Selective attention of primates or human being has been modeled and implemented by many vision researchers in a decade. And also several attempts, which improve object recognition using selective attention model, have existed. But there are few researches in the gaze planning for the results of selective attention process. Therefore we propose a planning method based on edge information in the attended regions. And we explain the edge description methods (edge density and entropy) and also propose a new description method, edge uniformity. We evaluate the performance of the methods in the viewpoint of attentive object recognition.

For successful SLAM, landmarks for pose estimation should be continuously observed. Firstly, we proposed the object selection algorithm from 2D images and 3D depth maps without human’s supervision. We used the SIFT algorithm to obtain descriptors of point features inside the object, and the surface segmentation algorithm to obtain separated objects from point clouds of 3D depth maps. Automatically selected objects were tested by the threshold function using repeatability, distinctiveness and saliency whether the objects were suitable or not for reusing and sharing between the robots. Secondly, we suggested the closed-form solution to estimate the 3D pose of robots from the information of selected objects. Furthermore, we provided the effective way to accomplish the tasks using multi-robot by compensating the accumulated navigating errors and re-planning the collision-free motion of the robots using the extended collision map algorithm.

One method of dedicated robots task allocation has selected a task to be assigned after comparing the results when tasks are allocated to robots, respectively. Thus, quick and accurate prediction of makespan is important for enhancing the be solved in polynomial time. In this paper, the makespan prediction is mathematically analyzed and a greed algorithm is suggested on the basis of the analysis. The effectiveness of the makespan prediction algorithm was verified by simulation in comparison with the complete enumeration.