January 30, 2015      



Poster child for Horizon 2020

Clever Robots for Crops (CROPS), an EU Seventh Framework Program (FP7, #246252) begun in 2010 and concluding during Horizon 2020?s first year (2014), has succeeded grandly in developing a modular agribot platform that can handle multiple agricultural jobs: sensing, manipulation, production and harvesting of high-value crops.

If the European Commission is looking for a symbolic project that catalyzes all that Horizon 2020 aspires to be, this is it.

Costing a respectable $11.6 million (?10.3 million) over five years ( 30 percent co-funded by the Dutch Horticultural Product Board) , involving a consortium of engineers and scientists from universities and private companies from eight* different nations, and hitting all of its research goals, the CROPS platform is a paragon of pan-European cooperation and joint technical expertise.

*Belgium, France, Germany, Italy, Netherlands, Slovenia, Spain and Sweden.

Catherine Simon, president of InnoEcho, the organizing company behind the annual Innorobo robotics conference, marveled at the hard-won technical and organizational innovation. When asked if the speed of innovation would have been better served by not taking on so much, like an entire platform for four different types of agribotics instead of just a single, task-specific machine, she agreed: ?If the CROPS project were to focus on detecting one specific type of fruit, it might be a shorter path to market.?

Then again, when viewed through the lens of multiple countries all participating in CROPS, she reckoned that speed would have been compromised anyway just by dint of having to deal with multiple governments.

In the end, speed may have been compromised, however, the fact that the consortium of countries did it together, and were successful, said a lot for unity and sharing responsibility, which is something that the European Commission seeks to foster.

Agribot that makes sense

Coordinated by Dutch-based Wageningen University & Research Centre, the CROPS robot multi-tasks through high value crops such as greenhouse and farmland vegetables, fruits in orchards and grapes for premium wines.

The CROPS robotic platform is capable of ?selective harvesting of sweet-peppers, apples and grapes, and for precision spraying of pesticides,? reports Phys.org.

?Sensor systems for obstacle avoidance for forest machines have also been developed. All robots use the same type of modular system and the same software architecture. This makes it easy for example to use a different camera or different type of robotic hand.?

The robots detect the fruit, sense its ripeness, then move to grasp and softly detach only the ripe fruit. Another objective is to develop techniques for reliable detection and classification of obstacles and other objects to enable successful autonomous navigation and operation in plantations and forests.

Single tool for farmer, vintner, orchardist and arborist

The CROPS website explains their project?s capabilities and the group?s R&D success:

CROPS has developed scientific know-how for a highly configurable, modular and clever carrier platform that includes modular parallel manipulators and intelligent tools (sensors, algorithms, sprayers, grippers) that can be easily installed onto the carrier and are capable of adapting to new tasks and conditions.

Several technological demonstrators have been developed for high value crops like greenhouse vegetables, fruits in orchards, and grapes for premium wines.

The CROPS robotic platform is capable of site-specific spraying (targets spray only towards foliage and selective targets) and selective harvesting of fruit (detects the fruit, determines its ripeness, moves towards the fruit, grasps it and softly detaches it).

Another objective of CROPS was to develop techniques for reliable detection and classification of obstacles and other objects to enable successful autonomous navigation and operation in plantations and forests. The agricultural and forestry applications share many research areas, primarily regarding sensing and learning capabilities.

The case for a “single” task-specific machine

Although five years is not an uncommon length of time to develop a commercially viable agribot, the case for speedy innovation of a “single” machine as opposed to a platform for multiple tasks for robots, is evident in CROPS producing a first-ever pepper harvesting robot (pictured above).

greenhouses

The robot is a milestone in harvesting. The sweet-pepper (also called bell pepper) harvesting robot developed in Wageningen UR is able to locate, to approach, to hold, to detach and to collect ripe fruits. Indeed, the agribot is a definite first, yet it’s still not commercially viable, and has just received additional funding to push it through it’s last mile of development, estimated to be about three years.

What if it had been fast-tracked for development and commercialization?

Awaiting such a robot are millions of metric tons of peppers, especially in places like China, the Netherlands and Spain. What if CROPS had taken on just this one groundbreaking machine instead of a platform for many?

According to the United Nations, the Netherlands handled 14.6 percent of the world?s fruit and vegetable exports making it the world’s largest. Much of the pepper crop for the Netherlands and Spain are from greenhouses for which the CROPS-developed pepper picker is ideal.

There are about 2,500 hours of labor needed to produce one acre of peppers. At approximately $7.90 (?7.00) per hour, that’s over $19K. For a bit of perspective, see photo above of greenhouses in Almeria, Spain, which from this photo looks like it could use more than a few of the CROPS pepper pickers.

Was opportunity passed over in favor of EU harmony?

It is what it is

Now that CROPS has succeeded in developing its Swiss army knife of an agribot, the project needs to move into the commercialization phase.

The question for 2015 is whether or not the CROPS modular platform can be manufactured in quantity and at an affordable price.

See attached download: CROPS: high tech agricultural robots
International Conference on Agricultural Engineering, Zurich, 2014