Yen-Ling Kuo, an assistant professor of computer science at the University of Virginia, is teaching robots to make educated guesses. Her approach merges principles from cognitive science with computational models, aiming to create machines that can reason under uncertainty. Kuo, an IEEE member, focuses on enabling robots to operate intelligently when they lack complete information.
This work sits at the intersection of cognitive and computer sciences, a focus that emerged from her childhood curiosity and professional experience at a Silicon Valley company. Kuo’s early fascination with how things work—sparked by reading about Michael Faraday and learning Logo programming in Taiwan—evolved into a career building smarter machines. The goal is not perfect knowledge, but better decision-making in dynamic, real-world environments.
Kuo’s research emphasizes helping robots weigh probabilities and infer likely outcomes, much like humans do. She realizes that complete certainty is often impossible; educated guesses offer a practical path forward. The work has potential applications in autonomous systems, from self-driving cars to service robots.
For robotics, this represents a shift from rigid, pre-programmed responses toward adaptive, context-aware behavior. Industries that rely on automation could benefit from machines that handle ambiguity without constant human input. However, widespread adoption depends on proving these systems are reliable and safe in critical scenarios.
Critics caution that guesswork introduces unpredictability, which is problematic in high-stakes environments like healthcare or transportation. The balance between flexibility and control remains a central challenge.