Our research focuses on creating next-generation architected soft and living materials by leveraging our expertise in mechanical design, materials science, stem cell biology, fluid mechanics, 3D printing, and biomanufacturing. The overarching goal of our laboratory is to formulate the fundamental science and engineering basis behind autonomous systems driven by sequential decision algorithms that will help us achieve our research vision at a fraction of the cost and speed compared to the traditional Edisonian research paradigm.

The goal of optimal design is to make the most efficient use of limited resources (such as time, budget, or available experiments) to achieve specific objectives, such as building accurate models, estimating parameters, or minimizing uncertainty. Our lab focuses on the application of sequential decision algorithms and optimal learning in experimental intelligence. We are engaged in developing methods that improve decision-making processes through iterative cyber-physical experimentation and learning. Our approach is based on adapting and refining strategies based on previous outcomes, enhancing both efficiency and precision. Every experimental workflow is and can be mathematically formulated as a sequential decision problem with uncertainty. This work has practical applications in various areas, including 3D printing optimization and resource management. Our goal is to combine theoretical research with practical problem-solving, contributing to advancements in scientific understanding and offering solutions to real-world challenges.

In the 'Self-Driving' research initiative, we work on integrating the cutting-edge tools and methodologies developed across all previous initiatives to establish self-driving laboratories. These state-of-the-art labs are engineered to revolutionize the discovery, optimization, and standardization processes in the field of soft and living materials. By harnessing the power of machine intelligence, experimental intelligence, and advanced automation, our self-driving labs automate material synthesis, characterization, and manufacturing. This integration allows for continuous closed-loop autonomous experimentation by scientific robotic agents, driven by sequential decision agents. This paradigm shift not only accelerates the pace of discovery but also ensures a higher level of reproducibility and standardization in research outcomes. Our vision is to transcend traditional boundaries in scientific research, opening new horizons for exploration and innovation in soft and living material science and engineering.