Register now After registration you will be able to apply for this opportunity online.
This opportunity is not published. No applications will be accepted.
Tree Manipulation with an Autonomous Harvester
We would like to develop an approach to solve the planning/control aspect of robotic tree manipulation, with the goal of using our autonomous tree harvester, Harveri, for robotic forestry missions. The project can be tailored to your needs/wishes.
Efficient forest management is of interest to both public and private sectors. Forests provide humans with raw materials and are a great ally in the fight against climate change. However, the forestry sector faces a significant labor shortage which is the problem we try to address with autonomous robots. Recently a small autonomous tree harvester, Harveri, has been developed at RSL [1], as an experimental platform for robotic precision tree harvesting.
We aim to use Harveri for tree manipulation tasks. The robot should be able to pick up the wood log on the ground and pile it on its trailer autonomously in an outdoor environment [2]. We would like to develop an approach to solve the planning/control aspect of tree harvesting. Depending on the progress of the project, real-world tests might be carried out. The project can be tailored to your needs/wishes.
[1] Jelavic, E., Kapgen, T., Kerscher, S., Jud, D., & Hutter, M. Harveri: A Small (Semi-) Autonomous Precision Tree Harvester.
[2] https://www.youtube.com/watch?v=sgveJUP-hJs
Efficient forest management is of interest to both public and private sectors. Forests provide humans with raw materials and are a great ally in the fight against climate change. However, the forestry sector faces a significant labor shortage which is the problem we try to address with autonomous robots. Recently a small autonomous tree harvester, Harveri, has been developed at RSL [1], as an experimental platform for robotic precision tree harvesting.
We aim to use Harveri for tree manipulation tasks. The robot should be able to pick up the wood log on the ground and pile it on its trailer autonomously in an outdoor environment [2]. We would like to develop an approach to solve the planning/control aspect of tree harvesting. Depending on the progress of the project, real-world tests might be carried out. The project can be tailored to your needs/wishes.
[1] Jelavic, E., Kapgen, T., Kerscher, S., Jud, D., & Hutter, M. Harveri: A Small (Semi-) Autonomous Precision Tree Harvester.
[2] https://www.youtube.com/watch?v=sgveJUP-hJs
Identify the key challenges and develop a suitable approach (e.g. RL, classical, combination)
Simulation environment development
Implementation and validation in simulations
Optional: real-world evaluation
Identify the key challenges and develop a suitable approach (e.g. RL, classical, combination)
Simulation environment development
Implementation and validation in simulations
Optional: real-world evaluation
Highly motivated for the topic
Programming experience (C++/Python)
Experience in robotic manipulation, reinforcement learning, or field robotics is a plus
Highly motivated for the topic
Programming experience (C++/Python)
Experience in robotic manipulation, reinforcement learning, or field robotics is a plus
Send an email with your CV and transcript to:
Edo Jelavic: jelavice@ethz.ch
Pascal Egli: pasegli@ethz.ch
Fang Nan: fannan@ethz.ch
Send an email with your CV and transcript to:
Edo Jelavic: jelavice@ethz.ch Pascal Egli: pasegli@ethz.ch Fang Nan: fannan@ethz.ch
