**Background**
The Autonomous River Cleanup (ARC) is a student-led initiative supported by the Robotic Systems Lab and aims to remove waste from rivers.
By joining ARC, you’ll work on the Mobile Autonomous Recycling Container (MARC), which uses two robotic arms to sort waste by material (plastic, metal, glass, etc.).
Given the limited space inside the container, we currently use collision-free path planners for robot control, running on the workstation’s CPU.
Since these planners are computationally intensive, this approach is not feasible for real-time application. Therefore, we rely on precomputed trajectories.
**Thesis Description**:
To enable real-time collision-free path planning, we aim to migrate our planning pipeline to cuRobo, a CUDA-accelerated path planning library [1].
With this approach, we want to overcome the limitations of using pre-computed trajectories, increase computation speed, and find smoother trajectories.
[1] Nvidia, cuRobo: CUDA Accelerated Robot Library, https://curobo.org/, last access: 05.09.2024
**Background** The Autonomous River Cleanup (ARC) is a student-led initiative supported by the Robotic Systems Lab and aims to remove waste from rivers. By joining ARC, you’ll work on the Mobile Autonomous Recycling Container (MARC), which uses two robotic arms to sort waste by material (plastic, metal, glass, etc.). Given the limited space inside the container, we currently use collision-free path planners for robot control, running on the workstation’s CPU. Since these planners are computationally intensive, this approach is not feasible for real-time application. Therefore, we rely on precomputed trajectories.
**Thesis Description**: To enable real-time collision-free path planning, we aim to migrate our planning pipeline to cuRobo, a CUDA-accelerated path planning library [1]. With this approach, we want to overcome the limitations of using pre-computed trajectories, increase computation speed, and find smoother trajectories.
[1] Nvidia, cuRobo: CUDA Accelerated Robot Library, https://curobo.org/, last access: 05.09.2024
During your time at ARC, you will do the following:
- Literature review on GPU accelerated and collision-free path planning
- Familiarization with the robot interface of Neura Robotics
- Modeling of the collision space in Omniverse
- Implementation of cuRobo in the existing code framework
- Comparison and evaluation of different planners
During your time at ARC, you will do the following:
- Literature review on GPU accelerated and collision-free path planning
- Familiarization with the robot interface of Neura Robotics
- Modeling of the collision space in Omniverse
- Implementation of cuRobo in the existing code framework
- Comparison and evaluation of different planners
Ideally, you already have the following skills or are eager to learn them:
- Proficiency in Python, ROS, and version control
- Experience in working with an existing code framework
- Autonomous working style
- Experience with Isaac Sim
- Experience with path-planning algorithms
Ideally, you already have the following skills or are eager to learn them:
- Proficiency in Python, ROS, and version control
- Experience in working with an existing code framework
- Autonomous working style
- Experience with Isaac Sim
- Experience with path-planning algorithms
Please send your CV, TOR and a short motivational statement to Jonas Stolle (jstolle@ethz.ch) and Emre Elbir (eelbir@ethz.ch)
Please send your CV, TOR and a short motivational statement to Jonas Stolle (jstolle@ethz.ch) and Emre Elbir (eelbir@ethz.ch)
