Small, light-weight flying robots such as the 20-gram DelFly Explorer form an extreme challenge to Artificial Intelligence, because of the strict limitations in onboard sensors, processing, and memory. I try to uncover general principles of intelligence that will allow such limited, small robots to perform complex tasks.
Vision is a prime sense for both animals and robots. I create efficient vision algorithms for robot control and navigation.
Fruit flies are able to fly, avoid obstacles, navigate, and socially interact with each other with only a 100,000 neurons. Insects are a rich source of inspiration for elegant, efficient AI.
As Rodney Brooks said: "Simulation is doomed to succeed" - I focus on problems actually faced by robots in the real world.
Please click below to have a look at a selection of my current research projects.
Autonomous drone racing Drone racing by human pilots is becoming a major e-sport. In its wake, autonomous drone racing has become a major challenge for artificial intelligence and control. Over the years, the speed of autonomous race drones has been gradually improving. Most of the autonomous racing drones are equipped with high-performance processors, with multiple, […]
We have developed a new, highly agile flapping-wing robot, called the DelFly Nimble. It can mimic high-speed insect escape maneuvers so accurately, that it exhibited very similar motion as fruitflies when performing these same maneuvers. Interestingly, the robot turned around an axis that was not controlled during the escape maneuver. In particular, it would turn […]
The Dutch Science Foundation (NWO) has granted me a personal grant on the topic of self-supervised learning. The grant, named TOP grant, is intended for researchers who obtained their PhD maximally 10 years ago. A structured study on self-supervised learning In the proposal, I forward self-supervised learning (SSL) as a reliable mechanism to have robots […]