Sebastian Stock

Learn More
One way to improve the robustness and flexibility of robot performance is to let the robot learn from its experiences. In this paper, we describe the architecture and knowledge-representation framework for a service robot being developed in the EU project RACE, and present examples illustrating how learning from experiences will be achieved. As a unique(More)
Robots are expected to carry out complex plans in real world environments. This requires the robot to track the progress of plan execution and detect failures which may occur. Planners use very abstract world models to generate plans. Additional causal, temporal, categorical knowledge about the execution, which is not included in the planner's model, is(More)
In this paperw ep ropose an ew approach to coordinate multiple machines in theg rain harvestingp rocess,b ased on meta-constraint reasoning.T hisw ay we obtainm oref lexiblep lans that can be adapteda te xecutiont ime. As an examples cenario we focuso ns ilage maizeh arvest-ing. We arguethatm oresophisticated flexible planning mechanisms areneeded in ordert(More)
This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system(More)
99 and as tutors. I will show examples of this approach for different stages in the origins of symbolic intelligence grounded through sensory-motor intelligence: the discovery of symbol use, the big spurt in vocabulary, the origins of grammar, and the origins of the self. Planning and execution is crucial for the performance of complex tasks in challenging(More)
This paper reports on the aims, the approach, and the results of the European project RACE. The project aim was to enhance the behavior of an autonomous robot by having the robot learn from conceptualized experiences of previous performance, based on initial models of the domain and its own actions in it. This paper introduces the general system(More)
  • 1