PG Diploma in Embedded AI with Robotics Applications (A Job-Oriented Training Program)
Durations – 500 Hrs.
Program Outline
Core Programming
- Mastering C Programming
- DSA & Competitive Problem Solving in C
- Mastering OOP using C++
- Electronics and Hardware Familiarization
- ARM Cortex-M Architecture & Embedded
- Embedded Protocols & Driver Development
- Linux System Programming using C
- Linux Device Driver & Kernel
- Embedded RTOS (FreeRTOS)
- Machine Learning Fundamentals & Advanced ML
- Deep Learning using TensorFlow
- Natural Language Processing
- Generative AI & Agentic AI
Tools / Software / Hardware
- Keil µVision, LPC1768
- Python, Pandas, NumPy
- TensorFlow, PyTorch, OpenCV
- Raspberry Pi 4
- IoT Cloud Platforms
- HackerRank, LeetCode
- VS Code, Dev-C++
Capstone Projects
- Competitive Programming
- Database Applications
- Machine Learning
- Embedded & RTOS Projects
- Linux Programming
- Deep Learning & NLP
- Generative AI
- Computer Vision & Robotics
Industry Job Roles
- Embedded Systems Engineer
- Firmware Developer
- Linux System Engineer
- AI / ML Engineer
- Robotics Engineer
- Software Developer (C/C++/Python)
Core Programming Fundamentals
Module 1 • Mastering C Programming 40 hrs
Key Skills: Program structure · Arrays · Functions · Searching & Sorting · Strings · HackerRank
| Introduction to C: simple C program structure, literals, constants, variables | Operators with precedence and associativity | Control flow statements with examples |
| Modular programming using functions | Numeric arrays: 1D and 2D arrays | Character arrays and string functions |
| Searching algorithms | Sorting algorithms | Problem-solving using HackerRank |
Learner Outcome: Develop structured C programs using core language features and solve logical problems using arrays, functions, and algorithms.
Module 2 • DSA & Competitive Problem Solving in C 60 hrs
Key Skills: Complexity · Pointers · Structures · Stacks & Queues · Linked Lists · Trees · Graphs
| Time and space complexity | Utopian Tree | Viral Advertising |
| Birthday Cake Candles | Migratory Birds | Kaprekar Number |
| Pangram string and anagram string | Palindrome Index | Array Rotation |
| Pointers: declaration, initialization, types, pointer to pointers | Structures: definition, structure variable, member access, nested structures | Introduction to data structures: stacks, queues, linked lists |
| Dynamic memory allocation | Static stack and dynamic stack | Static queue and dynamic queue |
| Circular queue | Linked list: singly linked list | Doubly linked list |
| File handling using C | Trees, DFS, BFS | Graphs |
Learner Outcome: Analyze complexity and implement data structures, algorithms, and graph traversal techniques to solve competitive programming problems.
Module 3 • Mastering OOP using C++ 54 hrs
Key Skills: Classes · Inheritance · Polymorphism · STL · Smart Pointers · Templates · Lambda
| Basic input/output: cin, cout, >> and << operators, endl, setw | Understanding namespace and introduction to OOP | Classes and objects, encapsulation, data hiding, and abstraction |
| Access specifiers – private and protected, this pointer | Constructors and destructors | Friend functions and operator overloading |
| Inheritance | Run-time polymorphism | Exception handling |
| Lambda expressions | Smart pointers | Templates |
| STL | Problem-solving using HackerRank | Project work |
Learner Outcome: Design modular and reusable applications using object-oriented principles, STL, and modern C++ features.
▶
Capstone Project • Capstone Project – Programming • Competitive programming projects in C, C++, and Python
★
CERTIFICATION MILESTONE · Certification in Programming
Core Engineering
Module 4 • Electronics and Hardware Familiarization 30 hrs
Key Skills: Analog circuits · Digital logic · Embedded architecture · Schematics · Datasheets
| Analog electronics: passive and active components | Circuit analysis using KCL and KVL | Diode, transistor, and op-amp circuits |
| Digital electronics: combinational circuits — adders, multiplexers, encoders, decoders | Sequential circuits: flip-flops, registers, counters | Microprocessors and microcontroller architecture |
| Basic embedded system architecture | Standard interfaces overview | Understanding schematics and datasheets |
Learner Outcome: Understand fundamental analog and digital electronics, embedded system architecture, and interpret hardware schematics and datasheets.
Embedded Systems Programming & Operating Systems
Module 5 • ARM Cortex-M Architecture & Embedded C Programming (LPC1768) 40 hrs
Key Skills: GPIO · ADC · Timers · LCD · Keypad · Temperature sensor · Register-level programming
| ARM Cortex-M3 architecture & LPC1768 overview | GPIO registers and GPIO programming: LED programming | Buzzer and switch programming |
| IO device programming: 16×2 LCD interfacing and programming | 4×4 matrix keypad interfacing and programming | ADC programming: LM35 temperature sensor interfacing and programming |
| Timer peripheral programming |
Learner Outcome: Develop and test embedded firmware for ARM Cortex-M microcontrollers and interface on-chip peripherals at the register level.
Module 6 • Embedded Protocols & Driver Development 40 hrs
Key Skills: PWM · RTC · WDT · PLL · NVIC · UART · SPI · SSP · I2C
| PWM peripheral programming | RTC (Real-Time Clock) | Watchdog Timer (WDT) |
| PLL (Phase-Locked Loop) & clock configuration | NVIC (Nested Vectored Interrupt Controller) & interrupt handling | UART (Universal Asynchronous Receiver Transmitter) communication |
| SPI (Serial Peripheral Interface) communication | SSP (Synchronous Serial Peripheral) communication | I2C (Inter-Integrated Circuit) communication |
Learner Outcome: Implement peripheral drivers and communication protocols for real-time embedded systems using the LPC1768 platform.
Module 7 • Linux System Programming using C 30 hrs
Key Skills: Shell commands · System calls · Process management · IPC · Multithreading · Mutex
| Linux shell commands | Manipulating files and directories | Manipulating data |
| File-related system calls | Process management | Signals |
| IPC – pipes, message queue, shared memory | Multithreading | Handling race conditions using Mutex |
Learner Outcome: Build system-level applications using Linux system calls, IPC mechanisms, and multithreading with synchronization.
Module 8 • Linux Device Driver & Kernel Programming 40 hrs
Key Skills: Kernel modules · Character device drivers · USB drivers · Major/minor numbers · EXPORT_SYMBOL
| Introduction to kernel programming | Makefile for kernel modules | Simple kernel module |
| Kernel dependency module using EXPORT_SYMBOL and extern | Passing parameters to the kernel module | Introduction to device drivers |
| Character device driver and real device driver | Major and minor numbers | Real character device driver |
| USB device driver |
Learner Outcome: Develop Linux kernel modules and character/USB device drivers for embedded hardware integration.
Module 9 • Embedded RTOS — FreeRTOS Firmware Programming 20 hrs
Key Skills: FreeRTOS tasks · Scheduling · Queues · Semaphores · ISR management · Memory management
| Overview of FreeRTOS: features and source code organization | RTOS concepts: hard real-time vs soft real-time | Multithreading, multitasking, concurrent execution |
| Scheduling and context switching | Memory management: heap vs stack, program vs data memory | FreeRTOS heap memory management and allocation schemes |
| FreeRTOS tasks APIs: creating tasks, priorities, state transitions | Scheduler algorithms, tick interrupt, idle task | Inter-task communication: FreeRTOS Queue APIs |
| Blocking read/write, receiving from multiple queues, and a mailbox | Interrupt management: events and ISRs, tasks vs ISRs | Semaphores: binary and counting semaphores |
| Resource management: shared resources and mutual exclusion |
Learner Outcome: Design real-time multitasking embedded applications using FreeRTOS scheduling, queues, semaphores, and synchronization mechanisms.
▶
Capstone Project • Capstone Project – Embedded Systems • Embedded and RTOS project on LPC1768 with multi-peripheral integration and Linux system programming
★
CERTIFICATION MILESTONE · Diploma in Embedded Programming
AI / ML & EDGE AI WITH ROBOTICS
Module 10 • Machine Learning Fundamentals & Advanced ML
Key Skills: Regression · Classification · Clustering · Ensemble · SVM · PCA · HyperParam tuning
| Introduction to machine learning | Supervised machine learning | Unsupervised machine learning |
| Train-test split the data. | ML workflow for project implementation | Regression |
| Simple linear regression | Multiple linear regression | Performance measure for regression |
| Classification and types | Logistic regression | Naïve Bayes classification |
| Decision trees and their types | K-Nearest Neighbour (KNN) classification | Performance measure for classification |
| Random Forest | Clustering and types | Evaluate clustering results, Elbow Plot |
| Optimizing regression models with forward elimination and Grid Search CV | Improving classification models with ensemble modeling | Model evaluation strategies (KFold, Stratified KFold) |
| Regularization: L1 and L2 | Bagging | Boosting techniques: ADA Boost |
| Hyperparameter tuning and SVM | Stacking and voting | Dimensionality reduction with PCA |
Learner Outcome: Build, optimize, and evaluate machine learning models for real-world embedded and IoT applications using supervised and unsupervised techniques.
Module 11 • Deep Learning using TensorFlow 24 hrs
Key Skills: ANN · CNN · RNN · LSTM · OpenCV · TensorFlow · PyTorch · Keras
| What is Deep Learning | Deep Learning methods and applications | Artificial Neural Network (ANN) |
| Hidden layers and activation functions | CNN for computer vision | Performance measures for ANN |
| Need for Hardware in Deep Learning. | Basics of image processing | OpenCV library |
| Image reading, writing, and enhancement | Edge detection, filtering, morphology | CNN architecture and its types |
| Building projects based on CNN | Need for data augmentation | Batch normalization and dropout |
| Object detection and recognition with CNN | Forward and backward propagation | TensorFlow, PyTorch, Keras |
| Recurrent Neural Network (RNN) | Long Short-Term Memory (LSTM) | Basic OpenCV functions |
Learner Outcome: Design and implement deep learning models for computer vision and sequence-based applications targeted at edge deployment.
Module 12 • Natural Language Processing 24 hrs
Key Skills: Text encoding · TF-IDF · Word2Vec · NER · Dependency parsing · Sentence embeddings
| Introduction to NLP and areas of application | Understanding the text | Text encoding |
| Word frequencies and stop words | Bag of words representation | Stemming and lemmatization |
| TF-IDF representation | Canonicalization | Phonetic hashing |
| Spell corrector | Pointwise mutual information | Gensim, Word2Vec |
| Word embeddings | Named Entity Recognition (NER) and Parts of Speech tagging | Dependency parsing and syntactic analysis |
| Semantic similarity and sentence embeddings | Bidirectional LSTM |
Learner Outcome: Develop NLP solutions for text processing, semantic understanding, and integration with AI pipelines.
✎
Assessment: Module Test (MCQ & Theory) · Technical Mock · Problem Solving using HackerRank
Module 13 • Generative AI & Agentic AI 30 hrs
Key Skills: VAE · GAN · Transformers · Prompt engineering · Zero/few-shot · Chain-of-thought
| Introduction to Generative AI | Rule-based vs neural generation | Generative Adversarial Networks (GAN) |
| Variational AutoEncoder (VAE) | Transformers | Applications of Generative AI and ethics |
| FastText and subword models | Sentence embeddings and similarity | Encoding long text documents |
| Visualizing embeddings with tools | Prompt engineering | Zero-shot and few-shot prompts |
| Chain-of-thought prompting style | System and user prompts | Common prompt engineering mistakes |
Learner Outcome: Create and apply generative AI models, transformers, and prompt engineering techniques for real-world AI applications.
✎
Assessment: Module Test (MCQ & Theory) · Technical Mock · Problem Solving using HackerRank
Module 14 • Computer Vision & Robotics using Raspberry Pi 32 hrs
Key Skills: Raspberry Pi GPIO · OpenCV · Face recognition · Object detection · TensorFlow Lite · IoT Cloud
| Overview of Raspberry Pi 4: features and architecture | GPIO programming in Python | Interfacing sensors with Raspberry Pi |
| Computer vision on Raspberry Pi | OpenCV basics on Raspberry Pi | Object detection & tracking using Haar cascades and HOG |
| Real-time face recognition on Raspberry Pi | Integration with IoT: sending CV/robotics data to the cloud for monitoring | Robotics fundamentals |
| Motor drivers (L293D, L298N) and controlling wheels/servos with Pi | Camera-based navigation using Pi Camera | Integrating robotics with computer vision |
| Deploying lightweight deep learning models (TensorFlow Lite, PyTorch Mobile) | Edge AI: object detection (YOLO Lite, MobileNet SSD) on Pi |
Learner Outcome: Deploy Edge AI and computer vision solutions on Raspberry Pi for real-time robotics applications, including object detection, face recognition, and autonomous navigation.
✎
Assessment: Module Test (MCQ & Theory) · Technical Mock · Problem Solving using HackerRank
▶
Capstone Project • Edge AI & Robotics: End-to-end computer vision and robotics project on Raspberry Pi with TensorFlow Lite deployment
★ CERTIFICATION MILESTONE • PG Diploma in Embedded AI with Robotics Applications
