2024 ECC workshop:
Advanced sensory-based estimation and control of autonomous vehicles: From theory to practice
Advanced sensory-based estimation and control of autonomous vehicles: From theory to practice
Contact: ztang2@kth.se, z.sun@tue.nl, and fidan@uwaterloo.ca
Recent decades have witnessed the rapid expansion of autonomous vehicle systems. Ground, aerial, marine surface, and underwater autonomous vehicles hold great promise as indispensable tools for delving into hazardous territories, augmenting human sensory and manipulation capabilities, and embarking on explorations of vast terrains that would otherwise remain inaccessible to human navigation. While academic efforts concerning the control of autonomous vehicles have witnessed significant expansion in recent years, a considerable disparity still exists between their capabilities and what real-world scenarios demand. Robust and computationally efficient controllers and estimation algorithms must be designed based on onboard exteroceptive sensors (e.g., vision, acoustic sensors, laser range finders), under which each vehicle can interact safely with neighbor vehicles and the surrounding environment. However, documented results for controlling robotic vehicles relying on onboard exteroceptive sensors either provide solutions only for ad-hoc scenarios or rely on large-scale simulations and field tests, lacking a unified and computationally efficient algorithm to ensure safe navigation in broader circumstances.
We propose a one-day workshop mainly devoted to the latest advancements in sensory-based estimation and control for unmanned systems, particularly emphasizing the demand for computationally efficient algorithms backed by formal performance guarantees for operations in real-world scenarios. For this purpose, we bring together experts in robotics and control to present the key topics on navigation and control of single vehicles, cooperative estimation and control of multiple vehicles, and reactive multi-vehicle collision avoidance, with applications on actual robotic vehicles. The proposed workshop will expose attendees to cutting-edge research in the field, with an eye on both theory and applications, providing graduate-level scientists and engineers new to the field insight into the challenges of designing computationally efficient algorithms with theoretical and performance guarantees for autonomous vehicles navigating in dynamic, unknown, and congested real-world environments. Furthermore, the workshop seeks to foster research collaborations between Control and Robotics communities, bridging the gap between theoretical advancements and their practical implementation.
Australian National University, Australia