith Subramanyam, Kowshik Thopalli, Spring Berman et al.

The problem of adapting models from a source domain using data from any target domain of interest has gained prominence, thanks to the brittle generalization in deep neural networks. While several test-time adaptation techniques have emerged, they typically rely on synthetic data augmentations in cases of limited target data availability. In this paper, we consider the challenging setting of single-shot adaptation and explore the design of augmentation strategies. We argue that augmentations utilized by existing methods are insufficient to handle large distribution shifts, and hence propose a new approach SiSTA (Single-Shot Target Augmentations), which first fine-tunes a generative model from the source domain using a single-shot target, and then employs novel sampling strategies for curating synthetic target data. Using experiments with a state-of-the-art domain adaptation method, we find that SiSTA produces improvements as high as 20\% over existing baselines under challenging shifts in face attribute detection, and that it performs competitively to oracle models obtained by training on a larger target dataset.

Karthik Elamvazhuthi, Sean Wilson, Spring Berman

We consider a multi-agent confinement control problem in which a single leader has a purely repulsive effect on follower agents with double-integrator dynamics. By decomposing the leader's control inputs into periodic and aperiodic components, we show that the leader can be driven so as to guarantee confinement of the followers about a time-dependent trajectory in the plane. We use tools from averaging theory and an input-to-state stability type argument to derive conditions on the model parameters that guarantee confinement of the followers about the trajectory. For the case of a single follower, we show that if the follower starts at the origin, then the error in trajectory tracking can be made arbitrarily small depending on the frequency of the periodic control components and the rate of change of the trajectory. We validate our approach using simulations and experiments with a small mobile robot.

Shenbagaraj Kannapiran, Sreenithy Chandran, Suren Jayasuriya et al.

The study of non-line-of-sight (NLOS) imaging is growing due to its many potential applications, including rescue operations and pedestrian detection by self-driving cars. However, implementing NLOS imaging on a moving camera remains an open area of research. Existing NLOS imaging methods rely on time-resolved detectors and laser configurations that require precise optical alignment, making it difficult to deploy them in dynamic environments. This work proposes a data-driven approach to NLOS imaging, PathFinder, that can be used with a standard RGB camera mounted on a small, power-constrained mobile robot, such as an aerial drone. Our experimental pipeline is designed to accurately estimate the 2D trajectory of a person who moves in a Manhattan-world environment while remaining hidden from the camera's field-of-view. We introduce a novel approach to process a sequence of dynamic successive frames in a line-of-sight (LOS) video using an attention-based neural network that performs inference in real-time. The method also includes a preprocessing selection metric that analyzes images from a moving camera which contain multiple vertical planar surfaces, such as walls and building facades, and extracts planes that return maximum NLOS information. We validate the approach on in-the-wild scenes using a drone for video capture, thus demonstrating low-cost NLOS imaging in dynamic capture environments.

Aniket Shirsat, Shatadal Mishra, Wenlong Zhang et al.

In this paper, we present a consensus-based decentralized multi-robot approach to reconstruct a discrete distribution of features, modeled as an occupancy grid map, that represent information contained in a bounded planar 2D environment, such as visual cues used for navigation or semantic labels associated with object detection. The robots explore the environment according to a random walk modeled by a discrete-time discrete-state (DTDS) Markov chain and estimate the feature distribution from their own measurements and the estimates communicated by neighboring robots, using a distributed Chernoff fusion protocol. We prove that under this decentralized fusion protocol, each robot's feature distribution converges to the ground truth distribution in an almost sure sense. We verify this result in numerical simulations that show that the Hellinger distance between the estimated and ground truth feature distributions converges to zero over time for each robot. We also validate our strategy through Software-In-The-Loop (SITL) simulations of quadrotors that search a bounded square grid for a set of visual features distributed on a discretized circle.

Zahi Kakish, Sritanay Vedartham, Spring Berman

In this work, we present preliminary work on a novel method for Human-Swarm Interaction (HSI) that can be used to change the macroscopic behavior of a swarm of robots with decentralized sensing and control. By integrating a small yet capable hand gesture recognition convolutional neural network (CNN) with the next-generation Robot Operating System \emph{ros2}, which enables decentralized implementation of robot software for multi-robot applications, we demonstrate the feasibility of programming a swarm of robots to recognize and respond to a sequence of hand gestures that capable of correspond to different types of swarm behaviors. We test our approach using a sequence of gestures that modifies the target inter-robot distance in a group of three Turtlebot3 Burger robots in order to prevent robot collisions with obstacles. The approach is validated in three different Gazebo simulation environments and in a physical testbed that reproduces one of the simulated environments.

Aniket Shirsat, Spring Berman

We consider a scenario in which a group of quadrotors is tasked at tracking multiple stationary targets in an unknown, bounded environment. The quadrotors search for targets along a spatial grid overlaid on the environment while performing a random walk on this grid modeled by a discrete-time discrete-state (DTDS) Markov chain. The quadrotors can transmit their estimates of the target locations to other quadrotors that occupy their current location on the grid; thus, their communication network is time-varying and not necessarily connected. We model the search procedure as a renewal-reward process on the underlying DTDS Markov chain. To accommodate changes in the set of targets observed by each quadrotor as it explores the environment, along with uncertainties in the quadrotors' measurements of the targets, we formulate the tracking problem in terms of Random Finite Sets (RFS). The quadrotors use RFS-based Probability Hypothesis Density (PHD) filters to estimate the number of targets and their locations. We present a theoretical estimation framework, based on the Gaussian Mixture formulation of the PHD filter, and preliminary simulation results toward extending existing approaches for RFS-based multi-target tracking to a decentralized multi-robot strategy for multi-target tracking. We validate this approach with simulations of multi-target tracking scenarios with different densities of robots and targets, and we evaluate the average time required for the robots in each scenario to reach agreement on a common set of targets.

Aniket Shirsat, Karthik Elamvazhuthi, Spring Berman

In this paper, we propose a probabilistic consensus-based multi-robot search strategy that is robust to communication link failures, and thus is suitable for disaster affected areas. The robots, capable of only local communication, explore a bounded environment according to a random walk modeled by a discrete-time discrete-state (DTDS) Markov chain and exchange information with neighboring robots, resulting in a time-varying communication network topology. The proposed strategy is proved to achieve consensus, here defined as agreement on the presence of a static target, with no assumptions on the connectivity of the communication network. Using numerical simulations, we investigate the effect of the robot population size, domain size, and information uncertainty on the consensus time statistics under this scheme. We also validate our theoretical results with 3D physics-based simulations in Gazebo. The simulations demonstrate that all robots achieve consensus in finite time with the proposed search strategy over a range of robot densities in the environment.

Zahi M. Kakish, Karthik Elamvazhuthi, Spring Berman

In this paper, we present a reinforcement learning approach to designing a control policy for a "leader" agent that herds a swarm of "follower" agents, via repulsive interactions, as quickly as possible to a target probability distribution over a strongly connected graph. The leader control policy is a function of the swarm distribution, which evolves over time according to a mean-field model in the form of an ordinary difference equation. The dependence of the policy on agent populations at each graph vertex, rather than on individual agent activity, simplifies the observations required by the leader and enables the control strategy to scale with the number of agents. Two Temporal-Difference learning algorithms, SARSA and Q-Learning, are used to generate the leader control policy based on the follower agent distribution and the leader's location on the graph. A simulation environment corresponding to a grid graph with 4 vertices was used to train and validate the control policies for follower agent populations ranging from 10 to 100. Finally, the control policies trained on 100 simulated agents were used to successfully redistribute a physical swarm of 10 small robots to a target distribution among 4 spatial regions.

Ragesh K. Ramachandran, Spring Berman

In this work, we present a novel automated procedure for constructing a metric map of an unknown domain with obstacles using uncertain position data collected by a swarm of resource-constrained robots. The robots obtain this data during random exploration of the domain by combining onboard odometry information with noisy measurements of signals received from transmitters located outside the domain. This data is processed offline to compute a density function of the free space over a discretization of the domain. We use persistent homology techniques from topological data analysis to estimate a value for thresholding the density function, thereby segmenting the obstacle-occupied region in the unknown domain. Our approach is substantiated with theoretical results to prove its completeness and to analyze its time complexity. The effectiveness of the procedure is illustrated with numerical simulations conducted on six different domains, each with two signal transmitters.

Ragesh K. Ramachandran, Zahi Kakish, Spring Berman

In this work, we present a novel distributed method for constructing an occupancy grid map of an unknown environment using a swarm of robots with global localization capabilities and limited inter-robot communication. The robots explore the domain by performing Levy walks in which their headings are defined by maximizing the mutual information between the robot's estimate of its environment in the form of an occupancy grid map and the distance measurements that it is likely to obtain when it moves in that direction. Each robot is equipped with laser range sensors, and it builds its occupancy grid map by repeatedly combining its own distance measurements with map information that is broadcast by neighboring robots. Using results on average consensus over time-varying graph topologies, we prove that all robots' maps will eventually converge to the actual map of the environment. In addition, we demonstrate that a technique based on topological data analysis, developed in our previous work for generating topological maps, can be readily extended for adaptive thresholding of occupancy grid maps. We validate the effectiveness of our distributed exploration and mapping strategy through a series of 2D simulations and multi-robot experiments.

Karthik Elamvazhuthi, Hendrik Kuiper, Spring Berman

This paper presents a novel partial differential equation (PDE)-based framework for controlling an ensemble of robots, which have limited sensing and actuation capabilities and exhibit stochastic behaviors, to perform mapping and coverage tasks. We model the ensemble population dynamics as an advection-diffusion-reaction PDE model and formulate the mapping and coverage tasks as identification and control problems for this model. In the mapping task, robots are deployed over a closed domain to gather data, which is unlocalized and independent of robot identities, for reconstructing the unknown spatial distribution of a region of interest. We frame this task as a convex optimization problem whose solution represents the region as a spatially-dependent coefficient in the PDE model. We then consider a coverage problem in which the robots must perform a desired activity at a programmable probability rate to achieve a target spatial distribution of activity over the reconstructed region of interest. We formulate this task as an optimal control problem in which the PDE model is expressed as a bilinear control system, with the robots' coverage activity rate and velocity field defined as the control inputs. We validate our approach with simulations of a combined mapping and coverage scenario in two environments with three target coverage distributions.

Shiba Biswal, Karthik Elamvazhuthi, Spring Berman

This paper, the second of a two-part series, presents a method for mean-field feedback stabilization of a swarm of agents on a finite state space whose time evolution is modeled as a continuous time Markov chain (CTMC). The resulting (mean-field) control problem is that of controlling a nonlinear system with desired global stability properties. We first prove that any probability distribution with a strongly connected support can be stabilized using time-invariant inputs. Secondly, we show the asymptotic controllability of all possible probability distributions, including distributions that assign zero density to some states and which do not necessarily have a strongly connected support. Lastly, we demonstrate that there always exists a globally asymptotically stabilizing decentralized density feedback law with the additional property that the control inputs are zero at equilibrium, whenever the graph is strongly connected and bidirected. Then the problem of synthesizing closed-loop polynomial feedback is framed as a optimization problem using state-of-the-art sum-of-squares optimization tools. The optimization problem searches for polynomial feedback laws that make the candidate Lyapunov function a stability certificate for the resulting closed-loop system. Our methodology is tested for two cases on a five vertex graph, and the stabilization properties of the constructed control laws are validated with numerical simulations of the corresponding system of ordinary differential equations.

Karthik Elamvazhuthi, Vaibhav Deshmukh, Matthias Kawski et al.

In this paper, we study the controllability and stabilizability properties of the Kolmogorov forward equation of a continuous time Markov chain (CTMC) evolving on a finite state space, using the transition rates as the control parameters. Firstly, we prove small-time local and global controllability from and to strictly positive equilibrium configurations when the underlying graph is strongly connected. Secondly, we show that there always exists a locally exponentially stabilizing decentralized linear (density-)feedback law that takes zero valu at equilibrium and respects the graph structure, provided that the transition rates are allowed to be negative and the desired target density lies in the interior of the set of probability densities. For bidirected graphs, that is, graphs where a directed edge in one direction implies an edge in the opposite direction, we show that this linear control law can be realized using a decentralized rational feedback law of the form k(x) = a(x) + b(x)f(x)/g(x) that also respects the graph structure and control constraints (positivity and zero at equilibrium). This enables the possibility of using Linear Matrix Inequality (LMI) based tools to algorithmically construct decentralized density feedback controllers for stabilization of a robotic swarm to a target task distribution with no task-switching at equilibrium, as we demonstrate with several numerical examples.

Ganesh P Kumar, Spring Berman

In this work, we analyze \textit{stochastic coverage schemes} (SCS) for robotic swarms in which the robots randomly attach to a one-dimensional boundary of interest using local communication and sensing, without relying on global position information or a map of the environment. Robotic swarms may be required to perform boundary coverage in a variety of applications, including environmental monitoring, collective transport, disaster response, and nanomedicine. We present a novel analytical approach to computing and designing the statistical properties of the communication and sensing networks that are formed by random robot configurations on a boundary. We are particularly interested in the event that a robot configuration forms a connected communication network or maintains continuous sensor coverage of the boundary. Using tools from order statistics, random geometric graphs, and computational geometry, we derive formulas for properties of the random graphs generated by robots that are independently and identically distributed along a boundary. We also develop order-of-magnitude estimates of these properties based on Poisson approximations and threshold functions. For cases where the SCS generates a uniform distribution of robots along the boundary, we apply our analytical results to develop a procedure for computing the robot population size, diameter, sensing range, or communication range that yields a random communication network or sensor network with desired properties.

Ganesh P Kumar, Spring Berman

We do a Probabilistic Analysis of the Network generated by robots involved in Stochastic Boundary Coverage

Ragesh K Ramachandran, Spring Berman

This paper studies the problem of reconstructing a two-dimensional scalar field using a swarm of networked robots with local communication capabilities. We consider the communication network of the robots to form either a chain or a grid topology. We formulate the reconstruction problem as an optimization problem that is constrained by first-order linear dynamics on a large, interconnected system. To solve this problem, we employ an optimization-based scheme that uses a gradient-based method with an analytical computation of the gradient. In addition, we derive bounds on the trace of observability Gramian of the system, which helps us to quantify and compare the estimation capability of chain and grid networks. A comparison based on a performance measure related to the H2 norm of the system is also used to study robustness of the network topologies. Our resultsare validated using both simulated scalar fields and actual ocean salinity data.