Persistent self-supervised learning: From stereo to monocular vision for obstacle avoidance

Self-supervised learning is a reliable learning mechanism in which a robot uses an original, trusted sensor cue for training to recognize an additional, complementary sensor cue. We study for the first time in self-supervised learning how a robot’s learning behavior should be organized, so that the robot can keep performing its task in the...

Applied Robotics: Precision Placement in RoboCup@Work (demonstration)

In this demonstration we show how various approaches from different computer science domains have been combined to win the 2013 world championship title in the RoboCup@Work league. RoboCup@Work aims to facilitate the use of autonomous robots in industry. Among other contributions, we show how artificial intelligence can be successfully...

Effective Approximations for Planning with Spatially Distributed Tasks

Planning in cooperative multiagent systems can be neatly formalized using Multi-Agent MDPs, but solving these models is computationally costly. This paper introduces a sub-class of problems called spatial task allocation problems (SPATAPS) that model problems in which a team of agents has to service a dynamically changing set of tasks that is...