Purpose -When designing hardware and algorithms for robotic manipulation and grasping, sensory information is typically needed to control the grasping process. This paper presents an overview of the major grasping and manipulation approaches and the more common hardware used to obtain the necessary sensory information. Design/methodology/approach -This paper presents an overview of tactile sensing in intelligent robotic manipulation. The history, the common issues, and applications are reviewed. Sensor performance is briefly discussed and compared to the human tactile sense. Advantages and disadvantages of the most common sensor approaches are discussed. Some examples are given of sensors that are widely available as of today. Eventually, some examples of the state-of-the-art in tactile sensing application are presented. Findings -Although many sensor technologies and strong theoretical models have been developed, there is still much left to be done in intelligent grasping and manipulation. This is partly due to the youth of the field and the complex nature of safe control in uncertain environments. Even though there are impressive results when it comes to specific examples of advanced manipulation, there seems to be room for great improvements of hardware and especially algorithms when it comes to more generic everyday domestic tasks. Originality/value -This paper presents a review of sensor hardware while also giving a glimpse of the major topics in grasping and manipulation. While better hardware of course is desirable, the major challenges seem to lie in the development and application of grasping and manipulation algorithms.

We present a method for automatic grasp generation based on object shape primitives in a Programming by Demonstration framework. The system first recognizes the grasp performed by a demonstrator as well as the object it is applied on and then generates a suitable grasping strategy on the robot. We start by presenting how to model and learn grasps and map them to robot hands. We continue by performing dynamic simulation of the grasp execution with a focus on grasping objects whose pose is not perfectly known.

No abstract

No abstract