Christopher D. McKinnon
Papers
7
Total Citations
165
H-Index
6
About
Christopher D. McKinnon is a robotics and autonomous systems researcher whose work sits at the intersection of machine learning, probabilistic modeling, and safe control for autonomous robots operating in complex, real-world environments. His research is particularly focused on enabling robots to perform repetitive tasks reliably over long time horizons, even as operating conditions evolve in unpredictable ways. McKinnon's most influential contribution, "Learn Fast, Forget Slow" (2019, 56 citations), introduced a predictive learning control framework using weighted Bayesian linear regression to help ground vehicles adapt to unknown and changing dynamics — a critical advancement for long-term autonomous operation. Complementing this, his work on experience-based model selection (2018, 24 citations) and mixture-of-Gaussian-process expert models (2017, 22 citations) demonstrated sophisticated approaches to handling multimodal and non-stationary robot dynamics. His research on stochastic Model Predictive Control further refined safe, high-performance path following through context-aware cost shaping and meta-learning strategies pairing forward and inverse models. Early work on automated rock fragment identification using time-of-flight cameras (2014, 30 citations) reflects his broader interest in practical robotic perception for industrial applications. Collectively, McKinnon's contributions advance the frontier of trustworthy, adaptive autonomy for robots deployed in unstructured, long-duration settings.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5
- 6
- 7