AI, Autonomy, Machine Learning, and Robotics

A2MR researchers develop and integrate computational, mathematical, and experimental methods for intelligent systems. Their work spans the full cycle from sensing and learning to decision-making, control, physical interaction, and collaboration with people.

• Develop machine-learning and artificial-intelligence methods that learn from data and support prediction, classification, scientific discovery, and decision-making.
• Formulate optimization and decision-making methods for complex systems operating under uncertainty.
• Design control and autonomy algorithms that allow engineered systems and robots to operate safely, robustly, and adaptively.
• Develop robotic and perception systems that combine sensing, computer vision, planning, control, and physical interaction.
• Study human-AI and human-robot interaction to improve safety, usability, trust, performance, and collaboration.
• Apply AI, autonomy, and robotics to smart manufacturing, cyber-physical systems, automated experimentation, and other data-rich engineering environments.

At the doctoral level, A2MR is an ISE Ph.D. concentration offered at the Blacksburg campus. The curriculum combines core preparation in mathematical modeling/analysis and statistical methods with advanced concentration courses in artificial intelligence and machine learning, control theory, robotics, perception, and human-robot interaction. Students develop an individualized plan of study with their advisor and Ph.D. advisory committee so that coursework supports the student's dissertation research.

Related A2MR focus areas are also defined for the ISE M.S. and M.Eng. programs. The M.S. pathway combines interdisciplinary coursework with thesis research, while the M.Eng. pathway emphasizes advanced professional preparation. Across degree levels, students may combine courses from multiple A2MR emphasis areas rather than being restricted to a single subfield.

Students can pursue interdisciplinary research with faculty across ISE and collaborating departments. Examples of A2MR research directions include:

• Artificial intelligence, machine learning, and learning theory: machine learning, deep learning, reinforcement learning, explainable AI, statistical learning, natural-language processing, and learning-enabled decision systems.
• Optimization and data-driven decision-making: mathematical programming, optimization under uncertainty, data-driven optimization, stochastic approximation, and methods that combine learning with optimization.
• Control, autonomy, and cyber-physical systems: linear and nonlinear control, adaptive and robust control, learning-enabled control, autonomous systems, and safe operation of cyber-physical systems.
• Robotics, perception, and human-robot interaction: robot perception, computer vision, planning, collaborative robotics, human-robot interaction, and human-centered intelligent systems.
• Intelligent and collaborative manufacturing: smart manufacturing, Industry 5.0, process monitoring and control, industrial AI, autonomous robotic manufacturing, quality assurance, and manufacturing analytics.
• Human-AI teaming and human-centered engineering: human-computer interaction, affective computing, wearable and assistive technologies, socio-technical systems, and the design of effective human-AI/robot teams.
• Autonomous experimentation and scientific discovery: closed-loop experimentation, intelligent sensing, data-driven discovery, and automated systems that select, conduct, and learn from experiments.

Affiliated Faculty Research and Labs