Autoplant: autonomous planting machine getting closer to reality in Sweden

Developed by Luleå Technical University and Bracke Forest

Fri 27 Jan 23


Autoplant, an autonomous planting machine project, has taken a step closer to reality with the first complete machine test in Bräcke, Sweden. Developed by Luleå Technical University and Bracke Forest, the machine is capable of ground preparation and planting without human intervention, promising exciting developments for forest regeneration.

Despite the success of field tests, it will be some time before the machine hits the market. “The field tests show great potential for an exciting development of technology for forest regeneration,” says Magnus Bergman, technical manager at SCA Forests and chairman of the Autoplant project.

Klas-Håkan Ljungberg… it has been challenging to develop such an advanced head with such a low weight.

The development of a lightweight planting head has been a significant challenge. “It has been challenging to develop such an advanced head with such a low weight,” says Klas-Håkan Ljungberg, CEO at Bracke Forest. “We are proud that our new prototype just weighs 200 kg – 10% of the weight of our other planting heads.”

Bracke Forest has presented several prototypes for different types of terrain. Precision and energy consumption have been important factors in the work of development. Analyses have been made to look at the time consumption on different soil and terrain types.

A key obstacle has been making the machine choose a suitable planting spot and bring the planting head to that location. To address this, Skogforsk developed a ‘spot chooser’ that uses an obstacle map to find the optimal planting spots.

Luleå Technical University has been working with image analysis and AI to recognize stumps, stones, and slashes with a stereo camera in real-time to create the obstacle map. However, there is still much work to be done in dealing with different weather, light, terrain, and soil conditions.

Route planning is done using a solution called Pathfinder.

It’s based on data from the harvester and different geodata. Choosing the right tree species for the right spot, which areas to avoid, how dense it should be planted, and the routing are tasks for the Pathfinder. Different route suggestions are presented depending on whether the machine should pick up the plants or if the plants are delivered, such as by a drone.

The machine must also be able to avoid unexpected obstacles, something that the Royal Institute of Technology is working on. Overall, the project has demonstrated great potential for technological advancements in forest regeneration.


Related Articles