A robotic dog that autonomously waters plants
A group of tech enthusiasts in Italy known as B-AROL-O has developed a robotic dog that autonomously tends to plants by activating an onboard sprinkler system. Its technology facilitates plant monitoring by distinguishing between healthy and poor leaf conditions. More developments are needed before it can be applied practically in agriculture, but even great ideas are sometimes born small.
The B-AROL-O Team is a group of friends who work or have previously worked for an Italian company in the packaging industry. Barolo is also a wine region. The dog is called FREISA, an acronym for Four-legged Robot Ensuring Intelligent Sprinkler Automation. With this new integration of robotics, AI, and agriculture, the team says it aims to introduce a new era of smart gardening solutions.
The robotic dog works by locomoting using its four limbs. A camera module is used to observe the surrounding environment. Plants are evaluated using AI and watered by FREISA if they look too dry. “Our robot demonstrates good abilities in identifying a target plant, navigating towards it, and examining its leaves before precisely adjusting its position to efficiently water the plant”, Gianluca Teti, member of the group, says. Initially, the team contemplated using vineyards as a setting for the dog. However, this choice presented certain challenges. Primarily, the vine leaves
grow at a height of at least 40 cm from the ground, significantly higher than the intended height for the dog robot
they planned to employ.
Also, the terrain where vines are typically cultivated, notably in Italy, tends to be uneven, posing navigation
difficulties for a robot. Therefore, the team chose a more controlled environment – a small garden with tomato plants. But, the team says, this decision does not rule out the possibility of continuing the project and potentially introducing the robotic dog to vineyards in the future.
The team’s objective was to assess a plant’s condition by analysing the state of its leaves and stems. The team had to
collect a vast array of images and then train various networks and models. The team believes that Quadruped Legged Platforms are ideally suited for a range of unstructured outdoor applications due to the ability to navigate complex terrain. They ruled out creating a robot running on wheels and tracks, noting that it would be poor at clearing obstacles over rough ground. The group also considered a quadcopter but felt its battery and payload would be poor. The team built the robot for less than US $500, using open-source software. FREISA won the Grand Prize in the 2023 OpenCV AI Competition. The team has already identified potential improvements such as using the OAK-D Lite’s stereo camera to estimate a target’s distance. (Source: Future Farming).
Siloking: Etruck now bigger and better
Kverneland’s latest news is about the updates to the Siloking diet feeder range include a stepless gearbox for the augers on the trailed models, a revamped version of the battery powered Etruck, while the diesel-fuelled machines can now run on hydrotreated vegetable oil (HVO).
The Variospeed stepless gearbox on the TrailedLine two and three auger mixers is said to take a lot less torque to get
things moving and therefore reduce horsepower demands. Three predefined auger speeds can be selected for cutting, mixing and feeding out with the push of a button, along with the option of remote activation from the machine loading the mix.
On the self-propelled Etruck capacity has been increased by swapping the single auger body for a twin which can
handle loads ranging from 12 to 20 m3. The lead-acid battery pack has been changed to one with lithium ion phosphorous capable of two to four mixes without recharging and projected lifespan of 3 000 to 5 000 full charge cycles. Prices start at £188 000 (R4,5 million) for the 12 m3 version. Back in 2019, Siloking announced it had sold over 100 of the battery powered feeders which were shown as a concept at EuroTier in 2016. Then the hopper capacity was 8 m3, increasing to 10 and 14 m3 in 2017. (Source: profi).
WeLASER: Another step closer to pesticide-free agriculture
After three years of work, an international partnership involving eight EU countries has released a precision weeding tool proving that herbicidefree agriculture is at hand.
The partnership formed by research centres, universities, private companies, and farmers’ organisations from Spain, Germany, Denmark, France, Poland, Belgium, Italy, and the Netherlands has completed the first stage of the development of the precision weeding prototype tool using laser to eradicate weeds. The aim is to improve productivity and competitiveness of crops, while eliminating health risks and the adverse environmental effects of chemicals.
The prototype includes an autonomous vehicle that drives through the crop and is equipped with an advanced detection system based on artificial intelligence (AI) through image acquisition and data processing, which allows it to distinguish and localise the centre of growth of the weed to be eradicated. Once targeted through the scanner, it
directs the high-powered fibre laser source to that meristem. This fast modulation concept allows precise energy pulses to be directed for highly efficient weed treatment. Data is managed by a cloud computing architecture and the system includes the IoT technology.
Although this project is currently concluding this first phase of development, further work will be needed, for example, to reduce the time required to work in the field, to make the prototype easier to handle and connect, and to reduce production costs to achieve a marketable model on the market. Beyond the development of the prototype, this project has resulted in the development of different innovations with multiple applications including:
• A high-power fibre laser source for the control of adventitious weeds through precise energy pulses.
• An innovative pump and cooling concept that minimises the energy demand of the laser for the weeding process.
• An improved power supply system for autonomous robotic platforms.
• An intelligent navigation manager for autonomous robots applicable to precision farming that enables navigation throughout the farm, not limited exclusively to the crop field.
• The integration of different artificial intelligence (AI) methodologies to identify various types of crops, including wide and narrow crops.
• An AI-based laser weed control implement that enables a wide working range for individualised plant treatment in crops of different types, while complying with all safety regulations required for working with laser technology.
In Europe alone, around 130 million tonnes of synthetic herbicides are used each year (not counting other chemicals). These substances do not discriminate between beneficial plants and insects in the soil that are not their target and can have effects on the health of animals and humans. In addition, weeds are developing resistance, which means that existing herbicides are becoming less and less effective.
González de Santos, one of the team members, says: “The WeLASER consortium is motivated to adopt smarter farming methods and build more sustainable food production systems while preserving the environment and health. WeLASER opens up a reliable and safe option and offers breakthroughs to solve a global problem.”