Charles Richter

Papers

Total Citations

248

H-Index

About

Charles Richter is a leading researcher in the intersection of robotics, deep learning, and safety-critical navigation. His primary focus is on enabling autonomous systems—particularly mobile robots—to operate reliably in unknown and unstructured environments. Richter’s major contribution lies in developing frameworks that combine perception, planning, and uncertainty quantification to ensure safe, high-speed navigation. His most cited work, "Safe Visual Navigation via Deep Learning and Novelty Detection" (2017, 172 citations), introduces a pioneering method for robots to recognize and safely handle unfamiliar scenarios that fall outside their training data, addressing a critical weakness of deep learning in real-world deployment. This work, alongside his Bayesian learning approach for high-speed navigation (61 citations) and his research on learning to plan for visibility (15 citations), has shaped how modern robots balance exploration with safety. Richter’s achievements are notable for bridging the gap between theoretical machine learning and practical, robust autonomy—a key challenge for deploying robots in dynamic, unpredictable settings. His research continues to influence students and engineers working on trustworthy autonomous systems.