Customize your FR3

plus (1) Franka Hand

The Hand is Franka Robotics' 2-finger gripper with exchangeable fingertips, fully integrated with the software of Franka Research 3, therefore plug-and-use. The fingertips can easily be changed and adapted to the objects to be grasped, e.g. by using 3D-printed fingertips.

 

plus (1) App Package for FR3

Apps are modular building blocks that can be combined into App Workflows to prototype robot behaviors rapidly. Each App contains a context menu where the user is guided interactively to enter parameters like speed and force, as well as to set robot poses by demonstration.

 

plus (1) RIDE

RIDE is the development interface for writing custom Apps and connecting third-party hardware and external resources. It's the ideal tool for customizing and extending the system’s capabilities.

 

plus (1) NVIDIA® Isaac Sim

NVIDIA Isaac Sim makes your development and testing better and faster, by creating photorealistic, physically accurate virtual environments. The scalable robotics simulation and synthetic data-generation tool is designed to seamlessly integrate with the latest robotic systems, including FR3. With such integration, you can replicate real-world scenarios and conduct comprehensive testing as well as analysis.

 

plus (1) Franka Toolbox for MATLAB

Franka Toolbox for MATLAB provides all necessary control options and signals from the FR3 robot, resulting in a quick, intuitive, and robust way for students and researchers to evaluate their algorithms – whether in the laboratory or classroom. In the toolbox, users will find a rich set of MATLAB® scripts and Simulink® blocks, and a collection of advanced demos, covering a wide array of possibilities for controlling the robot.

Find out more about Franka Toolbox for MATLAB

 

plus (1) Franka ROS 2

ROS 2, the successor to the widely acclaimed ROS, stands as a beacon of innovation, unlocking new possibilities for researchers and industry professionals alike. In keeping with our promise to support researchers and developers with robust and versatile tools to shape the future of robotics, we have released a brand-new Franka ROS 2 package. The comprehensive package offers a plethora of functionalities to enrich your FR3 robots with the full spectrum of opportunities unleashed by ROS 2.

Find out more about the possibilities with ROS 2

 

 

plus (1) Franka AI Companion

Franka AI Companion elegantly combines the hardware and software you need to streamline the setup and speed execution of your robotics and AI research work, while also offering NVIDIA® GPU-accelerated edge computational power and real-time 1kHz control.

Integration of GPU power with real-time control

Simplified research setup

Extended capabilities

Setup sharing

Find out more

Franka AI Companion-no_bg-1

Have questions about FR3 customization?

The right interface for each use case

Three access levels to the robot address different needs and skills, for the whole spectrum of robotics research.

DESK

The ease of use and minimal programming time makes Desk the most suitable interface for rapid prototyping, simple human robot interaction studies and demos.

See details

desk.470b822

RIDE

It enables researchers to fully integrate the Franka Robotics system into experimental setups, and exploit its integrated high performance controllers. It is also a great tool for teaching introductory robotics.

See details

ride.a041de5

FCI

FCI bypasses the robot’s Control to let researchers run their own control algorithms in external real-time capable PCs at 1 kHz. It is the ideal interface to explore low-level planning and control schemes.

See details

fci.7cc017e
  DESK RIDE FCI
Workflow-based programming using Apps    
Quick prototyping of experiments and demos    
Execution of robot tasks  
Development of customized Apps    
Connection of third-party hardware  
Connection of external resources  
1 kHz torque, position and velocity control    
1 kHz measurement of sensor signals and robot status    
Access to kinematic and dynamic robot model    
Integration with ROS and MATLAB & Simulink    

 

The reference robotic platform for research, globally

Start collaborations across a multitude of fields and compare results with a continuously growing network of Franka Robotics academic users.

 

Check the academic community's publications
map_static.051d4a8

Resources and Community

An open and global research ecosystem enabled by a powerful robotics platform for quicker time to results and publishing. Franka Research 3 is the reference platform to integrate existing research, share breakthroughs and collaborate on projects, replicate studies and promote papers with the community.

Join Franka Community

Learn with our tutorials

Get FCI documentation

Visit Franka Hub

From AI, ML, Robot Control and Motion Planning, to Manipulation and HRI.

For researchers at the cutting edge of AI & Robotics, FRANKA RESEARCH 3 provides a reference force-sensitive robotic platform and powerful control interfaces, for quick time to results and publishing. The platform also offers a low barrier to entry for researchers in search of a robot arm to automate their experimental setup, as well as a support for teaching robot control and automation courses.
  1. Guided Uncertainty Aware Policy Optimization
    nvidia-2
  2. Motion Reasoning for Goal-Based Imitation Learning
    Stanford.607c3ad
  3. RLBench: The Robot Learning Benchmark
    imperial_College_London.2148d25
  4. Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation
    VW_ML.c041e69
  5. Reinforcement Learning for Robotic Rock Grasp Learning in Off-Earth Space Environments
    aau_logo_en.e9e099d
  6. Learning Generalizable Coupling Terms for Obstacle Avoidance via Low-Dimensional Geometric Descriptors
    Edinburgh.6bddc1f
  7. 6-DOF Grasping for Target-driven Object Manipulation in Clutter
    nvidia-2
  8. Provably Safe and Efficient Motion Planning with Uncertain Human Dynamics
    mit.b24b824
  9. A novel adaptive controller for robot manipulators using active inference
    Delft-University.ac08994
  10. A Teleoperation Interface for Loco-manipulation Control of MOCA
    iit.5a95f42
  11. Planning Maximum-Manipulability Cutting Paths - RRT*-RMM
    birmingham.d5e7c04
  12. Online Replanning in Belief Space for Partially Observable Task and Motion Problems
    mit.b24b824
  13. Object-Centric Task and Motion Planning in Dynamic Environments
    Stanford.607c3ad
  14. Scaffold Learning: Learning to Scaffold the Development of Robotic Manipulation Skills
    Stanford.607c3ad
  15. Learning to Generate 6-DoF Grasp Poses with Reachability Awareness
    minnesota.793726f
  16. Learning Pregrasp Manipulation of Objects from Ungraspable Poses
    tsinghua1.d6c8814
  17. Interaction Force Computation Exploiting Environment Stiffness Estimation for Sensorless Robot Applications
    supsi.ba900b5
  18. Feedback-based Fabric Strip Folding
    aalto_university_logo.2effafc
  19. Describing Physics For Physical Reasoning: Force-based Sequential Manipulation Planning
    maxplanck.2fef5ef
  20. Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from Images
    maxplanck.2fef5ef
  21. A Capability-Aware Role Allocation Approach to Industrial Assembly Tasks
    Delft-University.ac08994
  22. A Framework for Human-Robot Interaction User Studies
    waterloo.4f899ab
  23. Search-Based Task Planning with Learned Skill Effect Models for Lifelong Robotic Manipulation
    cmu.6b59dfc
  24. A Shared Autonomy Reconfigurable Control Framework for Telemanipulation of Multi-arm Systems
    iit.5a95f42

Guided Uncertainty Aware Policy Optimization

Motion Reasoning for Goal-Based Imitation Learning

RLBench: The Robot Learning Benchmark

Constrained Probabilistic Movement Primitives for Robot Trajectory Adaptation

Reinforcement Learning for Robotic Rock Grasp Learning in Off-Earth Space Environments

Learning Generalizable Coupling Terms for Obstacle Avoidance via Low-Dimensional Geometric Descriptors

6-DOF Grasping for Target-driven Object Manipulation in Clutter

 

Provably Safe and Efficient Motion Planning with Uncertain Human Dynamics

 

 

A novel adaptive controller for robot manipulators using active inference

A Teleoperation Interface for Loco-manipulation Control of MOCA

Planning Maximum-Manipulability Cutting Paths - RRT*-RMM

 

 

 

 

Online Replanning in Belief Space for Partially Observable Task and Motion Problems

Object-Centric Task and Motion Planning in Dynamic Environments

 

 

 

 

Scaffold Learning: Learning to Scaffold the Development of Robotic Manipulation Skills

Learning to Generate 6-DoF Grasp Poses with Reachability Awareness

 

 

 

Learning Pregrasp Manipulation of Objects from Ungraspable Poses

Interaction Force Computation Exploiting Environment Stiffness Estimation for Sensorless Robot Applications

 

Feedback-based Fabric Strip Folding

 

 

 

 

 

 

 

Describing Physics For Physical Reasoning: Force-based Sequential Manipulation Planning

 

Deep Visual Reasoning: Learning to Predict Action Sequences for Task and Motion Planning from Images

 

A Capability-Aware Role Allocation Approach to Industrial Assembly Tasks

A Framework for Human-Robot Interaction User Studies

 

 

 

Search-Based Task Planning with Learned Skill Effect Models for Lifelong Robotic Manipulation

A Shared Autonomy Reconfigurable Control Framework for Telemanipulation of Multi-arm Systems