Behzad Samadi

Behzad Samadi

Director of Innovation and Engagement

Advanced Intelligent Systems

Biography

Behzad Samadi has worked as a Research Engineer at the R&D Centre of Irankhodro Industrial Group, Assistant Professor at Amirkabir University of Technology and a Research Associate at Concordia University. He then joined Maplesoft in 2012. He worked as a Senior Research Engineer to help Japanese car manufacturers including Toyota to employ model-based automatic code generation. He has founded Nubonetics to help robotics and manufacturing companies with their AI, industrial IoT, and cloud computing roadmap. His main areas of research are machine learning, model-based product development, modeling and control of automotive systems (chassis control, engine control, autonomous driving), convex optimization, robotics, piecewise smooth systems, 3D simulation of mechatronic systems, uncertainty analysis and model based fault detection and isolation.

Interests

  • Machine Learning
  • Automatic Code Generation
  • Model Predictive Control
  • Reinforcement Learning
  • Convex Optimization
  • Fault Detection, Isolation and Accommodation
  • Estimation Theory

Education

  • PhD in Mechanical Engineering, 2008

    Concordia University

  • MSc in Electrical Engineering, 1999

    Amirkabir University of Technology

  • BSc in Electrical Engineering, 1996

    Sharif University of Technology

Recent Posts

Convex Optimization: A Practical Guide

Python scripts included

Product Design Space

My current mind map

Model Based Reinforcement Learning

Is MBRL=MPC?

Estimation Theory

Kalman filtering made easy

Projects

Computational Tools for Piecewise Affine Systems

PWATOOLS is a set of tools for the analysis and design of piecewise affine (PWA) systems.

Model based automatic code generation for nonlinear model predictive control

Symbolic computation methods are employed to generate optimized C code for nonlinear model predictive controllers.

Talks

Nonlinear Model Predictive Control Webinar

Virtual Prototyping

Controller Synthesis for Nonholonomic Robots

This is an embedded Microsoft Office presentation, powered by Office Online.

Publications

Quickly discover relevant content by filtering publications.

Model based automatic code generation for nonlinear model predictive control

This paper demonstrates a symbolic tool that generates C code for nonlinear model predictive controllers. The optimality conditions are …

Design environment for nonlinear model predictive control

Model Predictive Control (MPC) design methods are becoming popular among automotive control researchers because they explicitly address …

Piecewise-affine approximations for a powertrain control verification benchmark

We present a benchmark example of an automotive powertrain control system converted to a hybrid system with piecewise-affine (PWA) …

A sum of squares approach to backstepping controller synthesis for piecewise affine and polynomial systems

This paper addresses backstepping controller synthesis for piecewise affine (PWA) systems. The main contribution of the paper is to …

Estimation of region of attraction for polynomial nonlinear systems: A numerical method

This paper introduces a numerical method to estimate the region of attraction for polynomial nonlinear systems using sum of squares …