Tasks Field Robot Event 2018

The Field Robot Event 2018 will be held at the DLG Feldtage in Bernburg-Strenzfeld, Germany. For the event five tasks are to be completed. The first four will count for the overall contest winner 2018, the last task will be awarded separately. Below each task will be shortly explained. For additional information see: http://www.fieldrobot.com/event/index.php/tasks/.

 

 

Task 1 – Basic Navigation 

For this task the robots are navigating autonomously. Within three minutes, the robot has to navigate through long curved rows of maize plants (picture 1). The aim is to cover as much distance as possible. On the headland, the robot has to turn and return in the adjacent row. There will be no plants missing in the rows. This task is all about accuracy, smoothness and speed of the navigation operation between the rows.

 

 

Task 2 – Advanced Navigation

For this task the robots are navigating autonomously. Under real field conditions, crop plant growth is not uniform. Furthermore, sometimes the crop rows are not even parallel. We will approach these field conditions in the second task. No large obstacles in the field, but more challenging terrain in comparison to task 1.

 

The robots shall achieve as much distance as possible within 3 minutes while navigating between straight rows of maize plants, but the robots have to follow a certain predefined path pattern across the field (picture 2). Additionally at some locations, plants will be missing (gaps) at either one or both sides with a maximum length of 1 meter. There will be no gaps at row entries.

 

The robot must drive the paths in given order. The code of the path pattern through the maize field is done as follows: S means START, L means LEFT hand turn, R means RIGHT hand turn and F means FINISH. The number before the L or R represents the row that has to be entered after the turn. Therefore, 2L means: Enter the second row after a lefthand turn, 3R means: Enter the third row after a right hand turn. The code for a path pattern for example may be given as: S ‐ 3L ‐ 2L ‐ 2R ‐ 1R ‐ 5L ‐ F.

 

 

Task 3 – Selective Sensing

For this task, the robots are navigating autonomously. The robots shall detect weed patches represented by red and blue golf tees (picture 3). Task 3 is conducted on the area used in task 2 with straight rows. Nevertheless, simple row navigation is required and the robot has to turn on the headland and return in the adjacent row. There will be nine (9) weed patches in total with three patches on each of the first three between row spacing. The end of the third row spacing is the finish line for this task 3.

 

The detection of the weed patch with a higher number of red tees shall be indicated by one loud acoustic signal while the detection of the weed patch with a higher number of blue tees must be confirmed by two consecutive and loud acoustic signals.

 

 

 

Task 4 – Soil-Engaged Weeding

For this task, the robots are navigating autonomously. The robots shall remove weeds from three (3) weed patches represented by red golf tees (picture 4). Probably a soil engaged active tool is needed to succeed in this task. In order to minimize the used energy the tool should be active only on the weed spots. Task 4 is conducted on the area used in task 2 with straight rows. Nevertheless, no specific path sequence will be given as in task 2 and the robot has to turn on the headland and return in the adjacent row. The three weed patches will be placed one on each of the three first row spacing. Thus, the end of the third row spacing is the finish line for this task.

 

Each tee removed from the weed patch counts, each tee moved to the headland outside the crop area counts more and each tee collected on the robot and transferred to the end of the third row spacing counts most. Tillage outside the weed patches will be punished.

 

 

 

Task 5 – Freestyle

Teams are invited to let their robots perform a freestyle operation. Creativity and fun are required for this task as well as an application‐oriented performance. One team member has to present the idea, the realization and perhaps to comment the robot’s performance to the jury and the audience. The freestyle task should be related to an agricultural application. Teams will have a time limit of five minutes for the presentation including the robot’s performance.

The task 5 is optional and will be awarded separately. We are currently brainstorming about what task we want to perform and how we are going to develop it.