In the field this year’s Sensing & Mapping task had an additional task requiring robots to remove 5 cans and place them outside the crop on the headland. Carbonite won because it managed to deliver all cans to the headland, Bullseye became second with 4 cans and CERES II third.
In the sensing and mapping task, the robots scout for five weeds and five cans in the field. It was one of the most difficult tasks in the 2022 competition. Only 3 teams managed to earn points. Winner FloriBot detected six out of ten. Kamaro became second and CERES II third.
In the Field Navigation task, CERES II managed to hit no plants and drove 50 meters in the field within the limited time of 3 minutes. HELIOS evo won the second prize. FloriBot finished in third place.
The winner of the Navigation task in simulation of the international Field Robot event is Carbonite. They managed to drive 142 meters in a virtual field in 3 minutes, with damaging 13 plants. The second place went to CERES II, and Kamaro came in third.
The Field Robot Event is a partner of the DLG Feldtage event. The DLG is streaming this event live on its digital platform.
Information on how to participate:
• Attending this virtual event is free of charge and requires a simple registration on DLG’s digital platform.
• The link to the registration is available here.
Have a look at the tasks, the rules have been updated! They are also available as a pdf in the download section.
For all teams that want to participate in the 2022 event, we organise regularly Zoom meetings. Next: June 8th from 16:00-17:00.
We will talk about the organisation, tasks, simulation environment and have a Q&A.
The Zoom meeting link will be sent to the Field Robot Event mailing list subscribers.
We have published new rules for your own robot model used in simulation. Have a look in 0. Hybrid event under Contest
In our first teams meeting we explained the virtual part of the event. A pdf of the presentation can be found under Downloads.
For all teams that want to participate in the 2022 event, we will organise a Zoom meeting on Friday, March 4th from 14:00-16:00.
Content:
The Zoom meeting link will be sent to the Field Robot Event mailing list subscribers.
The CLAAS foundation will again in 2022 financially support new teams coming to the event! You can apply for the support directly on their website.
Thanks at lot already to Sylvia Looks from the CLAAS foundation!
In the meanwhile we finalised the proceedings from 2021. For those of you who want to get started with the preparation for 2022, please have a look at the team paper and descriptions in the proceedings how they started and were more or less successful with their chosen strategies. The proceedings are a good preparation because in 2022 there will be similar challenges like described in task 1, task 3 and of course task 5 from 2021. More details will be soon on this website.
We are happy to inform you that we will conduct a Field Robot Event in 2022. Although the pandemic situation continues we do not want to give up. After some discussions we want to offer a hybrid version of the event: a mix of a virtual and field contest! We also will return to the DLG Field Days and prepare everything to be controlled from and on the DLG site. Therefore, robot teams are invited to participate without travelling (virtual event) or come physically as usual together with your own robot (field event). More details will be available soon. Save the date: 14th to 16th of June 2022 in Kirschgartshausen/Mannheim, Germany.
Due to the unpredictable pandemic situation there will be perhaps special rules coming up or even a cancellation. Therefore, please don’t blame us for any inconveniences.
Now available: All proceedings of previous Field Robot Events!
See the Downloads tab.
One of the goals of the field robot event is to learn from each other. We are therefore very happy with Kamaro’s initiative to make some of their software public. We expect this to boost our community and encourage collaboration and exchange between teams. It also helps aspiring participants to get started.
Kamaro has published their winning code for crop row navigation and their code for object detection using deep learning.
Which team is next?