Adaptative Regrasping Strategy for Rectangular Objects with Different Dimensions.
نویسندگان
چکیده
منابع مشابه
Regrasping
Regrasping must be performed whenever a robot's grasp of an object is not compatible with the task it must perform. Imagine a robotic cell with an arm alternatively picking up parts from a conveyor or a pallet and inserting them. The parts are presented in arbitrary orientations. I t can happen that the task cannot be achieved within a single grasp, due to a conjunction f constraints of the two...
متن کاملDesigning of 3D Rectangular Objects
This paper reviews the curve method [6] which recovers, as special cases, the two spline methods: one with interval tension in [5]: and the other with point tension in [4]. This curve scheme has been generalized for the designing of surfaces i.e. 3D objects (open or closed) can be captured, together with the facility of local as well as global. point and interval shape controls, with any rectan...
متن کاملA Large Margin Learning Method for Matching Images of Natural Objects with Different Dimensions
Imaging devices are of increasing use in environmental research requiring an urgent need to deal with such issues as image data, feature matching over different dimensions. Among them, matching hyperspectral image with other types of images is challenging due to the high dimensional nature of hyperspectral data. This chapter addresses this problem by investigating structured support vector mach...
متن کاملSupervised Policy Fusion with Application to Regrasping
I. INTRODUCTION Robust and stable grasping is one of the key requirements for successful robotic manipulation. Although, there has been a lot of progress in the area of grasping [1], the state-of-the-art approaches may still result in failures. Ideally, the robot would detect failures quickly enough to be able to correct them. In addition, the robot should be able to learn from its mistakes to ...
متن کاملGeneralizing Regrasping with Supervised Policy Learning
We present a method for learning a general regrasping behavior by using supervised policy learning. First, we use reinforcement learning to learn linear regrasping policies, with a small number of parameters, for single objects. Next, a general high-dimensional regrasping policy is learned in a supervised manner by using the outputs of the individual policies. In our experiments with multiple o...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series C
سال: 2001
ISSN: 0387-5024,1884-8354
DOI: 10.1299/kikaic.67.3212