Rowan Mcllister
Papers
1
Total Citations
38
H-Index
1
About
Rowan McAllister is a leading researcher in safe, uncertainty-aware autonomy, whose work bridges the critical gap between perception and motion planning for robots and self-driving vehicles. His most-cited paper, "Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty" (2022, 38 citations), tackles a fundamental challenge in robot navigation: predicting the future behavior of other agents when their type—pedestrian, cyclist, or car—is itself uncertain. By jointly reasoning over both trajectory and semantic class, McAllister’s framework enables robots to anticipate a richer, more realistic distribution of possible futures, directly improving safety in dynamic environments. This contribution is emblematic of his broader focus on probabilistic reasoning and decision-making under uncertainty, where he has developed methods that allow autonomous systems to quantify what they don’t know. McAllister’s work is highly influential in the robotics and autonomous vehicle communities, shaping how researchers model the interplay between perception noise and predictive planning. His research provides a rigorous foundation for building robots that can navigate confidently through unpredictable, human-filled spaces, making him a key voice in the pursuit of truly robust autonomy.
Research Focus
Key Achievements
Top Papers
- 1Heterogeneous-Agent Trajectory Forecasting Incorporating Class Uncertainty38 citations · 2022