scholarly journals Robotic Pick and Place Using Two-Finger Touch Sensing

2019 ◽  
Vol 8 (9) ◽  
pp. 70-77
Keyword(s):  
Shape Recognition ◽  
Recognition Algorithm ◽  
Pick And Place ◽  
Finger Touch ◽  
Multiple Scenarios ◽  
Usual Position

Pick and place robots are gaining popularity in the current era due to their ability to handle objects of varying sizes and dimensions. Research to improve the efficiency and design of these manipulators is currently the need of the hour. In this, a new and novel mechanism has been introduced; it is called Blind man Mechanism that is to find the object and to find shape of it. Shape Recognition algorithm to improve the hold on the object. It involves analysis of working of the human thumb and shape of the object. The Blind man mechanism allows object to be found, even when it is not in its usual position. It includes details about the thumb analysis to find an object, which further includes shape recognition of different objects in multiple scenarios also results for whether the object has been found or not. If found so verify for a pick place robot using MATLAB results

scholarly journals Robotic pick-and-place of novel objects in clutter with multi-affordance grasping and cross-domain image matching

2019 ◽  
pp. 027836491986801 ◽  
Author(s):  
Andy Zeng ◽  
Shuran Song ◽  
Kuan-Ting Yu ◽  
Elliott Donlon ◽  
Francois R. Hogan ◽  
...  
Keyword(s):  
Recognition Algorithm ◽  
Training Data ◽  
Success Rates ◽  
Cluttered Environments ◽  
Cross Domain ◽  
Classification Framework ◽  
Wide Range ◽  
Pick And Place ◽  
Additional Data Collection ◽  
Novel Objects

This article presents a robotic pick-and-place system that is capable of grasping and recognizing both known and novel objects in cluttered environments. The key new feature of the system is that it handles a wide range of object categories without needing any task-specific training data for novel objects. To achieve this, it first uses an object-agnostic grasping framework to map from visual observations to actions: inferring dense pixel-wise probability maps of the affordances for four different grasping primitive actions. It then executes the action with the highest affordance and recognizes picked objects with a cross-domain image classification framework that matches observed images to product images. Since product images are readily available for a wide range of objects (e.g., from the web), the system works out-of-the-box for novel objects without requiring any additional data collection or re-training. Exhaustive experimental results demonstrate that our multi-affordance grasping achieves high success rates for a wide variety of objects in clutter, and our recognition algorithm achieves high accuracy for both known and novel grasped objects. The approach was part of the MIT–Princeton Team system that took first place in the stowing task at the 2017 Amazon Robotics Challenge. All code, datasets, and pre-trained models are available online at http://arc.cs.princeton.edu/

Implementation and Comparison of a Fast Shape Recognition Algorithm using Different FPGA Platforms

2019 ◽  
Author(s):  
Andre Borja ◽  
Guillaume Varengues ◽  
Luis-Miguel Procel ◽  
Lionel Trojman ◽  
German Arevalo ◽  
...  
Keyword(s):  
Shape Recognition ◽  
Recognition Algorithm
Sign in / Sign up

Export Citation Format

Share Document