Stephanie Gil

Wild cetacean birth observations are extremely rare, with observations having been recorded in less than 10% of cetacean species. Here, we describe a detailed accounting of a sperm whale (Physeter macrocephalus) birth off the coast of Dominica within a well-documented social unit and consisted of sperm whales collaboratively lifting the newborn out of the water. We recorded data via multiple concurrent methods: underwater audio, aerial drone video, shipboard photography in addition to behavioral observations spanning before, during and after the whale birth. All 11 members from sperm whale "Unit A" were present and participated in the birth, which lasted 34 min from the time the flukes emerged until the completion of delivery. The sperm whale unit made extensive vocalizations, with statistically significant shifts in coda vocal style corresponding to key events, such as the beginning of the birth and interactions with short-finned pilot whales (Globicephala macrorhynchus) shortly after the birth event. An evolutionary analysis of wild cetacean births suggests that newborns being lifted out of the water dates to before the most recent common ancestor of toothed and baleen whales, > 36 million years ago, and that cooperative lifting of the newborn is noted, thus far, only in members of Odontoceti (toothed whales). This study provides the most in-depth observations of a wild cetacean birth.

We introduce a system for real-time sperm whale rendezvous at sea using an autonomous uncrewed aerial vehicle. Our system employs model-based reinforcement learning that combines in situ sensor data with an empirical whale dive model to guide navigation decisions. Key challenges include (i) real-time acoustic tracking in the presence of multiple whales, (ii) distributed communication and decision-making for robot deployments, and (iii) on-board signal processing and long-range detection from fish-trackers. We evaluate our system by conducting rendezvous with sperm whales at sea in Dominica, performing hardware experiments on land, and running simulations using whale trajectories interpolated from marine biologists' surface observations.

Optimizing neural networks for quantized objectives is fundamentally challenging because the quantizer is piece-wise constant, yielding zero gradients everywhere except at quantization thresholds where the derivative is undefined. Most existing methods deal with this issue by relaxing gradient computations with techniques like Straight Through Estimators (STE) and do not provide any guarantees of convergence. In this work, taking inspiration from Nesterov smoothing, we approximate the quantized loss surface with a continuous loss surface. In particular, we introduce LOTION, \textbf{L}ow-precision \textbf{O}ptimization via s\textbf{T}ochastic-no\textbf{I}se sm\textbf{O}othi\textbf{N}g, a principled smoothing framework that replaces the raw quantized loss with its expectation under unbiased randomized-rounding noise. In this framework, standard optimizers are guaranteed to converge to a local minimum of the loss surface. Moreover, when using noise derived from stochastic rounding, we show that the global minima of the original quantized loss are preserved. We empirically demonstrate that this method outperforms standard QAT on synthetic testbeds and on 150M- and 300M- parameter language models.

Wildlife field operations demand efficient parallel deployment methods to identify and interact with specific individuals, enabling simultaneous collective behavioral analysis, and health and safety interventions. Previous robotics solutions approach the problem from the herd perspective, or are manually operated and limited in scale. We propose a decentralized vision-based multi-quadrotor system for wildlife monitoring that is scalable, low-bandwidth, and sensor-minimal (single onboard RGB camera). Our approach enables robust identification and tracking of large species in their natural habitat. We develop novel vision-based coordination and tracking algorithms designed for dynamic, unstructured environments without reliance on centralized communication or control. We validate our system through real-world experiments, demonstrating reliable deployment in diverse field conditions.

Training large language models is an expensive, compute-bound process that must be repeated as models scale, algorithms improve, and new data is collected. To address this, next-generation hardware accelerators increasingly support lower-precision arithmetic formats, such as the Microscaling (MX) formats introduced in NVIDIA's Blackwell architecture. These formats use a shared scale within blocks of parameters to extend representable range and perform forward/backward GEMM operations in reduced precision for efficiency gains. In this work, we investigate the challenges and viability of block-scaled precision formats during model training. Across nearly one thousand language models trained from scratch -- spanning compute budgets from $2 \times 10^{17}$ to $4.8 \times 10^{19}$ FLOPs and sweeping over a broad range of weight-activation precision combinations -- we consistently observe that training in MX formats exhibits sharp, stochastic instabilities in the loss, particularly at larger compute scales. To explain this phenomenon, we conduct controlled experiments and ablations on a smaller proxy model that exhibits similar behavior as the language model, sweeping across architectural settings, hyperparameters, and precision formats. These experiments motivate a simple model in which multiplicative gradient bias introduced by the quantization of layer-norm affine parameters and a small fraction of activations can trigger runaway divergence. Through \emph{in situ} intervention experiments on our proxy model, we demonstrate that instabilities can be averted or delayed by modifying precision schemes mid-training. Guided by these findings, we evaluate stabilization strategies in the LLM setting and show that certain hybrid configurations recover performance competitive with full-precision training. We release our code at https://github.com/Hither1/systems-scaling.

We investigate the problem of learning the trustworthiness of agents in a directed graph, where agents receive stochastic trust information about their in-neighbors. We consider a setting where an unknown subset of agents may be malicious and disseminate misinformation about the trustworthiness of other agents. We present a learning protocol where agents determine their trusted neighborhoods based on the stochastic trust information they receive, and leverage the opinions of their trusted neighbors to assess the trustworthiness of other agents. We show that, under mild assumptions about the communication network, agents can learn the trustworthiness of other agents almost surely. Additionally, we establish an expected geometric convergence rate of the algorithm based on the properties of the stochastic trust values and the communication graph. Finally, we present numerical studies demonstrating that our convergence results hold in practice across various network topologies and with different numbers of malicious agents in the network.

Wireless communication-based multi-robot systems open the door to cyberattacks that can disrupt safety and performance of collaborative robots. The physical channel supporting inter-robot communication offers an attractive opportunity to decouple the detection of malicious robots from task-relevant data exchange between legitimate robots. Yet, trustworthiness indications coming from physical channels are uncertain and must be handled with this in mind. In this paper, we propose a resilient protocol for multi-robot operation wherein a parameter λt accounts for how confident a robot is about the legitimacy of nearby robots that the physical channel indicates. Analytical results prove that our protocol achieves resilient coordination with arbitrarily many malicious robots under mild assumptions. Tuning λt allows a designer to trade between near-optimal inter-robot coordination and quick task execution; see Fig. 1. This is a fundamental performance tradeoff and must be carefully evaluated based on the task at hand. The effectiveness of our approach is numerically verified with experiments involving platoons of autonomous cars where some vehicles are maliciously spoofed.

Vision-language models encode images and text in a joint space, minimizing the distance between corresponding image and text pairs. How are language and images organized in this joint space, and how do the models encode meaning and modality? To investigate this, we train and release sparse autoencoders (SAEs) on the embedding spaces of four vision-language models (CLIP, SigLIP, SigLIP2, and AIMv2). SAEs approximate model embeddings as sparse linear combinations of learned directions, or "concepts". We find that, compared to other methods of linear feature learning, SAEs are better at reconstructing the real embeddings, while also able to retain the most sparsity. Retraining SAEs with different seeds or different data diet leads to two findings: the rare, specific concepts captured by the SAEs are liable to change drastically, but we also show that commonly-activating concepts are remarkably stable across runs. Interestingly, while most concepts activate primarily for one modality, we find they are not merely encoding modality per se. Many are almost orthogonal to the subspace that defines modality, and the concept directions do not function as good modality classifiers, suggesting that they encode cross-modal semantics. To quantify this bridging behavior, we introduce the Bridge Score, a metric that identifies concept pairs which are both co-activated across aligned image-text inputs and geometrically aligned in the shared space. This reveals that even single-modality concepts can collaborate to support cross-modal integration. We release interactive demos of the SAEs for all models, allowing researchers to explore the organization of the concept spaces. Overall, our findings uncover a sparse linear structure within VLM embedding spaces that is shaped by modality, yet stitched together through latent bridges, offering new insight into how multimodal meaning is constructed.

In this work, we study the consensus problem in which legitimate agents send their values over an undirected communication network in the presence of an unknown subset of malicious or faulty agents. In contrast to former works, we generalize and characterize the properties of consensus dynamics with dependent sequences of malicious transmissions with dynamic (time-varying) rates, based on not necessarily independent trust observations. We consider a detection algorithm utilizing stochastic trust observations available to legitimate agents. Under these conditions, legitimate agents almost surely classify their neighbors and form their trusted neighborhoods correctly with decaying misclassification probabilities. We further prove that the consensus process converges almost surely despite the existence of malicious agents. For a given value of failure probability, we characterize the deviation from the nominal consensus value ideally occurring when there are no malicious agents in the system. We also examine the convergence rate of the process in finite time. Numerical simulations show the convergence among agents and indicate the deviation under different attack scenarios.

This work focuses on the problem of distributed optimization in multiagent cyberphysical systems, where a legitimate agent's iterates are influenced both by the values it receives from potentially malicious neighboring agents and by its own self-serving target function. We develop a new algorithmic and analytical framework to achieve resilience for the class of problems where stochastic values of trust between agents exist and can be exploited. In this case, we show that convergence to the true global optimal point can be recovered, both in mean and almost surely, even in the presence of malicious agents. Furthermore, we provide expected convergence rate guarantees in the form of upper bounds on the expected squared distance to the optimal value. Finally, numerical results are presented that validate our analytical convergence guarantees even when the malicious agents compose the majority of agents in the network and where existing methods fail to converge to the optimal nominal points.

The Friedkin-Johnsen (FJ) model describes how agents adjust their opinions through repeated interactions while accounting for the influence of agents who are partially stubborn. In this work, we demonstrate that the FJ model is stepwise equivalent to solving the average consensus problem via distributed gradient descent. This perspective provides a unifying framework that bridges opinion dynamics and optimization, enabling the application of well-established results from the optimization literature. To illustrate this, we examine the recently proposed FJ model with diminishing stubbornness and extend prior results that were concerned with fixed communication graphs to time-varying and jointly connected communication graphs. We derive convergence guarantees and analyze convergence rates under these relaxed assumptions. Finally, we present numerical experiments on random graphs to showcase the impact of diminishing stubbornness dynamics on convergence in both static and time-varying settings.

We introduce a Wireless Signal based Efficient multi-Robot eXploration (WiSER-X) algorithm applicable to a decentralized team of robots exploring an unknown environment with communication bandwidth constraints. WiSER-X relies only on local inter-robot relative position estimates, that can be obtained by exchanging signal pings from onboard sensors such as WiFi, Ultra-Wide Band, amongst others, to inform the exploration decisions of individual robots to minimize redundant coverage overlaps. Furthermore, WiSER-X also enables asynchronous termination without requiring a shared map between the robots. It also adapts to heterogeneous robot behaviors and even complete failures in unknown environment while ensuring complete coverage. Simulations show that WiSER-X leads to 58% lower overlap than a zero-information-sharing baseline algorithm-1 and only 23% more overlap than a full-information-sharing algorithm baseline algorithm-2. Hardware experiments further validate the feasibility of WiSER-X using full onboard sensing.

In this work, we consider the consensus problem in which legitimate agents share their values over an undirected communication network in the presence of malicious or faulty agents. Different from the previous works, we characterize the conditions that generalize to several scenarios such as intermittent faulty or malicious transmissions, based on trust observations. As the standard trust aggregation approach based on a constant threshold fails to distinguish intermittent malicious/faulty activity, we propose a new detection algorithm utilizing time-varying thresholds and the random trust values available to legitimate agents. Under these conditions, legitimate agents almost surely determine their trusted neighborhood correctly with geometrically decaying misclassification probabilities. We further prove that the consensus process converges almost surely even in the presence of malicious agents. We also derive the probabilistic bounds on the deviation from the nominal consensus value that would have been achieved with no malicious agents in the system. Numerical results verify the convergence among agents and exemplify the deviation under different scenarios.

Rendezvous with sperm whales for biological observations is made challenging by their prolonged dive patterns. Here, we propose an algorithmic framework that codevelops multiagent reinforcement learning-based routing (autonomy module) and synthetic aperture radar-based very high frequency (VHF) signal-based bearing estimation (sensing module) for maximizing rendezvous opportunities of autonomous robots with sperm whales. The sensing module is compatible with low-energy VHF tags commonly used for tracking wildlife. The autonomy module leverages in situ noisy bearing measurements of whale vocalizations, VHF tags, and whale dive behaviors to enable time-critical rendezvous of a robot team with multiple whales in simulation. We conducted experiments at sea in the native habitat of sperm whales using an "engineered whale"-a speedboat equipped with a VHF-emitting tag, emulating five distinct whale tracks, with different whale motions. The sensing module shows a median bearing error of 10.55° to the tag. Using bearing measurements to the engineered whale from an acoustic sensor and our sensing module, our autonomy module gives an aggregate rendezvous success rate of 81.31% for a 500-meter rendezvous distance using three robots in postprocessing. A second class of fielded experiments that used acoustic-only bearing measurements to three untagged sperm whales showed an aggregate rendezvous success rate of 68.68% for a 1000-meter rendezvous distance using two robots in postprocessing. We further validated these algorithms with several ablation studies using a sperm whale visual encounter dataset collected by marine biologists.

Development and testing of multi-robot systems employing wireless signal-based sensing requires access to suitable hardware, such as channel monitoring WiFi transceivers, which can pose significant limitations. The WiFi Sensor for Robotics (WSR) toolbox, introduced by Jadhav et al. in 2022, provides a novel solution by using WiFi Channel State Information (CSI) to compute relative bearing between robots. The toolbox leverages the amplitude and phase of WiFi signals and creates virtual antenna arrays by exploiting the motion of mobile robots, eliminating the need for physical antenna arrays. However, the WSR toolbox's reliance on an obsoleting WiFi transceiver hardware has limited its operability and accessibility, hindering broader application and development of relevant tools. We present an open-source simulation framework that replicates the WSR toolbox's capabilities using Gazebo and Matlab. By simulating WiFi-CSI data collection, our framework emulates the behavior of mobile robots equipped with the WSR toolbox, enabling precise bearing estimation without physical hardware. We validate the framework through experiments with both simulated and real Turtlebot3 robots, showing a close match between the obtained CSI data and the resulting bearing estimates. This work provides a virtual environment for developing and testing WiFi-CSI-based multi-robot localization without relying on physical hardware. All code and experimental setup information are publicly available at https://github.com/BrendanxP/CSI-Simulation-Framework

We introduce the concept of community consensus in the presence of malicious agents using a well-known median-based consensus algorithm. We consider networks that have multiple well-connected regions that we term communities, characterized by specific robustness and minimum degree properties. Prior work derives conditions on properties that are necessary and sufficient for achieving global consensus in a network. This, however, requires the minimum degree of the network graph to be proportional to the number of malicious agents in the network, which is not very practical in large networks. In this work, we present a natural generalization of this previous result. We characterize cases where, although global consensus is not reached, some subsets of agents <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$V_{i}$</tex> will still converge to the same values <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathcal{M}_{i}$</tex> among themselves. To reach this new type of consensus, we define more relaxed requirements in terms of the number of malicious agents in each community, and the number <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$k$</tex> of edges connecting an agent in a community to agents external to the community.

In this work, we introduce the Resilient Projected Push-Pull (RP3) algorithm designed for distributed optimization in multi-agent cyber-physical systems with directed communication graphs and the presence of malicious agents. Our algorithm leverages stochastic inter-agent trust values and gradient tracking to achieve geometric convergence rates in expectation even in adversarial environments. We introduce growing constraint sets to limit the impact of the malicious agents without compromising the geometric convergence rate of the algorithm. We prove that RP3 converges to the nominal optimal solution almost surely and in the $r$-th mean for any $r\geq 1$, provided the step sizes are sufficiently small and the constraint sets are appropriately chosen. We validate our approach with numerical studies on average consensus and multi-robot target tracking problems, demonstrating that RP3 effectively mitigates the impact of malicious agents and achieves the desired geometric convergence.

In this paper, we focus on the autonomous multiagent taxi routing problem for a large urban environment where the location and number of future ride requests are unknown a-priori, but can be estimated by an empirical distribution. Recent theory has shown that a rollout algorithm with a stable base policy produces a near-optimal stable policy. In the routing setting, a policy is stable if its execution keeps the number of outstanding requests uniformly bounded over time. Although, rollout-based approaches are well-suited for learning cooperative multiagent policies with considerations for future demand, applying such methods to a large urban environment can be computationally expensive due to the large number of taxis required for stability. In this paper, we aim to address the computational bottleneck of multiagent rollout by proposing an approximate multiagent rollout-based two phase algorithm that reduces computational costs, while still achieving a stable near-optimal policy. Our approach partitions the graph into sectors based on the predicted demand and the maximum number of taxis that can run sequentially given the user’s computational resources. The algorithm then applies instantaneous assignment (IA) for re-balancing taxis across sectors and a sector-wide multiagent rollout algorithm that is executed in parallel for each sector. We provide two main theoretical results: 1) characterize the number of taxis m that is sufficient for IA to be stable; 2) derive a necessary condition on m to maintain stability for IA as time goes to infinity. Our numerical results show that our approach achieves stability for an m that satisfies the theoretical conditions. We also empirically demonstrate that our proposed two phase algorithm has equivalent performance to the one-at-a-time rollout over the entire map, but with significantly lower runtimes.

In this work, we consider the consensus problem in which legitimate agents share their values over an undirected communication network in the presence of malicious or faulty agents. Different from the previous works, we characterize the conditions that generalize to several scenarios such as intermittent faulty or malicious transmissions, based on trust observations. As the standard trust aggregation approach based on a constant threshold fails to distinguish intermittent malicious/faulty activity, we propose a new detection algorithm utilizing time-varying thresholds and the random trust values available to legitimate agents. Under these conditions, legitimate agents almost surely determine their trusted neighborhood correctly with geometrically decaying misclassification probabilities. We further prove that the consensus process converges almost surely even in the presence of malicious agents. We also derive the probabilistic bounds on the deviation from the nominal consensus value that would have been achieved with no malicious agents in the system. Numerical results verify the convergence among agents and exemplify the deviation under different scenarios.

This paper presents MULAN-WC, a novel multi-robot 3D reconstruction framework that leverages wireless signal-based coordination between robots and Neural Radiance Fields (NeRF). Our approach addresses key challenges in multi-robot 3D reconstruction, including inter-robot pose estimation, localization uncertainty quantification, and active best-next-view selection. We introduce a method for using wireless Angle-of-Arrival (AoA) and ranging measurements to estimate relative poses between robots, as well as quantifying and incorporating the uncertainty embedded in the wireless localization of these pose estimates into the NeRF training loss to mitigate the impact of inaccurate camera poses. Furthermore, we propose an active view selection approach that accounts for robot pose uncertainty when determining the next-best views to improve the 3D reconstruction, enabling faster convergence through intelligent view selection. Extensive experiments on both synthetic and real-world datasets demonstrate the effectiveness of our framework in theory and in practice. Leveraging wireless coordination and localization uncertainty-aware training, MULAN-WC can achieve high-quality 3d reconstruction which is close to applying the ground truth camera poses. Furthermore, the quantification of the information gain from a novel view enables consistent rendering quality improvement with incrementally captured images by commending the robot the novel view position. Our hardware experiments showcase the practicality of deploying MULAN-WC to real robotic systems.

In this article, we develop a resilient binary hypothesis testing framework for decision making in adversarial multirobot crowdsensing tasks. This framework exploits stochastic trust observations between robots to arrive at tractable, resilient decision making at a centralized fusion center (FC) even when, first, there exist malicious robots in the network and their number may be larger than the number of legitimate robots, and second, the FC uses one-shot noisy measurements from all robots. We derive two algorithms to achieve this. The first is the two-stage approach (2SA) that estimates the legitimacy of robots based on received trust observations, and provably minimizes the probability of detection error in the worst-case malicious attack. For the 2SA, we assume that the proportion of malicious robots is known but arbitrary. For the case of an unknown proportion of malicious robots, we develop the adversarial generalized likelihood ratio test (A-GLRT) that uses both the reported robot measurements and trust observations to simultaneously estimate the trustworthiness of robots, their reporting strategy, and the correct hypothesis. We exploit particular structures in the problem to show that this approach remains computationally tractable even with unknown problem parameters. We deploy both algorithms in a hardware experiment where a group of robots conducts crowdsensing of traffic conditions subject to a Sybil attack on a mock-up road network. We extract the trust observations for each robot from communication signals, which provide statistical information on the uniqueness of the sender. We show that even when the malicious robots are in the majority, the FC can reduce the probability of detection error to 30.5% and 29% for the 2SA and the A-GLRT algorithms, respectively.

This letter studies the Friedkin-Johnsen (FJ) model with diminishing competition, or stubbornness. The original FJ model assumes that each agent assigns a constant competition weight to its initial opinion. In contrast, we investigate the effect of diminishing competition on the convergence point and speed of the FJ dynamics. We prove that, if the competition is uniform across agents and vanishes asymptotically, the convergence point coincides with the nominal consensus reached with no competition. However, the diminishing competition slows down convergence according to its own rate of decay. We study this phenomenon analytically and provide upper and lower bounds on the convergence rate. Further, if competition is not uniform across agents, we show that the convergence point may not coincide with the nominal consensus point. Finally, we evaluate our analytical insights numerically.

In this article, we consider the computational and communication challenges of partially observable multiagent sequential decision-making problems. We present 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. In particular: 1) we consider multiagent rollout algorithms that dramatically reduce required computation while preserving the key policy improvement property of the standard rollout method. We improve our multiagent rollout policy by incorporating it in an offline approximate policy iteration scheme, and we apply an additional “online play” scheme enhancing offline approximation architectures; 2) we consider the imperfect communication case and provide various extensions to our rollout methods to deal with this case; and 3) we demonstrate the performance of our methods in extensive simulations by applying our method to a challenging partially observable multiagent sequential repair problem (state space size <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$10^{37}$</tex-math></inline-formula> and control space size <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$10^{7}$</tex-math></inline-formula> ). Our extensive simulations demonstrate that our methods produce better policies for large and complex multiagent problems in comparison with existing methods, including POMCP, MADDPG, and work well where other methods fail to scale up.

In this article, we develop an algorithm for resilient path planning, where a team of robots must navigate in a resilient formation such that they achieve <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$F$</tex-math></inline-formula> -resilience, meaning they can coordinate in the presence of up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$F$</tex-math></inline-formula> adversaries. Resilient formations are those having high connectivity often achieved by driving robots close together. Unfortunately, the objective of maintaining resilience can often times conflict with achieving collision and obstacle avoidance. We seek to provide safe navigation while maintaining resilience by employing a local controller that uses control barrier functions (CBFs). CBF-based formulations are amenable to satisfying multiple objectives, but can be prone to deadlock if any of the objectives conflict with each other. Furthermore, it is difficult to know a priori where this may occur in a given environment. To this end, we 1) characterize when the environment will force a tradeoff between safe navigation and resilience, and 2) develop an algorithm that derives a new representation of the environment in which areas where resilience cannot be provably guaranteed are blocked off. This algorithm can be used to plan a path through an environment that always provably admits a resilient formation. If the algorithm cannot find such a path, an alternative CBF is proposed where resilience can be treated as a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">soft constraint</i> . For this case, a nested form of the CBF is executed and a critical gain is derived that provably prioritizes navigation over resilience while resilience is not attainable. Finally, in addition to simulation results, we run hardware experiments with six GoPiGo differential-drive robots that achieve <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$F$</tex-math></inline-formula> -resilient consensus while navigating through a cluttered environment, to showcase the applicability of our methods in the presence of adversaries.

Multi-agent cyberphysical systems enable new capabilities in efficiency, resilience, and security. The unique characteristics of these systems prompt a reevaluation of their security concepts, including their vulnerabilities, and mechanisms to mitigate these vulnerabilities. This survey paper examines how advancement in wireless networking, coupled with the sensing and computing in cyberphysical systems, can foster novel security capabilities. This study delves into three main themes related to securing multi-agent cyberphysical systems. First, we discuss the threats that are particularly relevant to multi-agent cyberphysical systems given the potential lack of trust between agents. Second, we present prospects for sensing, contextual awareness, and authentication, enabling the inference and measurement of ``inter-agent trust" for these systems. Third, we elaborate on the application of quantifiable trust notions to enable ``resilient coordination," where ``resilient" signifies sustained functionality amid attacks on multiagent cyberphysical systems. We refer to the capability of cyberphysical systems to self-organize, and coordinate to achieve a task as autonomy. This survey unveils the cyberphysical character of future interconnected systems as a pivotal catalyst for realizing robust, trust-centered autonomy in tomorrow's world.

In this paper, we focus on the autonomous multiagent taxi routing problem for a large urban environment where the location and number of future ride requests are unknown a-priori, but can be estimated by an empirical distribution. Recent theory has shown that a rollout algorithm with a stable base policy produces a near-optimal stable policy. In the routing setting, a policy is stable if its execution keeps the number of outstanding requests uniformly bounded over time. Although, rollout-based approaches are well-suited for learning cooperative multiagent policies with considerations for future demand, applying such methods to a large urban environment can be computationally expensive due to the large number of taxis required for stability. In this paper, we aim to address the computational bottleneck of multiagent rollout by proposing an approximate multiagent rollout-based two phase algorithm that reduces computational costs, while still achieving a stable near-optimal policy. Our approach partitions the graph into sectors based on the predicted demand and the maximum number of taxis that can run sequentially given the user's computational resources. The algorithm then applies instantaneous assignment (IA) for re-balancing taxis across sectors and a sector-wide multiagent rollout algorithm that is executed in parallel for each sector. We provide two main theoretical results: 1) characterize the number of taxis $m$ that is sufficient for IA to be stable; 2) derive a necessary condition on $m$ to maintain stability for IA as time goes to infinity. Our numerical results show that our approach achieves stability for an $m$ that satisfies the theoretical conditions. We also empirically demonstrate that our proposed two phase algorithm has equivalent performance to the one-at-a-time rollout over the entire map, but with significantly lower runtimes.

We introduce the Projected Push-Pull algorithm that enables multiple agents to solve a distributed constrained optimization problem with private cost functions and global constraints, in a collaborative manner. Our algorithm employs projected gradient descent to deal with constraints and a lazy update rule to control the trade-off between the consensus and optimization steps in the protocol. We prove that our algorithm achieves geometric convergence over time-varying directed graphs while ensuring that the decision variable always stays within the constraint set. We derive explicit bounds for step sizes that guarantee geometric convergence based on the strong-convexity and smoothness of cost functions, and graph properties. Moreover, we provide additional theoretical results on the usefulness of lazy updates, revealing the challenges in the analysis of any gradient tracking method that uses projection operators in a distributed constrained optimization setting. We validate our theoretical results with numerical studies over different graph types, showing that our algorithm achieves geometric convergence empirically.

Large events such as conferences, concerts and sports games, often cause surges in demand for ride services that are not captured in average demand patterns, posing unique challenges for routing algorithms. We propose a learning framework for an autonomous fleet of taxis that leverages event data from the internet to predict demand surges and generate cooperative routing policies. We achieve this through a combination of two major components: (i) a demand prediction framework that uses textual event information in the form of events' descriptions and reviews to predict event-driven demand surges over street intersections, and (ii) a scalable multiagent reinforcement learning framework that leverages demand predictions and uses one-agent-at-a-time rollout combined with limited sampling certainty equivalence to learn intersection-level routing policies. For our experimental results we consider real NYC ride share data for the year 2022 and information for more than 2000 events across 300 unique venues in Manhattan. We test our approach with a fleet of 100 taxis on a map with 2235 street intersections. Our experimental results demonstrate that our method learns routing policies that reduce wait time overhead per serviced request by 25% to 75%, while picking up 1% to 4% more requests than other model-based RL frameworks and classical methods in operations research.

We derive a learning framework to generate routing/pickup policies for a fleet of autonomous vehicles tasked with servicing stochastically appearing requests on a city map. We focus on policies that 1) give rise to coordination amongst the vehicles, thereby reducing wait times for servicing requests, 2) are non-myopic, and consider a-priori potential future requests, 3) can adapt to changes in the underlying demand distribution. Specifically, we are interested in policies that are adaptive to fluctuations of actual demand conditions in urban environments, such as on-peak vs. off-peak hours. We achieve this through a combination of (i) an online play algorithm that improves the performance of an offline-trained policy, and (ii) an offline approximation scheme that allows for adapting to changes in the underlying demand model. In particular, we achieve adaptivity of our learned policy to different demand distributions by quantifying a region of validity using the q-valid radius of a Wasserstein Ambiguity Set. We propose a mechanism for switching the originally trained offline approximation when the current demand is outside the original validity region. In this case, we propose to use an offline architecture, trained on a historical demand model that is closer to the current demand in terms of Wasserstein distance. We learn routing and pickup policies over real taxicab requests in San Francisco with high variability between on-peak and off-peak hours, demonstrating the ability of our method to adapt to real fluctuation in demand distributions. Our numerical results demonstrate that our method outperforms alternative rollout-based reinforcement learning schemes, as well as other classical methods from operations research.

In this paper we propose a novel algorithm, Wi-Closure, to improve the computational efficiency and robustness of loop closure detection in multi-robot SLAM. Our approach decreases the computational overhead of classical approaches by pruning the search space of potential loop closures, prior to evaluation by a typical multi-robot SLAM pipeline. Wi-Closure achieves this by identifying candidates that are spatially close to each other measured via sensing over the wireless communication signal between robots, even when they are operating in non-line-of-sight or in remote areas of the environment from one another. We demonstrate the validity of our approach in simulation and in hardware experiments. Our results show that using Wi-closure greatly reduces computation time, by 54.1% in simulation and 76.8% in hardware experiments, compared with a multi-robot SLAM baseline. Importantly, this is achieved without sacrificing accuracy. Using Wi-closure reduces absolute trajectory estimation error by 98.0% in simulation and 89.2% in hardware experiments. This improvement is partly due to Wi-Closure's ability to avoid catastrophic optimization failure that typically occurs with classical approaches in challenging repetitive environments.

We develop a resilient binary hypothesis testing framework for decision making in adversarial multi-robot crowdsensing tasks. This framework exploits stochastic trust observations between robots to arrive at tractable, resilient decision making at a centralized Fusion Center (FC) even when i) there exist malicious robots in the network and their number may be larger than the number of legitimate robots, and ii) the FC uses one-shot noisy measurements from all robots. We derive two algorithms to achieve this. The first is the Two Stage Approach (2SA) that estimates the legitimacy of robots based on received trust observations, and provably minimizes the probability of detection error in the worst-case malicious attack. Here, the proportion of malicious robots is known but arbitrary. For the case of an unknown proportion of malicious robots, we develop the Adversarial Generalized Likelihood Ratio Test (A-GLRT) that uses both the reported robot measurements and trust observations to estimate the trustworthiness of robots, their reporting strategy, and the correct hypothesis simultaneously. We exploit special problem structure to show that this approach remains computationally tractable despite several unknown problem parameters. We deploy both algorithms in a hardware experiment where a group of robots conducts crowdsensing of traffic conditions on a mock-up road network similar in spirit to Google Maps, subject to a Sybil attack. We extract the trust observations for each robot from actual communication signals which provide statistical information on the uniqueness of the sender. We show that even when the malicious robots are in the majority, the FC can reduce the probability of detection error to 30.5% and 29% for the 2SA and the A-GLRT respectively.