Autonomous Learning of Active Depth Perception: from Neural Models to Humanoid Robots – ALADeP

Many animals and robots use two eyes (or cameras) to see the world three-dimensionally and estimate precise distances. This project investigates how this ability can be developed in biological vision systems or learned by robots completely autonomously.

The main objectives of the project are: The development of a biologically plausible model for the autonomous learning of active stereo vision, especially distance estimation in mammals. The other goal is to model changes in the learning process in pathological cases (strabismus, amblyopia) and in the case of experimental environmental conditions. 

Affiliated partners and Project leader

FIAS: Prof. Jochen Triesch
Japan Advanced Institute of Science and Technology, Japan: Prof. Sungmoon Jeong

Sponsored by the Federal Ministry of Education and Research (BMBF), (FKZ 01GQ1414)

Project duration: 2014 - 2017