With the goal of “Teaching Tools to Be Teammates”, the Digital Manufacturing Research Team within AFRL is exploring how to make a variety of robotic manufacturing processes more agile and autonomous while actively collaborating with human subject level experts in order to achieve functional agility and overcome large deviations from the planned objective. Recent advances in machine learning and artificial intelligence have shown promise in providing this agility, and the team is exploring how to employ these algorithms while augmenting classic control theory, optimization, and physics-based modeling to enable more autonomy in manufacturing. From additive manufacturing systems to robotic part manipulation, we are developing models for how to map complex nonlinear data sets with high degrees of variability and uncertainty and make decisions about how to design, plan, and modify processing steps to achieve the desired structure or part with appropriate functionality.

Research topics of interest within this space include: (1) learning-based methods for process and robotic control; (2) control theory for additive manufacturing; (3) scheduling/operations research (optimization) for robotic manufacturing; (4) manufacturing process constrained topology optimization.

key words

Intelligent Robotics; Machine Learning; Optimization; Autonomy; Control Theory; Design for Manufacturing; Additive Manufacturing

Citizenship:  Open to U.S. citizens

Level:  Open to Postdoctoral and Senior applicants