Local Learning for Visual Robotic Systems
- Zugl.: Kiel, Univ., Diss., 2007
In this thesis a new supervised function approximation technique called Hierarchical Network of Locally Arranged Models is proposed to aid the development of learning-based visual robotic systems. In a coherent framework the new approach oers various means to create modular solutions to learning problems. It is possible to built up heterogeneous hierarchies so that dierent subnetworks can rely on dierent information sources. Modularity is realized by an automatic division of the input space of the target function into local regions where non-redundant models perform the demanded mapping into the output space. The goal is to replace one complex global model by a set of simple local ones. E.g. non-linear functions should be approximated with a number of simple linear models. The advantage of locality is the reduction of complexity: simple local models can more robustly be established and more easily be analyzed. Global validity is ensured by local specialization. The presented approach relies essentially on two new contributions: means to de ne the so-called domains of the local models (i.e. the region of their validity) and algorithms to split up the input space in order to achieve good approximation quality. The suggested models for the domains have dierent exibility so that the local regions can have various shapes. Two learning algorithms are developed of which the oine version works on a xed training set that is acquired before the application of the network, while the online version is useful if the network should be continually re ned during operation. Both algorithms follow the strategy to place more local models at these regions of the input space where good approximation of the target function is harder to achieve. Furthermore, mechanisms are proposed that unify domains in order to simplify created networks, that de ne the degree of cooperation and competition between the dierent local models and that automatically detect data outliers to secure the application of a network. The value of the new approach is validated with public benchmark tests where several competitors are outperformed.