- Introduction and Preliminaries
- Control Systems
- Modeling a Physical System
- Laplace Transform
- Control System Design
- Types of Control Strategies
- Home
- Skill Lync
- Courses
- Post Graduate Program in Motion Control
Post Graduate Program in Motion Control
All you need to know about motion control of autonomous vehicles can be learnt in Skill Lync’s 12-month Masters Certification Program in Motion Control.
Online
48 Weeks
Quick facts
particular | details | |
---|---|---|
Medium of instructions
English
|
Mode of learning
Self study
|
Mode of Delivery
Video and Text Based
|
Course overview
Motion control applications are plenty, especially when it comes to production lines where efficiency, power, and accuracy of movements are a must. A sub-field of automation, motion control of autonomous vehicles facilitates effortless movement of heavy materials between workstations.
Do you want to have an in-depth understanding of this exciting field? Then, enrol yourself in the Master's Certification Program in Motion Control by Skill Lync. Within a duration of 12 months, this course seeks to impart detailed knowledge of the functioning of autonomous vehicles, including the role of ADAS or Advanced Driver Assistance Systems.
There are a total of six courses in the program, with each course covering different topics. As a part of this Masters Certification Program in Motion Control syllabus, you will work on four different projects.
The Master’s Certification Program in Motion Control fee options is flexible with basic, pro, and premium plans to choose from. The facilities and the access duration for the course materials depend upon the payment plan you choose. Course completion certificates will be offered to all, but only the top 5% of the class will receive a merit certificate.
The highlights
- 12-month course duration
- Online mode of delivery
- CSE domain
- 5 courses in the program
- Course counselling available
- 4 projects to work on
- Flexible course plans
- Certificate of merit and completion available
- Placement support available
- Individual video support is available based on the chosen plan
- Top-class instructors
- Comprehensive curriculum
Program offerings
- Demo session
- Online learning model
- Flexible course plans
- Placement support
- Certification of merit and completion
- Individual video support
- Top instructors
- Comprehensive curriculum
Course and certificate fees
Flexible learning plans are available, and the course fee differs for each plan. You can choose the Basic plan, which offers 9 months of access to the course materials, the Pro plan which gives 18 months of access, or the Premium plan which provides lifetime access. The fee for each plan is not a one-time payment but must be paid every month for 10 months.
The facilities you receive will differ from plan to plan. To check them out, click here: https://skill-lync.com/computer-science-engineering-courses/masters-motion-control/about
Master’s Certification Program in Motion Control fee structure
Type of plan | Fee Amount (in INR) to be paid every month for 10 months |
Basic | Rs. 17500 |
Pro | Rs. 22500 |
Premium | Rs. 27500 |
certificate availability
certificate providing authority
Eligibility criteria
Though there are no specific Masters Certification Program in Motion Control eligibility criteria, it is preferred if you are an undergrad or graduate in electronics, electrical, mechanical, or aerospace engineering.
What you will learn
After completion of the Master’s Certification Program in Motion Control course, you will get a thorough understanding of the following–
- Autonomous vehicle controls
- Fundamentals of automotive systems and controls
- Model predictive controls, including the bicycle model and non-holonomic model
- Robust controls that deal with uncertain parameters of a system
- Optimal controls
- Deep reinforcement learning and control, which is a part of Machine Learning (ML)
Who it is for
The course is ideal for –
- Undergraduates and graduates, preferably in fields like Electronics, Electrical, Mechanical, or Aerospace Engineering who wish to have a thorough understanding of autonomous vehicles’ motion control
- PhD or Postgraduate learners of the same fields
Admission details
- Click here: https://skill-lync.com/computer-science-engineering-courses/masters-motion-control/about#pricing to visit the course website.
- Opt for a one-on-one demo session to understand the course better.
- Click on ‘Enrol Now’ and sign up or log into your Skill Lync account by giving simple details like your name, email address, etc.
- Make the required fee payment based on the plan of your choice.
- Secure a seat.
Filling the form
The online application must be filled to create an account with Skill Lync. You will need to enter details like your name, email address, and self-create password. Once that is done, just pay the fee, and you’re good to go.
The syllabus
Course 1: Automotive Systems and Controls using MATLAB/Simulink
Week 01 - Introduction to Modelling Techniques - Part I
Week 02 - Introduction to Modelling Techniques - Part II
- Modeling Techniques: Nonlinearities and Control
- Mathematical Modelling of Systems
- Mechanical
- Electrical
- Fluid system
- Thermal system
- Nonlinearities
- Effects of Nonlinearities
- Linearization
Week 03 - System Analysis - Part I
- System Analysis: Model Reductions
- Block Diagrams
- Signal-Flow Graphs (SFGs)
- Mason’s Rule
- SFGs of Differential Equations
Week 04 - System Analysis - Part II
- System Analysis: Fundamental Elements
- Poles, Zeros, and System Response
- First-Order Systems
- Second-Order Systems
- Higher-Order Systems
- System Response with Zeros
- Analysis of Block Diagrams
- Modifying the System Response
Week 05 - System Analysis - Part III
- System Analysis: Stability
- Routh-Hurwitz Criterion
- Special Cases of Routh-Hurwitz Criterion
- Steady-State Errors for Unity Feedback Systems
- Static Error Constants and System Type
- Steady-State Errors for Non-Unity Feedback Systems
- Sensitivity
Week 06 - System Analysis - Part IV
- System analysis: Root locus
- Definition of Root Locus
- Conditions of Root Locus
- Sketching the Root Locus – Part I
- Sketching the Root Locus – Part II
- Pole Sensitivity
Week 07 - Design Techniques - Part I
- Design Techniques: Bode and Nyquist Plots
- Bode Plots
- Gain Margin and Phase Margin
- Polar Plots
- Nyquist Plots
- Stability Analysis using Nyquist Plots
Week 08 - Design Techniques - Part II
- Design Techniques: Compensators - Part I
- Automatic Control Systems
- PID Controller Design using Ziegler-Nichols Rules
- Lag Compensation
- Lead Compensation
- Lag-Lead Compensation
- Computer-Based Design
- Physical Realization of Compensation
- Systems with Time-Delay
Week 09 - Design techniques – Part III
- Design Techniques: Compensators - Part II
- Gain Adjustment
- Lag Compensation
- Lead Compensation
- Lag-Lead Compensation
Week 10 - State-Space representation - Modelling and analysis
- State-Space Representation: Modelling and Analysis
- State-Space Representation
- State-Space to Transfer Functions
- Transfer Functions to State-Space
- Alternative Representations in State-Space
- Controllability
- Observability
- Stability in State-Space
Week 11 - State-Space representation - Design
- State-Space Representation: Design
- Similarity Transformations
- Controller Design
- Alternative Approaches to Controller Design
- Observer Design
- Alternative Approaches to Observer Design
Week 12 - Digital Control Systems and Future Scope
- Digital Control Systems and Future Scope
- Modeling the Digital Computer
- The Z-Transform
- Transfer Functions
- Stability
- Transformations
Course 2: Model Predictive Controls for Autonomous Driving
Week 1 - Introduction to Linear Algebra and Controls
- Linear Algebra Refresher
- Basics of Controls
Week 2 - Motion Models for Autonomous Driving
- Motion Models
- Lateral and Longitudinal Dynamics
Week 3 - Getting a Hold on LQR for Goal Reaching
- Linear Quadratic Regulator
- Problem Formulation
- Stability and Controllability of LQR
- Convergence of LQR
- Using LQR and Motion Model for a goal-reaching problem
Week 4 - Introduction to Convex and Non Convex Optimization
- Basics of Convex Optimization
- Introduction to Non-Linear Cost Function
Week 5 - Introduction to MPC
- Introduction to MPC
- Feedback in Optimal Control
- The Specialty of MPC’s Model
- Structure of LQR and What MPC Adds to it?
- Online Feedback
Week 6 - MPC for Goal Reaching Problem
- Sequential Quadratic Programming
- Tutorial on CVX_OPT
- Coding MPC
- MPC for Multiple-step Problem
Week 7 - Constrained MPC
- QP to MPC
- Constraints of MPC
- Static Obstacle Avoidance - Theory
Week 8 - MPC for Collision Avoidance
- MPC for a Static Obstacle in Practice
- Multiple Static Obstacle Condition
- MPC for Dynamic Obstacles
- Adding Pedestrians to Constraints
Week 9 - Lateral Conditions of MPC
- Lane Keeping Constraints in MPC
- Lane Change condition
Week 10 - Uncertainty in MPC
- Adding Uncertainty to a Motion Model
- Types of MPC and Different Cost Formulations
Week 11 - Setting Up CARLA Simulator
- Setting up CARLA
- Using CARLA to run a small client-server controller
- Testing PID in CARLA
Week 12 - Future Scope of MPC
- Future Scope of MPC
- MPC with Deep Learning Approach
- Details on Project Implementation
Course 3: Robust Controls
Week - 1 - Introduction
- Motivation
- Preliminaries
- Engineering background of robust control in automobiles
- Techno-commercial evaluations
- Business implications
- Future scope
- Fundamentals of non-linear/linear systems
- Linear algebra and function analysis
- Basic control theory
- System performance
- Mathematical modelling
Week - 2 - Robust control Fundamentals – Part 1
- Robust control fundamentals:
- Time domain and frequency domain properties
- Stabilization of linear systems
- Optimization theory
- Basics of convex analysis and linear matrix inequalities (LMI)
Week - 3 - Robust control Fundamentals – Part 2
- Robust control fundamentals:
- Algebraic Riccati equations
- Limitations of feedback control
- Robust Analysis: Small gain principle
- Robust Analysis: Lyapunov method
- Robust control of parametric system
Week - 4 - Robust control Fundamentals – Part 3
- Robust control theory:
- H_{2} control
- H_{\infty} control
Week - 5 - Hands-on demonstration
- Implementation of triple inverted pendulum in MATLAB/Simulink
- Explanation of the design theory
- Computer simulations
Week - 6 - Hands-on - 2
- Implementation of triple inverted pendulum in MATLAB/Simulink
- Explanation of the design theory
- Computer simulations
Week - 7 - Advanced Robust control Theory – Part 1
- Robust control fundamentals:
- Mu synthesis
- Regional pole placement
- Gain scheduled control
- Disturbance Observers
Week - 8 - Advanced Robust control Theory – Part 2
- Robust control fundamentals:
- Repetitive control for time-delayed systems
- H_{\infty} loop shaping control
- Integral quadratic constraint (IQC) control
Week - 9 - Hands-on - 3
- Implementation of hard disk drive in MATLAB/Simulink
- Explanation of the design theory
- Computer simulations
Week - 10 - Hands-on - 4
- Implementation of distillation column in MATLAB/Simulink
- Explanation of the design theory
- Computer simulations
Week - 11 - Hands-on - 5
- Implementation of a rocket in MATLAB/Simulink
- Explanation of the design theory
- Computer simulations
Week - 12 - Hands-on - 6
- Implementation of flexible link manipulator in MATLAB/Simulink
- Explanation of the design theory
- Computer simulations
Course 4: Optimal Controls
Week 01 - Introduction to optimal controls
- Terminology and notations
- General mathematical expressions
- Optimal control for static systems
- Constrained parameter optimization
- Unconstrained parameter optimization
Week 02 - Optimal controls for dynamic systems (Part 1)
- Calculus of variations
- Brachistochrone theory and example
Week 03 - Optimal controls for dynamic systems (Part 2)
- Two-point boundary value theory
- Introduction to Lagrange multipliers
- Geometric meaning of Lagrange multipliers
- Equality & inequality constraints
Week 04 - Optimal feedback control
- Neighbouring extremals
- Hamilton-Jacobi-Bellman (HJB) equation
- Pontryagin's minimum/maximum principle
- Transversality conditions
Week 05 - Dynamic programming
- Principle of optimality
- Dynamic programming theory
- Connection between dynamic programming and Pontryagin’s maximum principle
Week 06 - Linear Quadratic Regulator (LQR) Problems (Part 1)
- LQR theory and derivation
- Riccati equations and their properties
- Linear systems with quadratic criteria
Week 07 - Linear Quadratic Regulator (LQR) Problems (Part 2)
- Case with input constraints - the minimum principle
- Case with minimum time constraints
- Case with path constraints
- Singular arcs
Week 08 - Introduction to stochastic processes
- Expectation Operator
- Gaussian Random Variables
- Stochastic Processes
Week 09 - Optimal filtering theory (Part 1)
- Introduction
- Estimation of parameters using weighted least squares
- Linear Kalman filter derivation
Week 10 - Optimal filtering theory (Part 2)
- Extended Kalman Filter (EKF) derivation
- Duality of optimal control and optimal estimation
Week 11 - Linear Quadratic Gaussian (LQG)
- LQG theory and design
- Infinite horizon LQG
- Optimal feedback control in the presence of uncertainty
Week 12 - Tracking/disturbance rejection/Model Predictive Control (MPC)
- Introduction and fundamentals of model predictive control for autonomous vehicles
- Autonomous trajectory tracking and path following using MPC
- Vehicle Lateral and Longitudinal Control
Course 5: Deep Reinforcement Learning and Control
Week 01 - Introduction, Course Overview, and Reinforcement Learning Motivation
- Introduction to the course
- What to expect, and pre-requisites
- Motivation and fundamental framework of Reinforcement Learning
- Roots from behaviourism
- Different module definitions
- Terminology and Notation
- Mathematical description
- Goal of RL
- Real-world comparison
Week 02 - MDP
- Markov Decision Process
- Markov Property
- Rewards, decision and transition probability relationship
- Episodic Horizon and continuing tasks
- Intro to partially observable MDPs
Week 03 - RL Learning Process, Value Function and variants
- Bellman Equation
- State Value function (Math and applied)
- State-action value function (Q) (Math and applied)
- Off- and On-policy RL
- Exploration – exploitation tradeoff
- Exploration strategies
- e-greed algorithm
Week 04 - NN, Policy Gradients and Baselines
- Introduction to policy gradients
- Policy gradients and RL
- Likelihood ratio
- Dealing with Variance in PG
- Baselines
- Neural networks and PG (Python and Tensorflow/Pytorch)
Week 05 - Monte Carlo, Temporal Difference, Actor-critic and Value Function Methods
- DQN, SARSA and REINFORCE algorithms
- IID assumptions and experience-replay
- Monte Carlo estimations
- Eligibility traces
- Advantage estimation
- Introduction to Monte Carlo tree search
Week 06 - Deep Q-learning Algorithm, Application and Implementation
- DQN Algorithm
- Introduction to RL in MATLAB
- Problem formulation as MDP ( Theory and MATLAB)
- Implement DQN and different reward structures to see convergence and difference on a MATLAB grid-world environment
Week 07 - RL in Continuous Space
- Traditional Algorithms in continuous MDP domains
- Episodic estimates and extensions to continuous domains
- Policy gradient variations
- Value-based extensions
Week 08 - Policy-based Methods, Actor-critic and Algorithm
- Proximal Policy Optimization
- Trust-region policy optimization
- Extensions to Actor-critic algorithms
- Introduction to Human-level control learning paper
- Deep deterministic Policy gradient algorithm
Week 09 - Model-based Reinforcement Learning
- Model definitions
- Tabular implementation
- DYNA architecture
- DYNA algorithmic implementations
- Dealing with uncertain and/or dynamic models
Week 10 - Case Studies and Use Cases
- AlphaZero
- AlphaGo
- Atari state-of-the-art implementations
- Industrial Robots
- Manufacturing Applications
- Real-world implementations
- Introduction to “ RL that matters” paper and corresponding literature
- Thought process and problem formulation for an autonomous vehicle problem
Week 11 - Practical Implementation
- Continuous actor-critic algorithm formulation for an autonomous vehicle problem
- Programming in python
- Learning with different optimization techniques like RMSProp / ADAM
- Implementation using Tensorflow/Pytorch libraries
Week 12 - Extensions to RL
- Multi-agent RL
- Hierarchical Learning
- Transfer and curriculum Learning
- Distributed implementations
- Sim-2-real architectures
Evaluation process
Skill Lync offers two kinds of Masters Certification Program in Motion Control certification. The certificate of completion will be offered to all learners. However, based on your performance in the different projects, you will be graded. The top 5% of the learners will be awarded a merit certificate.
How it helps
One major benefit of Skill Lync’s Masters Certification Program in Motion Control is that the curriculum is extensive. Within the 12-month period, you will receive information that is thorough and capable of landing you a dream Engineering job in the automotive or aerospace sector. Plus, since you will work on four different projects throughout the course duration, you will get the hands-on experience which is a major competitive advantage.
FAQs
Three different course plans are available – Basic, Pro, and Premium. The fee for each of the plans differs, which must be paid every month for 10 months.
After pursuing this course, you can build a career in engineering in automobile or aerospace companies. You can even join companies like consultancy services and Y-Combinator startups.
Yes, job assistance facilities are available.
You will work on four different projects, namely, DC motor analysis, HEV controller design, Mathematical model for active suspension of an automobile, and control strategy for active suspension of an automobile.
You can get on a call with one of the representatives by contacting Skill Lync at 8939850851.