Patrick Bouffard

About

Patrick Bouffard is a leading researcher in the intersection of robotics, control theory, and machine learning, with a primary focus on autonomous aerial vehicles. His most impactful work centers on the development and experimental validation of learning-based model predictive control (LBMPC) for quadrotor helicopters. Bouffard’s major contribution is demonstrating that sophisticated, data-driven control algorithms can run reliably onboard resource-constrained micro aerial vehicles in real time. His seminal 2012 paper on the onboard implementation of LBMPC, which has garnered 174 citations, rigorously combined statistical learning with control engineering to provide formal guarantees on safety, robustness, and convergence—a critical step for deploying autonomous drones in complex environments. His follow-up work, with 67 citations, detailed the full design and experimental process of applying MPC to quadrotors, establishing a practical benchmark for the field. Bouffard also conducted a practical comparison of optimization algorithms for learning-based control, further advancing the efficiency of these systems. Through his hands-on, experimental approach, he has bridged the gap between theoretical control advances and real-world robotic performance, making him a key figure in the evolution of intelligent, autonomous flight.

Research Focus

Key Achievements

Top Papers

1. 1
   Learning-based model predictive control on a quadrotor: Onboard implementation and experimental results

   174 citations · 2012
2. 2
   On-board Model Predictive Control of a Quadrotor Helicopter: Design, Implementation, and Experiments

   67 citations · 2012
3. 3
   Practical Comparison of Optimization Algorithms for Learning-Based MPC with Linear Models

   8 citations · 2014

Key Collaborators

Contact & Links