UR5+10 Dual Arm System

Technical Details

Organisational Details

Sponsor: Federal Ministry for Economic Affairs and Climate Action
European Union
Federal Ministry of Education and Research
Grant number: Grant 50RA2126A (DFKI) and 50RA2126A (Uni) of the Federal Ministry for Economic Affairs and Climate Action Grant no. 870142 of the European Commission Grant no. 19543 of the Federal Ministry of Education and Research
Application Field: Assistance- and Rehabilitation Systems
Logistics, Production and Consumer
Space Robotics
Related Projects: UPLINX
Cross-site qualification program Machine Learning for practice (01.2018- 12.2019)
Learning from Causal Physical World Models (07.2022- 06.2024)
Multipurpose robotics for mAniPulation of defoRmable materIaLs in manufacturing processes (04.2020- 07.2023)
This system is used for teaching students.

System description

Manipulation lab (Photo: Alexander Fabisch, DFKI GmbH)
Robot and control computer (Photo: Alexander Fabisch, DFKI GmbH)

Our UR5+10 dual-arm system is a versatile platform designed to explore advanced robotic grasping and manipulation tasks. The system combines multiple robot arms, hands, grippers, and a motion capture system to provide a powerful tool for experimentation.

The centerpieces of the system are the Universal Robot 5 and 10 arms (CB3 series). Together, they provide the flexibility to explore a wide range of manipulation tasks.

The testbed features various robotic hands to suit different grasping tasks. We currently have two Prensilia Mia hands (left and right). These are compact and lightweight prosthetic hands with five fingers that can perform basic grasps and measure grasping forces. Seed Robotics' RH8D hand boasts 19 degrees of freedom for intricate manipulation, while the simple yet effective Robotiq 2F-140 grippers provide two-fingered grasping.

A Qualisys motion capture system, utilizing multiple cameras, precisely tracks object or human motion within the testbed or allows us to analyze and refine robot movements.

This dual-arm manipulation testbed is used for research in imitation learning, reinforcement learning, and grasp planning.

Back to the list of robot systems
last updated 07.11.2023