Building with bamboo for a low-carbon future

The project was funded by the Cyber Valley Research Fund and was carried out between 2021 and 2024 at the Institute of Computational Design and Construction (ICD), University of Stuttgart. It addressed the challenges of using robotic manipulation when constructing with non-standardized, flexible materials like bamboo.

The project's key achievements included:

Robotic system development

The project designed and implemented a custom mobile robotic system optimized for handling bamboo. To ensure effective manipulation of this material, the research team designed the robot's kinematics and control strategies in response to its flexible and anisotropic structure.

Task and motion planning (TAMP)

The research team developed a hybrid approach using Reinforcement Learning and Logic-Geometric Programming. Reinforcement Learning was used for dynamic adaptation in bending tasks, while Logic-Geometric Programming was applied for structured, multi-step planning of construction sequences. This approach meant the robotic system could combine adaptability and precision.

Simulation and learning framework

To model bamboo’s mechanical behavior, the project developed a high-fidelity simulation environment to train the robotic system’s Reinforcement Learning policies, before being used in the real world. The researchers improved this transfer from simulation to reality by using Domain Randomization and Curriculum Learning techniques, so that the robotic system could work reliably with real bamboo.

Experimental validation

In both simulated and real-world experiments, the robotic system successfully demonstrated reaching, transporting, and assembling bamboo elements. The researchers also tested cooperation between multiple robots, showing the potential for large-scale autonomous construction.

Architectural scale demonstrator

The project culminated in the development of a full-scale robotic demonstrator that could execute key construction tasks. Although some mechanical and electrical components required further refinement, the demonstrator proved the feasibility of robotic bamboo construction.

By contributing to the advancement of robotic construction methodologies, the outcome of this research project enabled robots to work with natural, renewable materials in a scalable and adaptive manner. In doing so, it provides a pathway to more sustainable, low-carbon building practices, fulfilling the Cyber Valley mission of turning AI and robotics research into a sustainable future for everyone.

This project produced the following peer-reviewed publications: 

N. K. Kalousdian et al., “Learning Robotic Manipulation of Natural Materials With Variable Properties for Construction Tasks”. In: IEEE Robotics and Automation Letters, Vol. 7, No. 2, April 2022, pp. 5749-5756. DOI: 10.1109/LRA.2022.3159288.

About the Cyber Valley Research Fund

The Cyber Valley Research Fund was established to support Cyber Valley research groups undertake basic research in the fields of artificial intelligence and robotics. The fund totaled five million euros, including contributions from six of Cyber Valley’s founding corporate partners: Amazon, BMW, Bosch, IAV, Mercedes-Benz, Porsche, and ZF. It supported 20 research projects, the first of which began in 2020, and the final of which will conclude in 2026.