Christopher Rodriguez

Papers

Total Citations

H-Index

About

Christopher Rodriguez is a pioneering researcher at the intersection of robotics, machine learning, and microfluidics, with a focus on building safer and more reliable autonomous systems. His primary research areas include imitation learning for robotic manipulation, uncertainty-aware failure detection, and the automation of microfluidic device design. Rodriguez’s most notable contribution is his work on runtime failure detection for imitation learning policies, where he addresses a critical gap in deploying complex robotic systems: detecting failures without requiring prior failure data. His 2025 paper, “Can We Detect Failures Without Failure Data?,” has already garnered 5 citations, highlighting its timely impact on the robotics community. Additionally, his earlier work on modular microfluidic design automation using machine learning (2019) laid foundational groundwork for integrating AI into lab-on-a-chip technologies, enabling faster and more cost-effective prototyping. Rodriguez’s research is particularly relevant as robotic systems tackle longer-horizon tasks in unstructured environments, where unexpected failures pose significant risks. By combining rigorous theoretical frameworks with practical applications, he is shaping the future of trustworthy autonomous systems and advancing the field of microfluidic automation.