In this paper, we propose and examine the feasibility of the robot-assisted behavioral intervention system so as to strengthen positive response of the children with autism spectrum disorder (ASD) for learning social skills. Based on well-known behavioral treatment protocols, the robot offers therapeutic training elements of eye contact and emotion reading respectively in child-robot interaction, and it subsequently accomplishes pre-allocated meaningful acts by estimating the level of children’s reactivity from reliable recognition modules, as a coping strategy. Furthermore, for the purpose of labor saving and attracting children’s interest, we implemented the robotic stimulation configuration with semi-autonomous actions capable of inducing intimacy and tension to children in instructional trials. From these configurations, by evaluating the ability of recognizing human activity as well as by showing improved reactivity for social training, we verified that the proposed system has some positive effects on social development, targeted for preschoolers who have a high functioning level.

We present a robust power transmission lines detection method based on vanishing point estimation. Vanishing point estimation can be helpful to detect power transmission lines because parallel lines converge on the vanishing point in a projected 2D image. However, it is not easy to estimate the vanishing point correctly in an image with complex background. Thus, we first propose a vanishing point estimation method on power transmission lines by using a probabilistic voting procedure based on intersection points of line segments. In images obtained by our system, power transmission lines are located in a fan-shaped area centered on this estimated vanishing point, and therefore we select the line segments that converge to the estimated vanishing point as candidate line segments for power transmission lines only in this fan-shaped area. Finally, we detect the power transmission lines from these candidate line segments. Experimental results show that the proposed method is robust to noise and efficient to detect power transmission lines.

This paper presents a new shape-based algorithm using affine category shape model for object category recognition and model learning. Affine category shape model is a graph of interconnected nodes whose geometric interactions are modeled using pairwise potentials. In its learning phase, it can efficiently handle large pose variations of objects in training images by estimating 2-D homography transformation between the model and the training images. Since the pairwise potentials are defined on only relative geometric relationship between features, the proposed matching algorithm is translation and in-plane rotation invariant and robust to affine transformation. We apply spectral matching algorithm to find feature correspondences, which are then used as initial correspondences for RANSAC algorithm. The 2-D homography transformation and the inlier correspondences which are consistent with this estimate can be efficiently estimated through RANSAC, and new correspondences also can be detected by using the estimated 2-D homography transformation. Experimental results on object category database show that the proposed algorithm is robust to pose variation of objects and provides good recognition performance.

This paper describes how a person extracts a unknown object with pointing gesture while interacting with a robot. Using a stereo vision sensor, our proposed method consists of two stages: the detection of the operators' face, the estimation of the pointing direction, and the extraction of the pointed object. The operator's face is recognized by using the Haar-like features. And then we estimate the 3D pointing direction from the shoulder-to-hand line. Finally, we segment an unknown object from 3D point clouds in estimated region of interest. On the basis of this proposed method, we implemented an object registration system with our mobile robot and obtained reliable experimental results.

This paper describes a new method for indoor environment mapping and localization with stereo camera. For environmental modeling, we directly use the depth and color information in image pixels as visual features. Furthermore, only the depth and color information at horizontal centerline in image is used, where optical axis passes through. The usefulness of this method is that we can easily build a measure between modeling and sensing data only on the horizontal centerline. That is because vertical working volume between model and sensing data can be changed according to robot motion. Therefore, we can build a map about indoor environment as compact and efficient representation. Also, based on such nodes and sensing data, we suggest a method for estimating mobile robot positioning with random sampling stochastic algorithm. With basic real experiments, we show that the proposed method can be an effective visual navigation algorithm.

Based on object recognition technology, we present a new global localization method for robot navigation. For doing this, we model any indoor environment using the following visual cues with a stereo camera; view-based image features for object recognition and those 3D positions for object pose estimation. Also, we use the depth information at the horizontal centerline in image where optical axis passes through, which is similar to the data of the 2D laser range finder. Therefore, we can build a hybrid local node for a topological map that is composed of an indoor environment metric map and an object location map. Based on such modeling, we suggest a coarse-to-fine strategy for estimating the global localization of a mobile robot. The coarse pose is obtained by means of object recognition and SVD based least-squares fitting, and then its refined pose is estimated with a particle filtering algorithm. With real experiments, we show that the proposed method can be an effective vision-based global localization algorithm.

This paper deals with a tangible interface system that introduces robot as remote avatar. It is focused on a new method which makes a robot imitate human arm motions captured from a remote space. Our method is functionally divided into two parts: capturing human motion and adapting it to robot. In the capturing part, we especially propose a modified potential function of metaballs for the real-time performance and high accuracy. In the adapting part, we suggest a geometric scaling method for solving the structural difference between a human and a robot. With our method, we have implemented a tangible interface and showed its speed and accuracy test.