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...

Toward Soft Heterogeneity in Robotic Swarms (demonstration)

Diversity and inequality are essences of our real world. Ant colonies are comprised of hundreds of individuals, with no two of them being exactly identical. A flock of birds contains individuals with slight variations in size, speed and vision. Looking at human societies such diversity can be seen among individuals differing in body shape and in...

An Interactive,Web-based Tool for Genealogical Entity Resolution (demonstration)

We demonstrate an interactive, web-based tool which helps historians to do Genealogical Entity Resolution. This work has two main goals: First, it uses Machine Learning (ML) algorithms to assist humanities researchers to perform Genealogical Entity Resolution. Second, it facilitates the generation of benchmark data for computer scientists to...

Automatically mapped transfer between reinforcement learning tasks via three-way restricted Boltzmann machines (abstract)

Automated Negotiation Based on Sparse Pseudo-Input Gaussian Processes (abstract)

This paper deals with a prominent type of complex negotiations. We propose a novel negotiation strategy called Dragon which employs sparse pseudo-input Gaussian processes (SPGPs) to model efficiently the behavior of the negotiating opponents. The experimental results provided in this paper show that Dragon outperforms the state-of-the-art...