Robotics project points to 'sea change' in berry harvest productivity

The AI ​​approach models worker skills and farm needs to move fruit from pickers to packing stations faster and more cost-effectively.

A new research project from Performance Projects and the University of Lincoln is developing a low-cost "human-robot teaming solution" using AI to maximize the efficiency of available human labor.

The AI ​​approach is being tested at Clock House Farm in Kent to model worker skills and farm needs in a bid to move fruit from pickers to packing stations more quickly, efficiently and cost-effectively.

The goal is to achieve a "game change" in the productivity of the soft fruit crop and thereby help address the well-documented labor shortage in the sector.

The project is called Co-FRUIT (Collaborative Fruit Retrieval Using Intelligent Transportation). As part of the research, an automated light electronic vehicle has been developed that transports empty trays to the collectors and full trays to the packing stations.

AI technology is used to match robotic dogs with human pickers so that they arrive at a convenient location at the appropriate time, with the help of sensors, to pick the fruit and then take it to the packinghouse.

Lincoln University professor Elizabeth Sklar is leading the project. “Human workers are paid by the piece, so we know roughly how quickly they can pick up,” she explained. "This means we can model when each picker will be ready for a robot to pick their fruit, so they don't have to spend time pressing a button and then waiting for the robot to arrive."

Of course, developments like this will require effective communication between humans and robots when they are operating in the same area of ​​the farm. To make this easier and to ensure worker safety, Lincoln University robotics experts Simon Pearson and Marc Hanheide are developing a kind of sign language so that workers can tell a robot to move closer, move back, stop, go left or right.

"The big transition in the next 15 years is that the industry will need hybrid solutions," Sklar said. "You're not going to take over a farm, flip a switch and say, 'On Monday all the robots are here and we don't need any more people.' Therefore, we need to develop systems that allow humans and robots to communicate effectively when they are operating side by side.”

The project, which began in early May 2022, will be completed by the end of October 2023. The aim is to develop an affordable navigation system for table strawberry retrieval that costs less than £500 and could help growers save money. in hardware costs by up to 90%.

Integrated scheduling and scheduling systems under development promise savings of up to 20% in human labor costs and a 5-10% reduction in farm manager time, according to the researchers.

Previous article

next article


"Blueberry promotions are working wonderfully"
An increase in Peruvian blueberry exports is expected despite ...
CAES researchers examine blueberry quality problems to p...