SiROP
Login   
Language
  • English
    • English
    • German
Home
Menu
  • Login
  • Register
  • Search Opportunity
  • Search Organization
  • Create project alert
Information
  • About SiROP
  • Team
  • Network
  • Partners
  • Imprint
  • Terms & conditions
Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.

GPU-based Online Trajectory Generation for a Robot Manipulation

Integrate cuRobo, a CUDA-accelerated robot motion generation library from NVIDIA on a Franka Emika Panda arm and a faive robot hand. Benchmark its performance and demonstrate the functionality of this library by executing a series of predefined tasks that incorporate inverse kinematics, collision checking and trajectory generation for a combined system of the robot arm and the robot hand. Check out this video: https://www.youtube.com/watch?v=Ux9tFBRLR-A and the following websites: https://curobo.org/ https://www.faive-robotics.com/ for information

Keywords: robotic arms, dexterous manipulation, kinematics, collision checking, trajectory generation

  • **Possible Work Packages** Get familiar with the architecture of the faive robotic hand, libfranka, and cuRobo Setup and integration of the cuRobo for the combined setup Develop interfaces to showcase trajectory generation and collision avoidance Design and conduct experiments to validate and benchmark system performance and solve defined challenges **Requirements** Capable of both working independently and collaborating in a team Have taken Robot Dynamics or a similar class Keen to learn more about trajectory generation for robots Proficiency in C/C++ and Python Experience in Pytorch/CUDA/Kinematics is a plus

    **Possible Work Packages**

    Get familiar with the architecture of the faive robotic hand, libfranka, and cuRobo

    Setup and integration of the cuRobo for the combined setup

    Develop interfaces to showcase trajectory generation and collision avoidance

    Design and conduct experiments to validate and benchmark system performance and solve defined challenges

    **Requirements**

    Capable of both working independently and collaborating in a team

    Have taken Robot Dynamics or a similar class

    Keen to learn more about trajectory generation for robots

    Proficiency in C/C++ and Python

    Experience in Pytorch/CUDA/Kinematics is a plus

  • Not specified

  • Barnabas Gavin Cangan, gavin.cangan@srl.ethz.ch, Soft Robotics Lab, D-MAVT Prof. Dr. Robert Katzschmann, rkk@ethz.ch, Soft Robotics Lab, D-MAVT

    Barnabas Gavin Cangan, gavin.cangan@srl.ethz.ch, Soft Robotics Lab, D-MAVT

    Prof. Dr. Robert Katzschmann, rkk@ethz.ch, Soft Robotics Lab, D-MAVT

Calendar

Earliest start2023-11-15
Latest end2024-03-31

Location

Soft Robotics Lab (ETHZ)

Labels

Semester Project

Topics

  • Information, Computing and Communication Sciences
  • Engineering and Technology

Documents

NameCommentSizeActions
20231109-cuRobo-TrajectoryGeneration.pdf1.3MBDownload
SiROP PARTNER INSTITUTIONS