Robot vision-based object grasping

Main functionalities

Object grasping from RGB images with the object and target detection tool, executed by a collaborative robot (Franka Emika).

Technical specifications

Object grasping from RGB images with the object and target detection tool, executed by a collaborative robot (Franka Emika).

Inputs and outputs

The annotated image stream can be inspected using rqt_image_view or rviz (select one of the topics /opendr/image_grasp_pose_annotated or /opendr/image_mask_annotated) or rostopic echo /opendr/object_detected This node also publishes a VisionInfo message in /opendr/object_catagories containing the name of a ROS parameter on the server where can be found the correspondance between class ids and class names.

Formats and standards

Linux Ubuntu 20.04 LTS

ROS1: OpenDR v2.0,  pytorch 1.9, ros-noetic-moveit, ros-noetic-libfranka, Python 3.8
ROS2: OpenDR v2.0, pytorch 1.9, ros-foxy-moveit, ros-foxy-libfranka, Python 3.8

All dependencies will be installed with the OpenDR toolkit and/or installation instructions are provided

Training material

undefined

Owner (organization)

undefined

Documents
Subscribe to newsletter

Please subscribe to our mailing list to be the first one informed about the new open calls, events and other hot news!


    Please check if the email you entered is correct
    All done!

    Your have successfully subscribed to Trinity newsletter.