Rafael Oliveira

Papers

Total Citations

H-Index

About

Rafael Oliveira is a researcher whose work sits at the intersection of probabilistic machine learning, Bayesian optimization, and control systems. His research addresses fundamental challenges in deploying intelligent controllers in real-world environments, where uncertainty, complex dynamics, and safety constraints must all be carefully managed. Among his notable contributions, Oliveira has explored how Bayesian optimization can enable safe robotic navigation under localization uncertainty, a critical problem for autonomous systems operating in unpredictable settings. His work on DISCO — Double Likelihood-free Inference Stochastic Control — tackles the challenge of controlling complex physical systems whose governing equations resist analytical treatment, enabling simulation-based strategies without requiring tractable likelihood functions. Complementing this, his research on heteroscedastic Bayesian optimization for stochastic model predictive control advances the field by explicitly accounting for input-dependent noise in system dynamics, improving the robustness of MPC frameworks in uncertain environments. While his papers are in the early stages of accumulating citations — each currently cited twice — they collectively represent a coherent and forward-looking research agenda that bridges principled probabilistic inference with practical control engineering, positioning Oliveira as an emerging voice in data-driven and uncertainty-aware autonomous systems.