Aionics Chief Scientist Dr. Venkat Viswanathan, Associate Professor of Mechanical Engineering at Carnegie Mellon University, made a big announcement at the Advanced Automotive Battery Conference this week in San Diego.
Building on his CMU lab’s first robot “Otto,” Prof. Viswanathan announced new work that introduces a novel workflow coupling robotics to machine-learning for efficient optimization of a non-aqueous battery electrolyte. The new robot, “Clio,” is coupled to Dragonfly – a Bayesian optimization-based experiment planner.
Clio autonomously optimizes electrolyte conductivity over a single-salt, ternary solvent design space. Using this workflow, Prof. Viswanathan’s lab identified six fast-charging electrolytes in an amazingly rapid 42 experiments across two workdays. Compare that to 60 days using exhaustive searches of the 1000+ possible candidates.
This work no doubt ushers us into a new era for materials optimization with robotics and machine learning.
The pre-print publication from Prof. Viswanathan’s group describing this work is available on arXiv here: https://arxiv.org/abs/2111.14786
AABC attendees can view Prof. Viswanathan’s talk on Pathable here: https://aabcon2021.us2.pathable.com/meetings/virtual/ZfScHnEMjFFvRKw95
Get the latest articles on all things data delivered straight to your inbox.