29.10.2026 IfI Colloquium: Towards Robust and Scalable Multi-Agent Aerial Manipulation
Speaker:
Dr. Sihao Sun
Researcher in Robotics, Delft University of Technology, The Netherlands
Date: Thursday, 29 October 2026, 17:15
Location: room BIM 4-033 at the Department of Informatics (IfI), Binzmühlestrasse 11, 8050 Zürich
Details about the format of the talk shall be checked always just ahead of a certain presentation date: (information here)
Abstract
Aerial manipulators act as flying hands, enabling physical interaction with the environment and the manipulation of objects. However, their limited load capacity restricts the forces and torques that each platform can exert on the objects. Multi-agent aerial manipulation offers a promising direction to fundamentally overcome these limitations. In this presentation, I will present our recent work on a centralized approach to the cooperative aerial manipulation of a cable-suspended load, along with our explorations of decentralized solutions aimed at improving scalability and fault tolerance. I will also discuss related work in the field of mechanical design, as well as learning-based and model-based planning and control for aerial manipulators. These developments open the door to future dexterious, robust, and scalable multi-agent aerial manipulation systems.
Bio
Sihao Sun is a postdoctoral researcher funded by NWO (Dutch Research Council) Veni grant, embedded in the Department of Cognitive Robotics at Delft University of Technology. He received his PhD in Aerospace Engineering from TU Delft in 2020, after which he held postdoctoral positions with the Robotics and Perception Group at the University of Zurich and the Robotics and Mechatronics Group at the University of Twente. He is the winner of an IEEE Robotics and Automation Letters Best Paper Award, and the NASA Tech Briefs Award. His work has been published in leading journals, including Nature, IEEE Transactions on Robotics, and Science Robotics. His research focuses on planning, control, and perception for aerial robots.