Wildlife
Completed

AI for Food Challenge

Developing high-precision agricultural robots that will increase land yield while reducing resources, with use of digital twins and reinforcement learning.

Making training and testing of farming robots faster and more affordable

Artificial Intelligence (AI) and robotics can help farmers to produce higher-quality food and have less impact on the environment. However, training and testing of agriculture robots is time consuming and expensive, because this usually happens in a physical environment and often involves the robot breaking down. In our project, we create a digital version of the robot that is tested and trained in a simulated environment. This way, training and testing of robots becomes faster and cheaper.

Info session

Our challenge partners

GOAL: Developing a framework for training and testing of autonomous robots in agriculture

In this project we will focus on: 

  • developing a framework for training and testing of autonomous robots, focussed specifically on the agricultural domain;
  • and building a demo setup for validating the applicability of the framework to a real-world setting.

The testing setup of Agrosim with a custom made physical and digital training environment for the turtlebot with gripper, Intel rear sense camera and lidar

We will do so by building a demo setup with a robot in an environment that will mimic a real-world scenario. At the same time we will train a digital twin of this robot in a simulated environment. We will:

  • Build the environment based on sensor information of the robot.
  • Develop object detection of fruits and mapping of surroundings for navigation with the help of minimal sensory information.
  • Integrate the ability to use own, pre-trained object detection algorithms
  • Set up a training framework in the simulated environment in order to teach the robot correct behavior.

The demo has been a success when the robot is able to ..

  • navigate smoothly within the physical environment without damaging itself
  • detect fruits and classify them correctly
  • grasp the fruit based on the sensory information it has
  • Autonomously collect fruits, based on easy command

Did you know

🥥   By 2050 there are expected to be 9 billion people on Earth. The planet must produce more food in the next four decades than all farmers in history have harvested over the past 8,000 years.

🥝  Industrial farms don’t support the rich range of life that more diverse farms do. As a result, the land suffers from a shortage of the ecosystem services, such as pollination, that a more diverse landscape offers. 

🥥   Robotic solutions such as pixelfarming can increase the biodiversity and proper usage of the soil, decreasing the weight of the machinery used for managing and cultivating this soil. 

🍉   Farmers’ interest in the latest technologies has turned agricultural robots and drones into a market that’s set to reach $23.06 billion by 2028. 

Application deadline

June 10, 2021
Join challenge

Timeline

Application Deadline: 20 June 2021

Final Presentations: 6 August 2021

A little more