Matthew Budd
Papers
3
Total Citations
20
H-Index
2
About
Matthew Budd is a robotics researcher specializing in safe autonomous exploration under uncertainty. His work sits at the intersection of decision theory, Gaussian processes, and risk-aware motion planning for mobile robots. Budd’s core contribution is developing rigorous frameworks that allow robots to explore unknown environments while formally guaranteeing safety—defined as staying within regions where critical environmental features (e.g., terrain steepness or radiation levels) remain below dangerous thresholds. His most cited paper, “Markov Decision Processes with Unknown State Feature Values for Safe Exploration using Gaussian Processes” (2020, 14 citations), introduced a novel method for balancing exploration and exploitation when feature values are unknown, using Gaussian process regression to model uncertainty and inform safe decision-making. This work has been extended in his 2024 paper “Planning under uncertainty for safe robot exploration using Gaussian process prediction” (5 citations), which addresses real-time planning challenges. Budd’s research is particularly impactful for field robotics applications—such as planetary rovers, disaster response, and environmental monitoring—where failure can be catastrophic. His correction notice (2024, 1 citation) underscores his commitment to reproducibility and rigor. By bridging probabilistic machine learning with control theory, Budd is helping to make autonomous exploration both ambitious and safe.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3