Papers by Luis Molina-Tanco
Architecture for a robot learning by imitation system
Robot learning by imitation has become a key topic in robotics research in the last years, due to... more Robot learning by imitation has become a key topic in robotics research in the last years, due to the increasing interest in social robots. While several architectures that deal with this topic have been proposed, few efforts have been done in finding unified formats that may help in analyzing and comparing these architectures. This paper firstly proposes a set of
A Model-based Humanoid Perception System for Real-time Human Motion Imitation
... SYSTEM OVERVIEW The flow of the proposed model-based humanoid perception system for real-time... more ... SYSTEM OVERVIEW The flow of the proposed model-based humanoid perception system for real-time human motion imitation consists ... The parent bone corresponds to the upper arm and is allowed to rotate around three perpendicular axes. ... Robot learning from demon stration ...
Real-time Human Motion Analysis for Human-Robot Interaction
... The proposed robot perception system must run on the robot and will therefore be restricted t... more ... The proposed robot perception system must run on the robot and will therefore be restricted to the robot capabilities. ... movement of head and hands, and ii) providing the joint angle information required for the robot to imitate ... Parent link, (X, Y )(i,j,l). If Hom(i, j, l) is equal to 1, the ...
Pattern Recognition Letters, 2007
Target representation and localization is a central component in visual object tracking. In this ... more Target representation and localization is a central component in visual object tracking. In this paper a new approach for target representation and localization is presented. This approach tackles two of the most important causes of failure in object tracking: changes of object appearance and occlusions. We propose a modified template matching approach which does not require a priori learning of object views. This method allows to track non-rigid objects in real-time by employing a weighted template which is dynamically updated, and a hierarchical framework that integrates all the components of the tracker. Our hierarchical tracker allows tracking of multiple objects with low increase of computational time. The capability of the tracking system to handle occlusions and target distortions is demonstrated for several video sequences.
A model-based humanoid perception system for real-time human motion imitation
... SYSTEM OVERVIEW The flow of the proposed model-based humanoid perception system for real-time... more ... SYSTEM OVERVIEW The flow of the proposed model-based humanoid perception system for real-time human motion imitation consists ... The parent bone corresponds to the upper arm and is allowed to rotate around three perpendicular axes. ... Robot learning from demon stration ...
A novel hybrid approach to upper-body human motion capture
This paper describes an upper-body human motion capture system which combines a learning-based al... more This paper describes an upper-body human motion capture system which combines a learning-based algorithm for human torso posture recognition with a model-based approach which estimates the human arms pose. The system uses a skin colour tracker to capture the movement of hands and face, and stereo data to obtain the silhouette of the human. The disparity map generated by the stereo vision system is also employed to perform a learning-based stage, providing an estimation of the torso posture. Experimental results show that the proposed approach runs at 20 frames per second in natural scenarios where the human is not required to wear special markers.
The Construction of Bounded Irregular Pyramids with a Union-Find Decimation Process
The Bounded Irregular Pyramid (BIP) is a mixture of regular and irregular pyramids whose goal is ... more The Bounded Irregular Pyramid (BIP) is a mixture of regular and irregular pyramids whose goal is to combine their advantages. Thus, its data structure combines a regular decimation process with a union-find strategy to build the successive levels of the structure. The irregular part of the BIP allows to solve the main problems of regular structures: their inability to preserve connectivity or to represent elongated objects. On the other hand, the BIP is computationally efficient because its height is constrained by its regular part. In this paper the features of the Bounded Irregular Pyramid are discussed, presenting a comparison with the main pyramids present in the literature when applied to a colour segmentation task.
Biological-plausible attention mechanisms are general approaches that permit a social robot to ex... more Biological-plausible attention mechanisms are general approaches that permit a social robot to extract only relevant information from the huge amount of input data. In this paper an attention mechanism based on the feature integration theory is proposed. The aim of this attention mechanism is to provide to higher-level modules of the vision system the most relevant regions in fast, dynamic scenarios where interaction with humans can occur. The proposed system integrates bottom-up (data-driven) and top-down (model-driven) processing. The bottom-up component determines and selects salient image regions by computing a number of different features. The top-down component makes use of object templates to filter out data and track significant objects. The proposed system has three steps: parallel computation of feature maps, feature integration and simultaneous tracking of the most salient regions. Its main characteristic is that the mechanism integrates the tracking of the most salient regions, which allows to handle changing environments with moving objects where occlusions can occur.
Model-based Pose Estimator for Real-time Human-Robot Interaction
This paper introduces a real-time motion analysis system based on hierarchical tracking and inver... more This paper introduces a real-time motion analysis system based on hierarchical tracking and inverse kine- matics. In particular, it is a computer-vision based, upper-body motion analysis system that works without special devices or markers. Self-occlusions and depth- ambiguity introduce errors that are addressed with a model-based pose estimator. A fast analytic inverse kinematics method is introduced. This method can re- cover from erroneous poses by using a new alternative evaluation scheme. Experimental results show that the complete system is able to imitate safely upper-body human movements using only limited cues, such as centroid coordinates and disparity of head and hands.
Pattern Recognition Letters, 2009
Towards developing an interface for human-robot interaction, this paper proposes a two-level appr... more Towards developing an interface for human-robot interaction, this paper proposes a two-level approach to recognise gestures which are composed of trajectories followed by different body parts. In a first level, individual trajectories are described by a set of key-points. These points are chosen as the corners of the curvature function associated to the trajectory, which will be estimated using and adaptive, non-iterative scheme. This adaptive representation allows removing noise while preserving detail in curvature at different scales. In a second level, gestures are characterised through global properties of the trajectories that compose them. Gesture recognition is performed using a confidence value that integrates both levels. Experimental results show that the performance of the proposed method is high in terms of computational cost and memory consumption, and gesture recognition ability.
A model-based humanoid perception system for real-time human motion imitation
This paper presents real-time human motion analysis based on hierarchical tracking and inverse ki... more This paper presents real-time human motion analysis based on hierarchical tracking and inverse kinematics. Our goal is to implement a mechanism of human-machine interaction that permits a robot to learn from human gestures, and, as a first stage, we have developed a computer-vision based human upperbody motion analysis system. This application requires developing a real-time human motion capturing system that works without special devices or markers. Since such a system is unstable and can only acquire, partial information because of self-occlusions, we have introduced a pose estimation method based on inverse kinematics. This system can estimate upper-body human postures with limited perceptual cues such as position of head and hands. The method has been tested using a HOAP-I humanoid robot.
This paper presents a general architecture that allows a humanoid robot to imitate upper-body mov... more This paper presents a general architecture that allows a humanoid robot to imitate upper-body movements of a human demonstrator. This architecture integrates a mechanism to memorize novel behaviours executed by a human demonstrator, with a module to recognize and generate its own interpretation of already observed behaviours. Our imitator includes three biologically plausible components: i) an attention mechanism to autonomously extract relevant information from the visual input; ii) a supra-modal representation of the motion of observed body parts to map visual and motor domains; and iii) an active imitation module which involves the motor systems in the behaviour recognition process. Experimental results with a real humanoid robot demonstrate the ability of the proposed architecture to acquire novel behaviours and to recognize and reproduce previously memorized ones.
In the learning by imitation framework, a module is required to translate the visually perceived ... more In the learning by imitation framework, a module is required to translate the visually perceived behaviour of the demonstrator's body to a representation where the imitator perceives its own movements, either visually, propioceptively, or both. This transformation must take into account the different body configurations of imitator and demonstrator. In this work, a solution to translation of the visually perceived end-effector motion is presented. The proposed approach is included in a system which allows a robot to learn the behaviour of a human demonstrator from stereo visual information. Real-time results are presented and discussed.
Pattern Recognition, 2006
The main goal of this work is to compare pyramidal structures proposed to solve segmentation task... more The main goal of this work is to compare pyramidal structures proposed to solve segmentation tasks. Segmentation algorithms based on regular and irregular pyramids are described, together with the data structures and decimation procedures which encode and manage the information in the pyramid. In order to compare the different segmentation algorithms, we have employed three types of quality measurements: the shift variance measure, the F function and the Q function.
Real-time human motion analysis for human-robot interaction
... The proposed robot perception system must run on the robot and will therefore be restricted t... more ... The proposed robot perception system must run on the robot and will therefore be restricted to the robot capabilities. ... movement of head and hands, and ii) providing the joint angle information required for the robot to imitate ... Parent link, (X, Y )(i,j,l). If Hom(i, j, l) is equal to 1, the ...
Online absorption of mediolateral balance disturbances for a small humanoid robot using accelerometer and force-sensor feedback
Sociable humanoid robots should be able to coexist with humans in human environments, where they ... more Sociable humanoid robots should be able to coexist with humans in human environments, where they will very likely have to face unexpected disturbance forces. In this paper, an online ankle-hip control strategy is presented that allows a standing biped robot to withstand a force in the mediolateral direction, using foot force-sensor and accelerometer feedback. The control algorithm is simple and can be implemented on any biped robot equipped with these sensors. Experimental results are presented for a small humanoid robot Fujitsu HOAP-1 showing that our method allows the robot to bear considerable perturbation forces.
Uploads
Papers by Luis Molina-Tanco