RFLib

RFLib is a foundational library for hardware interface, cuda interface (e.g. Ops). It is a part of the RobotFlow project.

Installation

This line will install with ops, it will take a few minutes.

pip install -e .

If you want to make a quick install, because you only want to use image library or hardware drivers, you can:

RFLIB_WITH_OPS=0 pip install -e .

Foundational Library/Drivers for

Image Utils: Docs

1. 2D Vision: For this part, we build upon mmcv.
2. 3D Vision
3. Multi-modal Perception

CNN Utils Docs

For this part, we build upon mmcv.

Hardware Interface

We have tested with:

1. Robot
   • mobile dual arm
     • Tobor: tutorial
   • robot arm
     • Flexiv Rizon 4: tutorial
     • Franka Emika Panda: tutorial
     • UR5: tutorial
     • Rokae xMate pro 3: tutorial
   • robot hand
     • Robotiq 85: tutorial
     • AG 95: tutorial
     • DH-3: tutorial
     • JQ3: tutorial
     • Allegro: tutorial
   • agv
     • Sunspeed: tutorial
2. Sensors
   • camera
     • RealSense D415/D435/L515: tutorial
     • Azure Kinect: tutorial
   • tactile
     • RFDigit: tutorial

Projects in RobotFlow

Software

• RFLib: RobotFlow foundational library for Robot Vision, Planning and Control.
• RFVision: RobotFlow vision-related toolbox and benchmark.
• RFMove: RobotFlow planning toolbox.
• ReinForce: RobotFlow reinforcement learning toolbox.
• RFController: RobotFlow controller toolbox.
• rFUniverse: A Unity-based Multi-purpose Simulation Environment.
• RFBulletT: A Pybullet-based Multi-purpose Simulation Environment.
• RF_ROS: ROS integration. Both ROS1 and ROS2 are supported.
• RobotFlow: The barebone of the whole system. It organizes all the functionalities.

Hardware

• RFDigit: A Customized Digit Tactile Sensor.

Open Ecosystem

• N-D Pose Annotator: support both rigid and articulated object pose annotation.
• model format converter: URDF and related model format converter.