Abstract: We present here the Hive Mind, a conceptual network designed to allow distributed multi-robot systems such as swarms, to individually connect and make network requests for data processing, data storage and computational offloading. Swarm robotics has been shown to offer several advantages over centralised systems but their emergent properties mean that they often lack efficiency and are challenging to monitor and control. The Hive Mind network is robot-led, so each agent in the swarm can connect individually, maintaining the distributed nature of the system but adding a new layer of cooperation. The Hive Mind is analogous to the world wide web for robots, it is a resource to share information and process data.

Abstract: We are motivated by quantile estimation of algae concentration in lakes. We find that multirobot teams improve performance in this task over single robots, and communication-enabled teams further over communication-deprived teams; however, real robots are resource-constrained, and communication networks cannot support arbitrary message loads, making naı̈ve, constant information-sharing but also complex modeling and decision-making infeasible. With this in mind, we propose online, locally computable metrics for determining the utility of transmitting a given message to the other team members and a decision-theoretic approach that chooses to transmit only the most useful messages, using a decentralized and independent framework for maintaining beliefs of other teammates. We validate our approach in simulation on a real-world aquatic dataset, and show that restricting communication via a utility estimation method based on the expected impact of a message on future teammate behavior results in a 44% decrease in network load while increasing quantile estimation error by only 2.16%.

Abstract: Communication delays can be catastrophic for multiagent systems. However, most existing state-of-the-art multiagent trajectory planners assume perfect communication and therefore lack a strategy to rectify this issue in real-world environments. To address this challenge, we propose Robust MADER (RMADER), a decentralized, asynchronous multiagent trajectory planner robust to communication delay. By always keeping a guaranteed collision-free trajectory and performing a delay check step, RMADER is able to guarantee safety even under communication delay. We perform an in-depth analysis of trajectory deconfliction among agents, extensive benchmark studies, and hardware flight experiments with multiple dynamic obstacles. We show that RMADER outperforms existing approaches by achieving a 100% success rate of collision-free trajectory generation, whereas the next best asynchronous decentralized method only achieves 83% success.

Abstract: The Robot Operating System (ROS2) is the most widely used software platform for building robotics applications. FogROS2 extends ROS2 to allow robots to access cloud computing on demand. However, ROS2 and FogROS2 assume that all robots are locally connected and that each robot has full access and control of the other robots. With applications like distributed multi-robot systems, remote robot control, and mobile robots, robotics increasingly involves the global Internet and complex trust management. Existing approaches for connecting disjoint ROS2 networks lack key features such as security, compatibility, efficiency, and ease of use. We introduce FogROS2-SGC, an extension of FogROS2 that can effectively connect robot systems across different physical locations, networks, and Data Distribution Services (DDS). With globally unique and location-independent identifiers, FogROS2-SGC securely and efficiently routes data between robotics components around the globe. FogROS2-SGC is agnostic to the ROS2 distribution and configuration, is compatible with non-ROS2 software, and seamlessly extends existing ROS2 applications without any code modification. Experiments suggest FogROS2-SGC is 19× faster than rosbridge (a ROS2 package

Abstract: In this paper, we aim at finding the conditions for input-state stability (ISS) and incremental input-state stability (ISS) of Gated Graph Neural Networks (GGNNs) that ensure the internal stability of a distributed control implemented with GGNNs. We show that this recurrent version of Graph Neural Networks (GNNs) can be expressed as a dynamical distributed system and, as a consequence, can be analysed using model-based techniques to assess its stability and robustness properties. Then, the stability criteria found can be exploited as constraints during the training process to enforce the internal stability of the neural network. The multi-robot motion control example shows that using these conditions increases the performance and robustness of the gated GNNs.

Abstract: In this work, we showcase a method for building underwater multi-robot SLAM datasets without requiring more than one robot operating in the field. The multi-robot SLAM problem is critically important, especially when considering underwater communications constraints. However, operating underwater vehicles is complex, expensive, and time-consuming. Therefore it is desirable to find methods of testing multi-robot SLAM systems without needing a real team of robots. This paper will discuss our process for splicing single-robot datasets into a synthetic multi-robot dataset. We show two real-world datasets representing different challenge problems and discuss a crucial contribution of our previous work on multi-robot SLAM under communications constraints.

Abstract: Effective communication is crucial for deploying robots in mission-specific tasks, but inadequate or unreliable communication can greatly reduce mission efficacy, for example in search and rescue missions where communication-denied conditions may occur. In such missions, robots are deployed to locate targets, such as human survivors, but they might get trapped at hazardous locations, such as in a trapping pit or by debris. Thus, the information the robot collected is lost owing to the lack of communication. In our prior work, we developed the notion of a path-based sensor. A path-based sensor detects whether or not an event has occurred along a particular path, but it does not provide the exact location of the event. Such path-based sensor observations are well-suited to communication-denied environments, and various studies have explored methods to improve information gathering in such settings. In some missions it is typical for target elements to be in close proximity to hazardous factors that hinder the information-gathering process. In this study, we examine a similar scenario and conduct experiments to determine if additional knowledge about the correlation between hazards and targets improves the efficiency of information gathering. To incorporate this knowledge, we utilize a Bayesian network representation of domain knowledge and develop an algorithm based on this representation. Our empirical investigation reveals that such additional information on correlation is beneficial only in environments with moderate hazard lethality, suggesting that while knowledge of correlation helps, further research and development is necessary for optimal outcomes.

Abstract: Multiple mobile robots must autonomously navigate and cooperatively explore complex environments in practical applications. Traditional methods face high communication and update costs of map merging. We propose CQLite, a distributed Q-learning-based approach with a coverage-weighted reward function and reduced communication overhead. CQLite's convergence and efficiency are analyzed theoretically and validated experimentally, outperforming RRT and DRL techniques with over 2x reduction in computation and communication.