For one year I worked at the Humboldt Universities – Artificial Intelligence Workgroup. My focus was on researching new ways of grasping and walking for for humanoid robots.
Background
The Idea was to merge the information of multiple sensors (acceleration, pressure, camera, etc.) instead of using every sensor on it’s own, to improve the grasping and walking abilities of humanoid robots. Also additional sensors where added.
Technologies
- Hardware: Nao Robots, additional modular sensors (e.g. acceleration)
- Software: C++
Results
The research resulted in promising new approaches for adaptive walking an grasping. A detailed paper on one of the grasping approaches was released: