Chemists need to perform many laborious and time-consuming experiments in the lab to discover and understand the properties of new materials. To support and accelerate this process, we propose a robot framework for manipulation that autonomously performs chemistry experiments. Our framework receives high-level abstract descriptions of chemistry experiments, perceives the lab workspace, and autonomously plans multi-step actions and motions. The robot interacts with a wide range of lab equipment and executes the generated plans. A key component of our method is constrained task and motion planning using PDDLStream solvers. Preventing collisions and spillage is done by introducing a constrained motion planner. Our planning framework can conduct different experiments employing implemented actions and lab tools. We demonstrate the utility of our framework on pouring skills for various materials and two fundamental chemical experiments for materials synthesis: solubility and recrystallization.
@article{arxiv.2212.09672,
title = {Chemistry Lab Automation via Constrained Task and Motion Planning},
author = {Naruki Yoshikawa and Andrew Zou Li and Kourosh Darvish and Yuchi Zhao and Haoping Xu and Artur Kuramshin and Alán Aspuru-Guzik and Animesh Garg and Florian Shkurti},
journal= {arXiv preprint arXiv:2212.09672},
year = {2023}
}
Comments
Equal author contribution from Naruki Yoshikawa, Andrew Zou Li, Kourosh Darvish, Yuchi Zhao and Haoping Xu