This paper presents a method to compute a feasible region for grasping unknown objects using visual features. The method is divided into two separate sections: candidates grasp generation and testing of the feasible r...
详细信息
Autonomous navigation of a mobile robot is a challenging task. Much work has been done in indoor navigation in the last 10-15 years. Fewer results have been obtained in outdoor robotics. Laser range finder technology ...
详细信息
This paper presents a new approach to the prediction of visual occlusions for a robotic system performing visual servoing tasks. The case of a multi-arm robotic cell equipped with a multi-camera eye-to-hand visual sys...
详细信息
In this paper we address a new problem in reinforcement learning. Here we consider an agent that faces multiple learning tasks within its lifetime. The agent's objective is to maximize its total reward in the life...
详细信息
ISBN:
(纸本)0780378660
In this paper we address a new problem in reinforcement learning. Here we consider an agent that faces multiple learning tasks within its lifetime. The agent's objective is to maximize its total reward in the lifetime as well as a conventional return in each task. To realize this, it has to be endowed an important ability to keep its past learning experiences and utilize them for improving future learning performance. This time we try to phrase this problem formally. The central idea is to introduce an environmental class, BV-MDPs that is defined with the distribution of MDPs. As an approach to exploiting past learning experiences, we focus on statistics (mean and deviation) about the agent's value tables. The mean can be used as initial values of the table when a new task is presented. The deviation can be viewed as measuring reliability of the mean, and we utilize it in calculating priority of simulated backups. We conduct experiments in computer simulation to evaluate the effectiveness.
This paper presents an automatic dextrous handling and inspection system for optoelectronics components using a novel 6 DOF microgripper. The control system includes three hierarchical layers: actuator control layer, ...
详细信息
This paper is about the implementation of grasping skills in a humanoid robot. Following a developmental approach the robot is initially equipped with little perceptual and motor competencies whose role is to bootstra...
详细信息
In the submillimetric objects manipulations, the adhesion (capillary force, pull-off force and Van-der-Waals force) and the electrostatic forces affect the behavior of the micro-objects. These forces decrease signific...
详细信息
作者：
Böhlen, MarcSchool of Art
The Robotics Institute Carnegie Mellon University PittsburghPA United States
Typically, the animal world has been used conceptually by roboticists as a source of inspiration for finding new approaches to efficient locomotion, perception and intelligent control [Brooks91], [Hallam, Walker93], [...
详细信息
This paper describes the development and the application of an object tracking algorithm from a sequence of images. The algorithm is based on window-matching techniques using the sum of squared differences (SSD) as a ...
详细信息
Hospitals face with heavy traffic of goods everyday, where transportation tasks are mainly carried by human. Analysis of the current situation of transportation in a typical hospital showed several transportation task...
详细信息
暂无评论