Community Research and Development Information Service - CORDIS


SWEEPER Report Summary

Project ID: 644313
Funded under: H2020-EU.

Periodic Reporting for period 1 - SWEEPER (Sweet Pepper Harvesting Robot)

Reporting period: 2015-02-01 to 2016-07-31

Summary of the context and overall objectives of the project

In modern greenhouses there is a high demand to automate labour. The availability of a skilled workforce that accepts repetitive tasks in harsh greenhouse climate conditions is decreasing rapidly. The reduced capacity and the resulting increase in labour costs is putting major pressure on the competitiveness of the European greenhouse sector. Present robotization of this labour has entered a high level of technological readiness. However, a gap remains which halts the transition from science to economic and societal impact; the so called ‘Technological Innovation Gap’.

SWEEPER’s main objective is to put the first generation greenhouse harvest robots onto the market. Until now this has never been achieved and this will ensure Europe’s leading role in agricultural robotics. It will solve the current labour capacity problems in modern greenhouses, where harsh climate conditions and repetitive work puts pressure on the workforce supply. Without further mechanization, greenhouse food production will most likely migrate out of Europe due to increased labour costs, which has an expected increase in costs of 40% in the coming 10 years. Increasing the efficiency and reduced labour dependence will ensure Europe’s leading greenhouse food production yields and competiveness. SWEEPER secures moving into this direction. When a proven system is moved towards the market, it opens up a whole new high tech commercial area. Although SWEEPER aims at a singular crop, which has an estimated European yearly yield of 1,300,000,000 kg, knowledge and technology can be easily migrated to other greenhouse areas thereafter.

In the EU-FP7-project CROPS extensive research has been performed on agricultural robotics. One of the applications was a sweet pepper harvesting robot. It was shown that such a robot is economically and technically viable. In SWEEPER, the proven hardware and software modules developed in CROPS will be used as the groundwork, and the knowledge gained in CROPS will directly be put to benefit. The successful software modules based on the Robotic-Operating-System (ROS) will be maintained and expanded. Also the gripper end-effector will be retained. This patent pending module is able to grasp the sweet pepper without the need of an accurate measurement of the position and orientation of the fruit. Further it was concluded that instead of a 9 degree of freedom (DOF), a 4DOF robot arm is sufficient, greatly reducing costs. To improve the level of robotic cognitive abilities, crop models will be applied to approximate location of sweet peppers. This “model-based vision” will increase and speed up fruit detection, localisation and rating of its maturity. Based on the insights of CROPS, sensors will be placed onto the gripper only. Also a time-of-flight sensor will be introduced which is able to record both colour and 3D information simultaneously. In CROPS it revealed that different growers use different cropping systems ranging in crop density. In SWEEPER, the cropping system itself will be optimized to facilitate robotic harvesting.

The SWEEPER objectives are:
1: Revise and improve the CROPS hardware and integrate it into a sweet pepper robot.
2: Develop and improve the software to control the robot.
3: Optimize the standard sweet pepper production system in order to make the robot perform best and demonstrate the final system.
4: Test the robot under laboratory and operational conditions in the greenhouse.
5: Support market introduction.

Work performed from the beginning of the project to the end of the period covered by the report and main results achieved so far

The robot is an assembly of several subsystems such as a mobile autonomous platform, a robotic arm holding an end-effector for fruit harvesting, and post-harvest logistics. The end-effector will contain sensing tools for detection of sweet pepper and obstacles in order to use precise eye-hand control. The robot will gradually evolve as a Basic, Advanced and Final System. Functionality depends on the hardware and software modules and their maturity. Robot prototypes will be tested in laboratory prior to commercial greenhouse testing. The Final System will be evaluated and demonstrated during the last season. It will serve as input for production of a commercial system as follow-up to the Sweeper project.

In the first period, the Basic System was built and tested in the lab and in a commercial greenhouse for the most suitable yellow pepper variety. First fruits were harvested with the robot. The outcome of these tests is used to support the design and development of the Advanced System, which is now on-going. A custom ordered illumination and RGB-Depth camera system (both smaller and light-weight) for it are on its way. Further we work on a revision of the end-effector in order to hold both the camera and illumination. First lab tests with the Advanced System are expected for autumn 2016, a full version will be ready for greenhouse test at the end of the second project year. The experiments for optimal cropping conditions are on-going and have yielded first year results.

Progress beyond the state of the art and expected potential impact (including the socio-economic impact and the wider societal implications of the project so far)

The current state of the art in automated harvesting of fruits and vegetables has remained remarkably stationary in the past three decades. Around 50 robotic harvesting systems have thus far been globally developed of which none have been commercialised to this date. On average, the harvesting success of prototypes has been around 66% with a cycle time of 33 seconds per fruit. This is far below the rate to be commercially viable, under the assumption that the market demands a machine that is highly accurate and fast. However, near perfect harvest success and high speed are not prerequisites for economic viability: also with lower performance such a robot can be of supportive value in the greenhouse. The major problem is often the gap that remains in the desired and achieved Technological Readiness Level (TRL) lacking practical robustness, failure control and required post-harvest logistics.

It is our ambition to break through this trend. A high TRL is too often wrongly seen as a side target in fundamental scientific research, as its main objective is usually to apply and investigate novel techniques (a proof-of-concept) and not to bring the robot to the market. In CROPS a similar level was reached as other state-of-the-art results, with a modular system fit for several different tasks (harvesting apples, grapes, sweet peppers and spraying). In SWEEPER we want to lift a fundamental science prototype result out of the laboratory and onto the market. This will be achieved by developing a targeted system best-fit for high TRL and market readiness. In order to achieve this we focus on following: exploring alternative robot designs, using state-of-the-art robot hardware and software innovations, integrated logistics, improved fruit detection & ripeness determination, obstacle detection and avoidance, crop optimization for mechanical harvesting, human-robot coexistence and collaboration, and growers and societal acceptance.

The SWEEPER project will provide new technology for the greenhouse horticultural sector, especially for sweet pepper growers. Sweet peppers are chosen to be the first crop to be automated because it is a high value product, greenhouse cultivation is already highly standardized which affords further mechanisation and amounts for a significant part of the greenhouse sector. The automatic harvester will contribute to solve some of today’s major grower issues as labour costs, labour availability and food safety and quality.

Related information

Record Number: 196360 / Last updated on: 2017-03-29