Customize Consent Preferences

We use cookies to help you navigate efficiently and perform certain functions. You will find detailed information about all cookies under each consent category below.

The cookies that are categorized as "Necessary" are stored on your browser as they are essential for enabling the basic functionalities of the site. ... 

Always Active

Necessary cookies are required to enable the basic features of this site, such as providing secure log-in or adjusting your consent preferences. These cookies do not store any personally identifiable data.

No cookies to display.

Functional cookies help perform certain functionalities like sharing the content of the website on social media platforms, collecting feedback, and other third-party features.

No cookies to display.

Analytical cookies are used to understand how visitors interact with the website. These cookies help provide information on metrics such as the number of visitors, bounce rate, traffic source, etc.

No cookies to display.

Performance cookies are used to understand and analyze the key performance indexes of the website which helps in delivering a better user experience for the visitors.

No cookies to display.

Advertisement cookies are used to provide visitors with customized advertisements based on the pages you visited previously and to analyze the effectiveness of the ad campaigns.

No cookies to display.

Onderwijs

Delft team enters robot picking challenge

Engineers from the TU Delft Robotics Institute and from the TU spinoff Delft Robotics are joining the Amazon Picking Challenge (Jun 29 – July 3, 2016). But first they’re testing their system at the RoboBusiness Europe event in Odense, Denmark (June 1-3, 2016).

The first Amazon picking challenge was in 2015. It proved to be a challenging event for robots engineers. Not only should their robots handle very diverse objects, ranging from T-shirts to books, but first they had to find and identify the items. After last year’s event, Delft engineers decided to join the competition.

Dr Carlos Hernández Corbato (Biorobotics Lab at the Mechanical, Maritime and Materials Engineering Faculty) and Kanter van Deurzen MSc. (Delft Robotics) assembled a team with all the experts they needed. Robot motion planners navigate the robot arm around obstacles, vision experts locate objects and support the navigation, and artificial intelligence experts process the images to recognise the dozens of different objects regardless of their position or their covering each other. And then there are the mechanical experts for the robot movements and the various grippers or suction cups needed to pick or place the items.

During the competition in Leipzig, robots equipped with grippers will autonomously retrieve a broad range of products from shelves and put them in a container (the pick task). In the second round, they have to retrieve products from the container and put them back on the shelves (the stow task).

For this, the team has built a flexible robot system based on industry standards. It features a robot arm with seven degrees of freedom, high-quality 3D cameras, and an in-house developed gripper. The team has integrated advanced software components based on state-of-the-art artificial intelligent techniques and robotics.

The team’s specialty, according to Van Deurzen, is the robustness of the system. “Often experimental robots are held together with tie wraps and duct tape,” he said. “We want to present a robot that can be used by the industry.” In their view, a robot system must be sufficiently reliable to improve aspects such as speed.

When asked if he wasn’t worried that pickers were going to lose their jobs to robots, Van Deurzen answered that the ever-shortening delivery times were pushing the packet industry to do the picking in the middle of the night.”It’s because that Amazon can’t get people for these jobs that they want to start using robots,” said Van Deurzen.

Team Delft Proposal

Amazon Picking Challenge 2015

Redacteur Redactie

Heb je een vraag of opmerking over dit artikel?

delta@tudelft.nl

Comments are closed.