Learning how to grasp objects
نویسندگان
چکیده
This paper deals with the problem of estimating an appropriate hand posture to grasp an object, from 2D object’s visual cues in a many-to-many (objects,grasp) configuration. A statistical learning protocol implementing vector-valued regression is adopted for both classifying the most likely grasp type and estimating the hand posture. An extensive experimental evaluation on a publicly available dataset of visuo-motor data reports very promising results and encourages further investigations.
منابع مشابه
Grasp analysis of a four-fingered robotic hand based on Matlab simmechanics
The structure of the human hand is a complex design comprising of various bones, joints, tendons, and muscles functioning together in order to produce the desired motion. It becomes a challenging task to develop a robotic hand replicating the capabilities of the human hand. In this paper, the analysis of the four-fingered robotic hand is carried out where the tendon wires and a spring return me...
متن کاملUsing Geometry to Detect Grasp Poses in 3D Point Clouds
This paper proposes a new approach to using machine learning to detect grasp poses on novel objects presented in clutter. The input to our algorithm is a point cloud and the geometric parameters of the robot hand. The output is a set of hand poses that are expected to be good grasps. There are two main contributions. First, we identify a set of necessary conditions on the geometry of a grasp th...
متن کاملLearning and Inference of Dexterous Grasps for Novel Objects with Underactuated Hands
Recent advances have been made in learning of grasps for fully actuated hands. A typical approach learns the target locations of finger links on the object. When a new object must be grasped, new finger locations are generated, and a collision free reach-to-grasp trajectory is planned. This assumes a collision free trajectory to the final grasp. This is not possible with underactuated hands, wh...
متن کاملVisual Guided Grasping of Aggregates using Self-Valuing Learning
We present a self-valuing learning technique which is capable of learning how to grasp unfamiliar objects and generalize the learned abilities. The learning system consists of two learners which distinguish between local and global grasping criteria. The local criteria are not object specific while the global criteria cover physical properties of each object. The system is self-valuing, i.e. it...
متن کاملA Developmental Grasp Learning Scheme for Humanoid
A DEVELOPMENTAL GRASP LEARNING SCHEME FOR HUMANOID ROBOTS Bozcuoğlu, Asil Kaan M.Sc., Department of Computer Engineering Supervisor : Assoc. Prof. Dr. Erol Şahin Co-Supervisor : Asst. Prof. Dr. Erhan Öztop September 2012, 64 pages While an infant is learning to grasp, there are two key processes that she uses for leading a successful development. In the first process, infants use an intuitional...
متن کامل