As robots become a mass consumer product, they will need to learn new skills by interacting with typical human users. Past approaches have adapted reinforcement learning (RL) to a...
Abstract. The proposed algorithm has been developed as a pre-processing tool for inflating cortical surface meshes, which have been created using segmentation and subsequent triang...
We propose dynamical systems trees (DSTs) as a flexible model for describing multiple processes that interact via a hierarchy of aggregating processes. DSTs extend nonlinear dynam...
ABSTRACT. Reconfigurable systolic arrays can be adapted to efficiently resolve a wide spectrum of computational problems; parallelism is naturally explored in systolic arrays and r...
This paper presents a data-driven approach for segmenting range data to enable a humanoid robot to perform interactive domestic tasks. Range data is segmented into geometric primi...