In addition to receiving a contract award, SPRIND will support the Polybot team through intensive mentoring, strategic development guidance, and access to investors. The team will pitch their business idea to over 300 potential investors at the Venture SPRIND event in Berlin in April 2025.
"This contract underlines the fact that Polybot is not an ivory tower idea, but a concrete solution for future-proof, sustainable agriculture," says project leader Wieland Brendel from the Max Planck Institute for Intelligent Systems and the ELLIS Institute in Tübingen, Germany.
The close collaboration with SPRIND marks a significant success for the Tübingen AI ecosystem. Polybot is a strong example of how the Tübingen AI Center links research with real-world applications. "This first external validation motivates our team enormously," says Martin Kiefel, technical leader of the project. "With this support, we can now train our learning algorithms on the most challenging tasks in agriculture—like harvesting fine vegetables—and test them directly with farmers in the field."
Bernhard Schölkopf, Scientific Director of the ELLIS Institute and Director at the Max Planck Institute for Intelligent Systems, adds: "Excellent research unfolds its full power when it not only creates knowledge but also helps to solve the challenges of our time."
More sustainable farming
Polybot is a fully autonomous solution for growing crops, fruits, and vegetables using state-of-the-art AI technology. The robot aims to automate a wide range of activities—such as weeding, picking tomatoes or cucumbers, and free pruning. By integrating computer vision and robotic mechanics, Polybot helps reduce the need for chemical herbicides and promotes sustainable, small-scale farming.
Automating manual tasks enables farmers to use labor more efficiently and potentially increase yields over time. The core of the system is an autonomous robot equipped with a precise manipulator capable of executing complex tasks like tomato harvesting. Its control system is based on an innovative machine-learning pipeline that allows the robot to quickly learn new tasks through farmer demonstrations—eliminating the need for time-consuming programming.
Innovation in agriculture
The current validation project is evaluating the practical applicability of Polybot in harvesting fine vegetables—a task requiring high precision and advanced 3D perception. This makes it a challenging yet suitable test environment to demonstrate the robot's ability to automate tasks that have traditionally been considered economically unfeasible.
Beyond technical testing, the project also focuses on the benefits for farmers. Currently, fine vegetable harvesting is almost entirely manual, with labor shortages posing ongoing challenges. In collaboration with farmers, the project aims to define requirements for a market-ready product that delivers practical value.
"The Polybot project leverages recent breakthroughs in machine learning to make polyculture farming economically viable. I am delighted that we can bring such ideas to life at the Tübingen AI Center—ideas that are socially valuable and made possible only through cutting-edge research," says Matthias Bethge, Director of the Tübingen AI Center.
For more information:
Linda Behringer
Max Planck Institute for Intelligent Systems
Tel: +49 151 2300 1111
Email: linda.behringer@is.mpg.de
www.mpg.de