• Publications
  • Influence
Simple Gabor feature space for invariant object recognition
In this study, fundamental properties of Gabor features, construction of the simple feature space, and invariant search operations in the feature space are discussed in more detail. Expand
Action recognition and understanding through motor primitives
This work deals with single arm/hand actions which are very similar to each other in terms of arm/ hand motions, and uses a combination of discriminative support vector machines and generative hidden Markov models to model the process. Expand
Invariance properties of Gabor filter-based features-overview and applications
This study provides an overview of Gabor filters in image processing, a short literature survey of the most significant results, and establishes invariance properties and restrictions to the use of Gbps filters in feature extraction. Expand
Assessing Grasp Stability Based on Learning and Haptic Data
A probabilistic learning framework to assess grasp stability is proposed and it is shown that knowledge about grasp stability can be inferred using information from tactile sensors, which opens a number of interesting venues for the future research. Expand
Learning task constraints for robot grasping using graphical models
This paper shows how an object representation and a grasp generated on it can be integrated with the task requirements and presents a system designed to structure data generation and constraint learning processes that is applicable to new tasks, embodiments and sensory data. Expand
Learning grasp stability based on tactile data and HMMs
This work presents an investigation of probabilistic modeling for inferring grasp stability based on learning from examples and classification of a grasp as stable or unstable before applying further actions on it, e.g. lifting. Expand
Physical rehabilitation exercises assessment based on Hidden Semi-Markov Model by Kinect v2
This work investigates how Hidden Semi-Markov Model can be used to monitor and evaluate physical rehabilitation exercises by Kinect v2 to support medical personnel and patients during rehabilitation at home and gives a feedback to physiotherapists and patients about exercise execution. Expand
New shortest-path approaches to visual servoing
Two new shortest-path approaches to visual servoing are presented, which avoids the use of a 3D model of the target object by using homography based partial pose estimation and a position-based approach that guarantees both shortest Cartesian trajectory and object visibility. Expand
Sampled differential dynamic programming
SaDDP is presented, a sampled version of the widely used differential dynamic programming (DDP) control algorithm that contributes through establishing a novel connection between two major branches of robotics control research, that is, gradient-based methods such as DDP and Monte Carlo methods that utilize random simulated trajectory rollouts. Expand
Online motion synthesis using sequential Monte Carlo
We present a Model-Predictive Control (MPC) system for online synthesis of interactive and physically valid character motion. Our system enables a complex (36-DOF) 3D human character model to balanceExpand