An MRSD team was selected for the finals in the Amazon Picking Challenge in Leipzig, Germany and and came in 7th out of 16.

picking

The 2016 Amazon Picking Challenge (the “Challenge”) is a skill Challenge sponsored by Amazon Robotics LLC (the “Sponsor”) aimed to strengthen the ties between the industrial and academic robotic communities and promote shared and open solutions to some of the big problems in unstructured automation. The Challenge will task entrants with building their own robot hardware and software (collectively, a “Robot”) that can attempt simplified versions of the general task of picking items from shelves. Selected finalists (as outlined below) will have their Robots presented with a stationary and lightly populated inventory shelf and be asked to pick a subset of the products from the shelf and put them in a tote and also stow products into the shelf. The Challenge combines object recognition, pose recognition, grasp planning, compliant manipulation, motion planning, task planning, task execution, and error detection and recovery. The Robots will be scored by how many items are picked and stowed in a fixed amount of time. Entrants will share and disseminate their approach to improve future Challenge results and industrial implementations

Read more here