Robotics Day 2024 Fresh Perspectives on Robotics

Dr. Eldert van Henten is a professor of Biosystems Engineering at the Agricultural Biosystems Engineering group of Wageningen University. Covering applications in the whole agri-food chain, his technical research interests include sensing, modelling, and optimal control of bio-systems in the precision farming context as well as agricultural robotics. 

Autonomous driving development is challenging due to multi-modal sensors, hardware, and advanced algorithms (perception, planning, and control). A major obstacle is the diversity of the traffic environment, particularly in edge scenarios. The strict safety requirements and human-like comfort desire are also pushing the design and testing, validation technologies. This talk presents some technologies dealing with those challenges, focusing on three pillars: Real2Sim - from real data to simulation models, Sim2Real - a scenario-based testing process from simulation to hardware and physical vehicle testing based on an XiL engineering development cycle, and safety-comfort driving algorithms (MPC, data-driven learning control). Some vehicle demonstrations will be shown. 

Proving that a technological solution helps to solve a medical problem only brings you so far. To actually solve the medical problem, providing access to your solution is a must. Users need to be able to use your system. Giving it to them for free of course would be an option, but given the hoops you need to jump through to actually develop your technology into a working product, you probably are looking for some way of reimbursing your cost. Therefore, the usual approach is to sell this product. This is, however, not the end of the road for you. This talk is aimed at providing an introductory insight into the steps that come after you have the technology and will focus on answering the question: how to productize your medical (robotic) technology – in a sustainable manner?

For robots to be able to truly integrate human-populated, dynamic, and unpredictable environments, they will have to have strong adaptive capabilities. In this talk, I argue that these adaptive capabilities should leverage interaction with end users, who know how (they want) a robot to act in that environment. I will present an overview of my work on the topic of Human-Interactive Robot Learning, a growing interdisciplinary subfield that embraces rich, bidirectional interaction to shape robot learning.