C2-A2 AGRODROID the world’s new Smart Farming product

C2-A2 AGRODROID the world’s new Smart Farming product

Link to publication

European software developer ‘Cognitive Technologies’ has developed the world’s first industrial agrodroid for international agricultural market.

Cognitive Technologies – one of the top developers of AI-based systems for self-driving cars and autonomous transportation – announces the launch of the world’s first C2-A2 AGRODROID (Cognitive 2 – Agro 2 – Droid 1), an industrial model of the universal control system for autonomous agricultural machinery.

“C2-A2 is an artificial brain that is equipped with a cradle – a universal device for fast connection with different agricultural machinery: harvesters, tractors, sprayers and others, – says Olga Uskova, president of Cognitive Technologies, – Within our team we consider C2-A2 as a brother-in-law of the world-famous R2-D2 (an astromech droid character of the Star Wars epic space opera)”.

“Installation of C2-A2 AGRODROID makes any harvester or tractor autonomous and any agricultural activity smart. Supplying the solution with a cradle makes it possible to move this artificial brain from one machine to another without purchasing a new system each time”, – continues Olga Uskova.

The C2-A2 AGRODROID is developed on the basis of the Cognitive Agro Pilot – an autonomous driving system for agricultural machinery that was presented earlier. The key innovation of the new product is the state-of-the-art Convolutional Neural Network (CNN) that was modified by the Cognitive Pilot team for agricultural purposes and tasks.

“On international agricultural market this is the first product of such type that is based on standard Nvidia computing device (Nvidia Jetson TX2) with deep neural networks”, – claims Uskova.

An important feature of the new product is a complete safety of all the fieldworks. In comparison with the existing autonomous driving systems for agricultural machinery, which are GPS-based, the neural networks based C2-A2 opens a new class of systems that is able to protect equipment and people from all possible collisions.

Another competitive advantage of the presented solution is the lack of expensive sensors. Unlike other analogues that use expensive laser scanners (Lidars) and stereo cameras, Cognitive Technologies team has developed such a computer vision system that is able to achieve similar results with the use of just one single video camera.

The use of just one sensor, not 3 or 4 as proposed by other manufacturers, allows to reduce the cost of the whole solution by 3-5 times. The final cost of the C2-A2 AGRODROID will be about 3.000 USD, which is approximately 1.5% of the cost of the combine harvester and about 3% of the cost of the tractor.

“We estimate the agrodroids market volume at 94 billion USD and expect to get at least 15% market share in the next five years. The world’s tractor fleet that is ready for our solution is about 27 million machines”, – concludes Olga Uskova.

Russian autonomous harvester works into the night

Russian autonomous harvester works into the night

Link to publication

Russian IT-company and Ai developer, Cognitive Technologies, has released a new version of its autonomous driving system for harvesters that can work at night.

The latest development follows the company’s successful field testing of a prototype autonomous harvester in August (see Grain Central story).

Cognitive Technologies president, Olga Uskova, said the ability to work at night time would minimise the impact of the weather and human factors and could improve the quality of grain harvesting by 25-30 per cent.

She said the new system was capable of performing more complex manoeuvres than its predecessor. “At any time of the day the harvester equipped with the system is able to make a U-turn or move along a difficult and curved trajectory,” he said.

“The maximum speed of the autonomous harvester now is 11 kilometres/hour, while it automatically monitors the edge of the collected crop.”

The system itself determines if the harvesting collection boundary starts to deviate from a straight line. If this happens, the combine itself simply corrects the track and continues harvesting.

“It is important that the harvester is able to determine not only the edge of the field: the system recognises other machinery, people and animals,” Mrs Uskova said. “It also understands where the field is already processed, and where it is not.

“In future the number of objects for detection and segmentation will be increased and this will make it possible to distinguish different cultures growing on the same field.” Mrs Uskova said the machine used a camera as its main sensor for collecting data and navigating.

“The harvester does not need a high-precision GPS: it can be completely autonomous, relying only on the video signal,” he said.

Tests were carried out on the TORUM 760 combine harvester jointly with the Rostselmash combine manufacturer in the Rostov region of southern Russia.

The autonomous harvester worked on a rice field of 40 hectares and successfully passed all the tests in the night. Cognitive Technologies expects to create a fully autonomous grain harvester by 2023-2024.

Fully driverless combine harvester by 2024

Fully driverless combine harvester by 2024

Published on AGRILAND.IE
Link to publication

An off-the-shelf combine harvester has been converted to automatically steer itself by a Russian technology company, at a “fraction of the normal cost of such technology”.

This, says the company, is a precursor to fully autonomous (driverless) operation in the near future.

The company is called Cognitive Technologies; it develops robotic systems and software.

What are the advantages of such developments? The company claims that the use of such technology can increase output and reduce losses. It allows the combine harvester operator to “focus on machine settings, rather than steering and driving”.

Working in “low-growth” barley (standing just 30cm tall), the challenge was to come up with a practical system using only one video camera, instead of a plethora of cameras and sensors. In effect, the company says that its system employs only one camera and a “neural network”, unlike “much more expensive” systems from mainstream machinery manufacturers.

According to the company, the system works to a high level of accuracy – targeting a sub-5cm tolerance. The current system automatically stops the combine harvester upon completing each task – awaiting intervention by the driver. A task could encompass multiple rounds of a field.

Olga Uskova, President of Cognitive Technologies, explained: “We’ve spent five years developing this technology thus far. We expect to create a fully autonomous grain harvester by 2023-2024.

“We have already created a highly-developed computer vision system that allows just one camera to achieve similar results as leading international manufacturers get with three to four sensors. As a result, the cost of the equipment is three to four times lower. And this gives us a significant competitive advantage,” she added.

The company field-tested its equipment during recent weeks; the system was fitted to a Russian-built Rostselmash RSM 181 Torum harvester. The tests were carried out in the Rostov region of southern Russia.

Over the course of one and a half days, the system was “re-trained” from wheat to barley. At present, it recognises the edge of the crop, thus determining where the machine should steer itself. According to the company, it can do this “better than a human driver”.

The camera and associated software can identify all manner of obstacles including: uncut versus cut areas; swaths or layers of straw; trees; roadways; people; etc.

Russians test driverless harvester

Russians test driverless harvester

Link to publication

Russia has stepped into the era of automated machinery with a Russian company field testing an autonomous grain harvester.

Cognitive Technologies, which develops robotic systems and software for machine vision, has field tested a Rostselmash RSM 181 Torum harvester in the Rostov region of Southern Russia.

Company president, Olga Uskova, said the company had spent more than five years developing the system and expected to have a fully autonomous grain harvester available for commercial release by 2023-2024.

She said the system was low-cost because it used a single video camera as a sensor, unlike other systems that used laser scanners, stereo cameras, lidars (light detection and ranging), etc.

“The automated complex of our smart harvester includes a video camera and artificial intelligence system,” she said.

“The neural network of the system is now able to allocate five main classes of the field scene:

1) Unmowed part of the field

2) Mowed part of the field

3) Roll in the hay

4) Everything that falls in the view of the camera from the header of the harvester

5) All other objects – obstacles, other machinery, forests, trees, roads, weeds, people etc.

“The additional competitive advantage of our Ai system is that it sees various types of field boundaries (edges, rolls).”

Mrs Uskova said in the field tests, instead of the planned field of wheat that would have been more than 80 centimetres high, farmers provided fields of barley that were about 30 cm high.

“This was a great, almost impossible challenge. For 1.5 days we retrained the neural network based on the datasets of other agro cultures. As a result, the neural network was able to determine the stacked roll and the field scene better than the person. The result surpassed all expectations. This is a breakthrough,” she said.

Robot harvesters are ready to rule Russia's fields

Robot harvesters are ready to rule Russia’s fields

Link to publication

The Republic of Tatarstan in central Russia has unveiled a program to develop unmanned combines for agriculture. The first robot harvesters will be working the fields in just two years.

A combine harvester slowly crawls across a Russian field and processes crops. At first glance, there is nothing unusual in this. If you look closer, however, you will find there are no humans inside – the harvester functions entirely by itself.

As the Russian agricultural sector faces a severe shortage of workers, scant manpower remains in rural areas. Many Russian agricultural holding companies have no alternative but to bring in migrant workers to the fields. The use of unmanned agricultural vehicles, however, will solve several problems at once – there won’t be a need to ship in human workers, and it will increase productivity. A robot combine harvester does not need to sleep; it does not get ill, or need to go on holiday.

A program to develop unmanned vehicles for agriculture has now been launched in Tatarstan; and an agricultural holding company, Agropolis, will produce this smart equipment for smart agriculture.

Investment into Agropolis over the next five years will total more than $225 million, and the first unmanned harvesters will be ready in two years. Each is expected to cost only 15-20 percent more than traditional, man-operated vehicles.

Agropolis’ main shareholders include Rostselmash, Russia’s largest manufacturer of agricultural machinery, and Soyuz-Agro, one of Tatarstan’s leading agricultural holding companies, as well as the Russian company Cognitive Technologies (CT). The latter already has experience in the creation of unmanned vehicles, and closely cooperates with KAMAZ, Russia’s largest producer of trucks, for which CT is developing unmanned vehicle control systems.

Better than Google?

Robotic systems for Russia’s agricultural sector will be developed in several key areas, said Olga Uskova, president of CT. First, this concerns agricultural harvesters and other equipment.

“This robotic technology is based on our developments for KAMAZ trucks, whereby the camera and the computer create a so-called ‘virtual tunnel,’ and the vehicle itself decides where it needs to go,” Ms Uskova said, adding that Russian systems are just as good as leading foreign companies in this field – such as Google – and even surpass them in some respects.

According to Ms Uskova, foreign-built systems are largely designed for ideal road conditions – markers, pointers, signs and smart roads. CT’s systems are geared to Russian conditions and can be used in the absence of any road indicators.

Russia uses this approach in addition to the active model, which involves the use of radiating devices – radars and lidars – that determines the distance and speed of objects. This model is used in many international projects, such as Google Car.

Drones eradicating weeds

Agropolis also plans to create automated crop monitoring systems. Drones will fly around fields and for example, monitor the presence of weeds. Also, stationary measuring devices will be installed in different parts of fields and for example, measure moisture levels or useful minerals in the soil. If these figures drop, then a command will be given to activate automatic watering, or fertilizer systems.

There are obstacles, however, to the use of drones in agriculture. “So far, there is no legislative basis for this kind of transport vehicle,” said Oleg Korobkin, director of operations of the DPD transport company in Russia.

“Creating the necessary maintenance infrastructure is an important condition to facilitate the emergence of demand for such equipment,” said Alexander Dyakonov, transport director of the logistics company, FM Logistic. “Moreover, we should think about what to do with the current human drivers; more than 2 million people operate and service commercial transport and other vehicles in Russia”.