Robohub.org
 

Grasping with robots – which object is in reach?

by
17 August 2014



share this:

This post is part of our ongoing efforts to make the latest papers in robotics accessible to a general audience.

Imagine a robot reaching for a mug on the table, only to realize that it is too far, or that it would need to bend its arm joint backwards to get there. Understanding which objects are within reach and how to grasp them is an essential requirement if robots are to operate in our everyday environments. To solve this problem, a recent Autonomous Robots paper by Vahrenkamp et al. proposes a new approach to build a comprehensive representation of the capabilities of a robot related to reaching and grasping.

The “manipulability” representation shown below allows the robot to know where it can reach in 6D with its right arm. That means it knows which x,y,z positions it can reach, as well as the orientation of the robot hand that is best for manipulation. The representation takes into account constraints due to joints in the arm. The manipulability is encoded by color (blue: low, red: high).

armar4_rightarm6

A cut through one of these vector clouds looks like this.

manip_armar2

In addition to single handed grasping, the authors discuss how the approach can be extended to grasping with two arms. Experiments were run in simulation on the humanoid robots ARMAR-III and ARMAR-IV.

And in case you want to try this at home, there is an open source version of this work here.

For more information, you can read the paper Representing the robot’s workspace through constrained manipulability analysis (Nikolaus Vahrenkamp and Tamim Asfour, Autonomous Robots – Springer US, July 2014) or ask questions below!



tags:


Autonomous Robots Blog Latest publications in the journal Autonomous Robots (Springer).
Autonomous Robots Blog Latest publications in the journal Autonomous Robots (Springer).





Related posts :



Team builds first living robots that can reproduce

AI-designed Xenobots reveal entirely new form of biological self-replication—promising for regenerative medicine.
02 December 2021, by

Exploring ROS2 using wheeled Robot – #3 – Moving the robot

In this post you’ll learn how to publish to a ROS2 topic using ROS2 C++. We are moving the robot Dolly robot, simulated using Gazebo 11.
30 November 2021, by

An inventory of robotics roadmaps to better inform policy and investment

Silicon Valley Robotics in partnership with the Industrial Activities Board of the IEEE Robotics and Automation Society, is compiling an up to date resource list of various robotics, AIS and AI roadmaps, national or otherwise.
29 November 2021, by

Robots can be companions, caregivers, collaborators — and social influencers

People are hardwired to respond socially to technology that presents itself as even vaguely social. While this may sound like the beginnings of a Black Mirror episode, this tendency is precisely what allows us to enjoy social interactions with robots and place them in caregiver, collaborator or companion roles.
26 November 2021, by

Interview with Tao Chen, Jie Xu and Pulkit Agrawal: CoRL 2021 best paper award winners

The award-winning authors describe their work on a system for general in-hand object re-orientation.
24 November 2021, by
ep.

341

podcast

How Simbe Robotics is Innovating in Retail, with Brad Bogolea

Brad Bogolea discusses the innovation behind Tally, the autonomous robot from Simbe Robotics. Tally collects real-time analytics inside retail stores to improve the customer shopping experience, as well as the efficiency of managing the store.
23 November 2021, by





©2021 - ROBOTS Association


 












©2021 - ROBOTS Association