An Active Vision System for Detecting, Fixating and Manipulating Objects in the Real World

Abstract

The ability to autonomously acquire new knowledge through interaction with the environment is an important research topic in the field of robotics. The knowledge can be acquired only if suitable perception-action capabilities are present: a robotic system has to be able to detect, attend to and manipulate objects in its surrounding. In this paper, we present the results of our longterm work in the area of vision based sensing and control. The work on finding, attending, recognizing and manipulating objects in domestic environments is studied. We present a stereo based vision system framework where aspects of Top-down and Bottom-up attention as well as foveated attention are put into focus and demonstrate how the system can be utilized for robotic object grasping.

Grounded object individuation by a humanoid robot

“…In contrast, a wide variety of methods have been developed that allow robots to recognize previously observed objects. The majority of these methods use 2D and 3D visual features (see [14], [15], [7], [9], [11]). Other vision-based approaches have also been proposed for finding image regions from multiple views that contain the same object [16].…”

“…In contrast, most methods used by robots to recognize objects start with a fixed object representation in which the robot's training data is labeled with one of a finite number of object identities (see [4], [5], [6], [7], [8], [9], [10], [11] for a representative sample of such approaches). These methods implicitly make the assumption that the object individuation task has already been solved.…”

Using Saliency-Based Visual Attention Methods for Achieving Illumination Invariance in Robot Soccer

“…For instance, in the work of Rasolzadeh et al [9], the visual attention module gets executed prior to the object detection and recognition modules to direct the head saccades and help the robot figure out where to search for important objects. Frintrop et al proposed a similar approach [10,11], where the regions of interest are detected using both bottom up and top down saliency extraction followed by a fast-classifier that classifies regions for object recognition purposes.…”

Salient features based on visual attention for multi-view vehicle classification

“…In a similar manner, Siagian and Itti [12,13] use salient features derived from attention together with context information to build a system for mobile robotic applications that can differentiate outdoor scenes from various sites on a campus [12] and for localization of a robot [13]. In Rasolzadeh et al [14], a stereoscopic vision system framework identifies attention-based features that are then utilized for robotic object grasping. Rotenstein et al [15] propose the use of mechanisms of visual attention to be integrated in a smart wheelchair for disabled children to help in visual search tasks.…”