Prof. Philippe Bonnifait
Cooperative localization for autonomous cars: Lessons learned from the Grand Cooperative Driving Challenge (Wednesday, September 6th)
The Heudiasyc Laboratory participated to the final stage of the GCDC 2016 at Helmond, in the Netherlands. One the most challenging scenario was merging on a two-lane highway with 9 other cars participating to the challenge. Typically, all the vehicles in the left lane had to merge into the right lane after having received a message from the infrastructure, because of road works for instance. This talk will present the system that has been developed for the challenge and discuss the lessons that have been learned from it. Based on this experience, some cooperative localization problems will be formalized and some solutions will be presented.
Prof. Davide Scaramuzza
Towards Agile Flight of Vision-controlled Micro Flying Robots: from Active Vision to Event-based Vision (Thursday, September 7th)
Autonomous quadrotors will soon play a major role in search-and-rescue and remote-inspection missions, where a fast response is crucial. Quadrotors have the potential to navigate quickly through unstructured environments, enter and exit buildings through narrow gaps, and fly through collapsed buildings. However, their speed and maneuverability are still far from those of birds. Indeed, agile navigation through unknown, indoor environments poses a number of challenges for robotics research in terms of perception, state estimation, planning, and control. In this talk, I will give an overview of my research activities on visual navigation of quadrotors, from slow navigation (using standard frame-based cameras) to agile flight (using active vision and event-based cameras). Topics covered will be: visual inertial state estimation, monocular dense reconstruction, active vision and control, event-based vision.
Prof. Stéphane Doncieux
Creativity: the missing feature for robots to deal with open environments (Friday, September 8th)
Many robots solve complex tasks in closed environments that are fully known by the robot designer. Robots are much rarer in our every day environment. The main reasons are its complexity and openness that frequently result in unpredictable situations created by new objects or new dynamics of interaction. Numerous applications of robotics would benefit from robot abilities to deal with open environments. It will be argued that performance, the main guide in the robotics field, is not enough to encourage the development of the features required to deal with such environments. It will be suggested to add originality, thus defining a new bi-objective criterion: creativity. Some approaches to creativity in robotics will be presented as well as the challenges that it raises.