Course

Unit I

Mathematical Concepts Review- Linear Algebra, Probability & Statistics Fundamentals. Descriptive Data Analysis – Central Tendency, Dispersion, Visualization. Supervised Learning Basics – k-NN, Naive Bayes, Decision Trees, Ensemble Methods. Regression Techniques – Ordinary Least Squares. Classifier Performance Metrics – Precision, Recall, F1 Score.

Unit II

Artificial Neurons, Perceptron, Multi-Layer Perceptron (MLP), Backpropagation Algorithm, Hyperparameter Tuning, Sensor Data Processing and Real-Time Perception, Motion Planning and Control Computer Vision: Object Detection, Scene Understanding NLP in Robotics: Voice-Controlled Systems Cluster Analysis: K-Means, DBSCAN

Unit III

Reinforcement Learning – Policy Learning, Reward Modeling. Cognitive Robotics – Reasoning and Planning in Uncertain Environments. AI in Manufacturing – Predictive Maintenance, Smart Automation. Human-Robot Interaction (HRI) – Safety, Usability. Ethics & Safety in AI Robotics – Bias, Transparency, Responsible Design

Unit IV

Sensors & Actuators – Classification, Operation Principles, Calibration. Conventional Sensors – Thermocouples, Inductive, Capacitive, Piezoelectric, Encoders. Basic Actuators – Electromechanical, Electrical Machines. Fuzzy Set Theory – Fuzzy vs. Crisp Sets, Operations. Fuzzy Logic & Control: Mamdani and Sugeno Models, Applications in Robotic

Learning Objectives
LO1. Gain foundational knowledge in linear algebra, probability, and statistics for AI
           algorithms.

LO2. Learn and apply supervised, unsupervised, and neural network-based learning techniques
          to solve robotics problems.

LO3. Understand AI applications in vision, language processing, and real-time robotic
          perception and decision-making.

LO4. Explore reinforcement learning, cognitive robotics, and design for intelligent robotic
          systems.

Course Outcomes

CO1: Apply mathematical, statistical, and supervised learning methods to analyze data and build
          classification/regression models for robotic applications.

CO2: Design and train neural networks for perception, motion control, and decision-making in
           robotic systems.                                             

CO3: Implement computer vision, natural language processing, and clustering algorithms for
           real-time perception and environment understanding in robotics.

CO4: Apply reinforcement learning and cognitive robotics principles to robotic learning and
           planning, while addressing ethical and safety issues. 

CO-PO Mapping

Textbooks:

1. Stuart Russell and Peter Norvig, Artificial Intelligence: A Modern Approach, Pearson.

Robin R. Murphy, Introduction to AI Robotics, MIT Press

2. J. Russell and P. Norvig. Artificial Intelligence: A Modern Approach (3rd edition), Prentice-Hall, 2010.
3. J.Klir & Bo Yuan, “Fuzzy Sets and Fuzzy Logic Theory and Applications”, Prentice Hall of India, 2009
4. Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, Second Edition, O’Reilly Media, 2019.

Reference

1. Aurélien Géron, Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, Second Edition, O’Reilly Media, 2019.
2. Earl Gose, Richard Johnsonbaugh, Steve Jost, Pattern Recognition and Image Analysis, Pearson Education India, 2015.
3. Clarence W. de Silva (2015) Sensors and Actuators: Engineering System Instrumentation, Second EditionAndrzej M Pawlak (2006) Sensors and Actuators in Mechatronics: Design and Applications
4. Timothy S.Ross, “Fuzzy Logic with engineering applications”, Weily India Pvt. Ltd., 2011.
5. Rao V.B and Rao H.V., “C++, Neural Networks and Fuzzy Logic”, BPB Publications