Ricardo Pezzuol Jacobi

About

Ricardo Pezzuol Jacobi is a leading researcher at the intersection of embedded systems, control theory, and machine learning, with a particular focus on the hardware acceleration of complex algorithms. His primary contributions lie in the real-time implementation of Nonlinear Model Predictive Control (NMPC) on Field-Programmable Gate Arrays (FPGAs). Jacobi’s most cited work, a 2016 paper on custom-precision floating-point operations for NMPC (12 citations), addresses a critical bottleneck in industrial control: solving optimization problems within strict real-time constraints. He further advanced this field by developing FPGA-based hardware-in-the-loop (HIL) simulation flows for strongly coupled linear systems, using Gaussian elimination to achieve high performance. In a notable fusion of machine learning and control, Jacobi also created the BIOTS tool, a multi-objective particle swarm optimizer that tunes Support Vector Machine hyperparameters specifically for NMPC applications. His work is instrumental in bridging the gap between sophisticated, computationally intensive algorithms and their practical deployment in embedded, real-time environments, making him a key figure in the evolution of intelligent, hardware-accelerated control systems.

Research Focus

Key Achievements

Top Papers

1. 1
   Nonlinear model predictive control hardware implementation with custom-precision floating point operations

   12 citations · 2016
2. 2
   FPGA HIL simulation of a linear system block for strongly coupled system applications

   6 citations · 2013
3. 3
   A SVM optimization tool and FPGA system architecture applied to NMPC

   5 citations · 2017

Key Collaborators

Contact & Links