Derek Knowles
Papers
3
Total Citations
9
H-Index
2
About
Derek Knowles is a researcher at the forefront of safe and reliable multi-robot autonomy, with a focus on bridging the gap between advanced control theory and practical deployment. His work centers on three key areas: safety-constrained neural network training, multi-robot navigation under uncertainty, and connectivity maintenance for distributed systems. In his most cited work (2021), Knowles introduced a novel method for training feedforward neural networks using reachability analysis, enabling safety-critical applications like human-robot interaction—a crucial step for deploying AI in the real world. He further advanced the field by developing a multi-robot navigation algorithm using partially observable Markov decision processes (POMDPs) with belief-based rewards (2023), which simultaneously achieves goal-reaching and position uncertainty reduction. Additionally, his distributed ADMM-based trajectory planner (2020) ensures communication network connectivity despite motion and sensing uncertainties, a fundamental requirement for coordinated multi-robot missions. With a growing citation footprint, Knowles’ contributions are shaping the future of autonomous systems, making them safer, more robust, and ready for complex, real-world environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3