Peter T. Jardine
Papers
7
Total Citations
63
H-Index
5
About
Peter T. Jardine is a leading researcher in autonomous systems, specializing at the intersection of model-predictive control (MPC), reinforcement learning, and multi-robot coordination. His most impactful work introduces a novel framework that uses reinforcement learning to automatically tune the objective function weights in adaptive predictive controllers—a critical step that traditionally relies on tedious trial-and-error. This approach, detailed in his top-cited paper (28 citations), enables differential drive robots to achieve optimal performance without manual calibration. Jardine further advanced the field with a robust model-predictive guidance system for autonomous vehicles navigating cluttered environments (12 citations), guaranteeing constraint satisfaction and obstacle avoidance even under bounded uncertainties. His contributions extend to self-assembly systems, where he pioneered formation and pinning control algorithms that allow teams of mobile robots to autonomously construct three-dimensional structures. With a growing citation record and a focus on data-driven control, Jardine’s work bridges theoretical control design with practical, learning-based implementations, making him a key figure in the development of intelligent, resilient autonomous systems for real-world applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3Machine Learning for Data-Driven Control of Robots7 citations · 2018
- 4
- 5
- 6
- 7