Papers
5
Total Citations
145
H-Index
3
About
Ross Allen is a robotics and controls researcher whose work bridges the gap between theoretical guarantees and real-time autonomous decision-making. His most influential contribution is a machine learning approach for real-time reachability analysis (65 citations), which enables robots to determine whether a desired state is reachable within cost constraints—a fundamental problem in controls and optimization. He extended this work to kinodynamic planning for quadrotors in dynamic environments (48 citations), providing a practical framework for obstacle avoidance that has informed the development of agile aerial robots. Allen also made notable contributions to space robotics with internally-actuated rovers for all-access surface mobility on small Solar System bodies (27 citations), addressing the unique challenges of weak-gravity locomotion. More recently, he has explored multi-agent systems, proposing health-informed policy gradients for reinforcement learning (2019) and distributed online planning for min-max problems in networked Markov games (2024). His research consistently integrates rigorous mathematical foundations with deployable algorithms, making him a key figure in advancing autonomous systems that must operate safely and efficiently under real-world constraints.
Research Focus
Key Achievements
Top Papers
- 1A machine learning approach for real-time reachability analysis65 citations · 2014
- 2
- 3
- 4Health-Informed Policy Gradients for Multi-Agent Reinforcement Learning3 citations · 2019
- 5