Multi-robot coordination is crucial for autonomous systems, yet real-world deployments often encounter various failures. These include both temporary and permanent disruptions in sensing and communication, which can significantly degrade system robustness and performance if not explicitly modeled. Despite its practical importance, failure-aware coordination remains underexplored in the literature. To bridge the gap between idealized conditions and the complexities of real-world environments, we propose a unified failure-aware coordination framework designed to enable resilient and adaptive multi-robot target tracking under both temporary and permanent failure conditions. Our approach systematically distinguishes between two classes of failures: (1) probabilistic and temporary disruptions, where robots recover from intermittent sensing or communication losses by dynamically adapting paths and avoiding inferred danger zones, and (2) permanent failures, where robots lose sensing or communication capabilities irreversibly, requiring sustained, decentralized behavioral adaptation. To handle these scenarios, the robot team is partitioned into subgroups. Robots that remain connected form a communication group and collaboratively plan using partially centralized nonlinear optimization. Robots experiencing permanent disconnection or failure continue to operate independently through decentralized or individual optimization, allowing them to contribute to the task within their local context. We extensively evaluate our method across a range of benchmark variations and conduct a comprehensive assessment under diverse real-world failure scenarios. Results show that our framework consistently achieves robust performance in realistic environments with unknown danger zones, offering a practical and generalizable solution for the multi-robot systems community.

Yudong Yang, Jimin Zhuang, Guangzhi Sun, Changli Tang, Yixuan Li, Peihan Li, Yifan Jiang, Wei Li, Zejun Ma, Chao Zhang. Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing. 2025.

Multi-robot collaboration for target tracking in adversarial environments poses significant challenges, including system failures, dynamic priority shifts, and other unpredictable factors. These challenges become even more pronounced when the environment is unknown. In this paper, we propose a resilient coordination framework for multi-robot, multi-target tracking in environments with unknown sensing and communication danger zones. We consider scenarios where failures caused by these danger zones are probabilistic and temporary, allowing robots to escape from danger zones to minimize the risk of future failures. We formulate this problem as a nonlinear optimization with soft chance constraints, enabling real-time adjustments to robot behaviors based on varying types of dangers and failures. This approach dynamically balances target tracking performance and resilience, adapting to evolving sensing and communication conditions in real-time. To validate the effectiveness of the proposed method, we assess its performance across various tracking scenarios, benchmark it against methods without resilient adaptation and collaboration, and conduct several real-world experiments.

Recently a line of research has delved into the use of graph neural networks (GNNs) for decentralized control in swarm robotics. However, it has been observed that relying solely on the states of immediate neighbors is insufficient to imitate a centralized control policy. To address this limitation, prior studies proposed incorporating L-hop delayed states into the computation. While this approach shows promise, it can lead to a lack of consensus among distant flock members and the formation of small clusters, consequently failing cohesive flocking behaviors. Instead, our approach leverages spatiotemporal GNN, named STGNN that encompasses both spatial and temporal expansions. The spatial expansion collects delayed states from distant neighbors, while the temporal expansion incorporates previous states from immediate neighbors. The broader information gathered from both expansions results in more effective and accurate predictions. We develop an expert algorithm for controlling a swarm of robots and employ imitation learning to train our decentralized STGNN model based on the expert algorithm. We simulate the proposed STGNN approach in various settings, demonstrating its decentralized capacity to emulate the global expert algorithm. Further, we implemented our approach to achieve cohesive flocking, leader following, and obstacle avoidance by a group of Crazyflie drones. The performance of STGNN underscores its potential as an effective and reliable approach for achieving cohesive flocking, leader following, and obstacle avoidance tasks.

Recent research has explored the use of graph neural networks (GNNs) for decentralized control in swarm robotics. However, it has been observed that relying solely on local states is insufficient to imitate a centralized control policy. To address this limitation, previous studies proposed incorporating K-hop delayed states into the computation. While this approach shows promise, it can lead to a lack of consensus among distant flock members and the formation of small localized groups, ultimately resulting in task failure. Our approach is to include the delayed states to build a spatiotemporal GNN model (ST-GNN) by two levels of expansion: spatial expansion and temporal expansion. The spatial expansion utilizes K-hop delayed states to broaden the network while temporal expansion, can effectively predict the trend of swarm behavior, making it more robust against local noise. To validate the effectiveness of our approach, we conducted simulations in two distinct scenarios: free flocking and flocking with a leader. In both scenarios, the simulation results demonstrated that our decentralized ST-GNN approach successfully overcomes the limitations of local controllers. We performed a comprehensive analysis on the effectiveness of spatial expansions and temporal expansions independently. The results clearly demonstrate that both significantly improve overall performance. Furthermore, when combined, they achieve the best performance compared to global solution and delayed states solutions. The performance of ST-GNN underscores its potential as an effective and reliable approach for achieving cohesive flocking behavior while ensuring safety and maintaining desired swarm characteristics.

Modular self-assembling systems typically assume that modules are present to assemble. But in sparsely observed ocean environments modules of an aquatic modular robotic system may be separated by distances they do not have the energy to cross, and the information needed for optimal path planning is often unavailable. In this work we present a flow-based rendezvous and docking controller that allows aquatic robots in gyre-like environments to rendezvous with and dock to a target by leveraging environmental forces. This approach does not require complete knowledge of the flow, but suffices with imperfect knowledge of the flow's center and shape. We validate the performance of this control approach in both simulations and experiments relative to naive rendezvous and docking strategies and show that energy efficiency improves as the scale of the gyre increases.

We study the problem of assigning robots with actions to track targets. The objective is to optimize the robot team's tracking quality which can be defined as the reduction in the uncertainty of the targets' states. Specifically, we consider two assignment problems given the different sensing capabilities of the robots. In the first assignment problem, a single robot is sufficient to track a target. To this end, we present a greedy algorithm (Algorithm 1) that assigns a robot with its action to each target. We prove that the greedy algorithm has a 1/2-approximation bound and runs in polynomial time. Then, we study the second assignment problem where two robots are necessary to track a target. We design another greedy algorithm (Algorithm 2) that assigns a pair of robots with their actions to each target. We prove that the greedy algorithm achieves a 1/3-approximation bound and has a polynomial running time. Moreover, we illustrate the performance of the two greedy algorithms in the ROS-Gazebo environment where the tracking patterns of one robot following one target using Algorithm 1 and two robots following one target using Algorithm 2 are clearly observed. Further, we conduct extensive comparisons to demonstrate that the two greedy algorithms perform close to their optimal counterparts and much better than their respective (1/2 and 1/3) approximation bounds.

We present a flow-based control strategy that enables resource-constrained marine robots to patrol gyre-like flow environments on an orbital trajectory with a periodicity in a given range. The controller does not require a detailed model of the flow field and relies only on the robot's location relative to the center of the gyre. Instead of precisely tracking a pre-defined trajectory, the robots are tasked to stay in between two bounding trajectories with known periodicity. Furthermore, the proposed strategy leverages the surrounding flow field to minimize control effort. We prove that the proposed strategy enables robots to cycle in the flow satisfying the desired periodicity requirements. Our method is tested and validated both in simulation and in experiments using a low-cost, underactuated, surface swimming robot, i.e. the Modboat.

As the most serious global infectious disease in the past 100 years, it has caused severe loss of life and property to countries and their people worldwide in the past year. As the most powerful tool in the fight against the epidemic, how to quickly promote the COVID-19 vaccine administration plays a vital role in gradually establishing an immune barrier in the population as soon as possible and blocking the COVID-19 epidemic. In this paper, we provide a machine learning-based policy recommendation method on the vaccination campaign of COVID-19 by minimizing three different cost factors: the duration of the pandemic, the budget of the COVID-19 battle as well as the death toll. To generate a more efficient vaccination policy, we construct an Age-stratified Susceptible-Infected-Recovered (ASSIR) model. We validate our method based on the real-world dataset of India by comparing our simulated results with the government's vaccination plan from machine learning prediction. Our approach shows a 13% decrease in disease control time and government budget. At the same time, we find out that vaccination based on each province's population leads to a 12.4% decrease in the death toll than on infection cases. The model developed in this study has practical implications for COVID-19 vaccination campaigns and the infection control of other infectious diseases.