Talk Title: Teams of cooperating aerial robots in the wild
Abstract: Agile and tightly cooperating Unmanned Aerial Vehicles (UAVs) in demanding real-world environments with high density of obstacles (such as forest) will be discussed in this talk. Deployment of teams of flying robots without external localization such as GNSS and motion capture systems bring numerous challenges especially if the UAV perception must be done in high speeds and close to the terrain. I will present some insights into the research of fully autonomous aerial teams relying on onboard artificial intelligence. I will discuss the important research question of whether the UAV groups can adapt better to localization failure than a single robot and how cooperative aerial vehicles can achieve high agility in high obstacle density areas. In addition to the fundamental swarming research, I will be talking about real applications of multi-robot systems such as indoor documentation of large historical objects (cathedrals) by formations of cooperating UAVs, a cooperative inspection of underground mines inspired by the DARPA SubT competition, localization and interception of unauthorized drones, aerial firefighting, radiation sources localization, power line inspection, and marine teams of cooperating heterogeneous robots.
Talk Title: From discrete to continuous, tens to hundreds, and navigation to coordinated manipulation
Abstract: While recent advances have made multi-robot systems (MRS) increasingly feasible, there remains a significant gap between theoretical research and practical implementation. Much of the existing multi-robot research has focused on relatively simple tasks like navigation, often overlooking or simplifying kinodynamic constraints, and emphasizing scalability for hundreds of robots in discretized environments. However, to bridge this gap and advance MRS towards real-world applications, it is crucial to address more complex challenges.
Our research team is currently working on pushing the boundaries of MRS capabilities in each of these directions by tackling complex tasks such as manipulation, incorporating realistic kinodynamic constraints, scaling systems to accommodate thousands of robots, and operating in continuous spatio-temporal domains. These efforts aim to move MRS beyond simplified laboratory conditions and towards the complex, unstructured environments they will encounter in practical applications, thereby addressing some of the key challenges hindering broader MRS implementation.
Talk Title: Improving Interactions Among Semi-Cooperative Robots
Abstract: Robots will transform our everyday lives, from home service and personal mobility to large-scale warehouse management and wildlife monitoring. Across these applications, robots need to interact with humans and other robots in complex, dynamic environments. Understanding how robots interact allows us to design safer and more robust systems. This talk presents an overview on how we can integrate underlying cooperation and interaction models into the design of the robot teams. We use tools from behavioral decision theory to design interaction models, combined with game theory and control theory to develop distributed control strategies with provable performance guarantees. This talk focuses on teams of robots interacting with cluttered environments, with applications in autonomous driving, resource delivery, and wildlife monitoring.
Talk Title: Robust and adaptive solutions for multi-robot coordination
Abstract: One of the main challenges in deploying multi-robot solutions in the real world is that they are typically designed to face fixed and often simplified constraints and system models, whereas real-world applications present ever-changing conditions and constraints that evolve over time. Malfunctioning or failing sensors and robots, as well as unpredictable energy consumption, remain likely problems and can severely impact a solution's ability to perform its assigned task. Efficient solutions for these systems need to be highly adaptive, allowing for system reconfiguration and possibly limiting the need for reliable communication with the rest of the team to successfully navigate these challenging conditions and cooperatively accomplish complex missions. In this talk, I will present some recent path-planning solutions developed in our group for various applications ranging from source localization to coverage and inspection missions. These examples illustrate how we integrate these challenges to develop more reliable and agile approaches.