P. J. Erickson

Massachusetts Institute of Technology, University of Utah

Papers

Total Citations

H-Index

About

P. J. Erickson’s research lies at the intersection of machine learning, scientific discovery, and sensor-based autonomy, with a focus on how computational systems can augment human cognitive limits. In their seminal work, “Computer-Aided Discovery: Toward Scientific Insight Generation with Machine Support” (2016, 22 citations), Erickson challenged the traditional assumption that scientific discovery is exclusively human-driven, demonstrating how machine support can generate insights from vast datasets in fields like observational astronomy and geoscience. This paper has become a foundational reference for researchers exploring human-AI collaboration in science. Erickson also made notable contributions to Bayesian inference and robotics in “Bayesian Computational Sensor Networks: Small-scale Structural Health Monitoring” (2015, 10 citations), where they developed a methodology enabling a mobile robot equipped with vision and ultrasound sensors to simultaneously map small-scale structures and detect damage such as holes or cracks. This work showcases Erickson’s ability to bridge probabilistic modeling with real-world sensing, advancing structural health monitoring. Though their citation counts reflect a focused, emerging impact, Erickson’s research is recognized for pioneering the integration of machine support into the scientific discovery process, offering a compelling vision for the future of data-driven insight generation.