By IIT Roorkee
This course covers the fundamentals of robotics and intelligent control. It explores essential topics such as fuzzy logics, neural networks, and reinforcement learning, with MATLAB-based simulation studies to help bring theory into practice.
-
Anatomy, Actuation, Sensing, and Programming
Discover the basic components of a robot—how it is built, how it moves, senses its environment, and is programmed to perform tasks. This module lays the foundation for understanding robot structure and function. 🛠️ -
Control – Kinematic Control Strategies
Learn how robots use geometry and movement relationships (kinematics) to control their motion. This section introduces strategies for planning movements based on position and orientation. 📐 -
Dynamic Robot Control Strategies
Dive into methods that consider forces and inertia (dynamics) to achieve precise and smooth robot movements. Ideal for understanding how robots react to real-world conditions. ⚙️
-
Review of Fuzzy Logics – Sets and FLC using Lyapunov Analysis
Explore fuzzy logic, a technique that handles uncertainty and approximate reasoning, and see how Lyapunov analysis helps in ensuring system stability. 📊 -
Fuzzy C-means Clustering for Redundant Robot Arm Control
Understand how clustering algorithms, like Fuzzy C-means, optimize the control of robot arms that have extra degrees of freedom, allowing for more efficient movements. 🤹 -
Takagi-Sugeno Fuzzy and Mamdani Fuzzy Based Control of Mobile Robots
Learn two prominent fuzzy control methods applied to mobile robots to manage their behavior in uncertain environments, ensuring smoother and more adaptive control. 🚀
-
Review of Neural Networks
Get an introduction to neural network models, including the Perceptron, Single Layer Perceptron, Multi Layer Perceptron, and Radial Basis Function networks, which are key to modern control systems. 📚 -
Neural Network Feedback Linearization Controller
Discover how neural networks can be employed to simplify (linearize) complex robot dynamics, making it easier to design effective control strategies. 🔄 -
Radial Basis Function Based Neural Network Controller
Focus on a specialized neural network approach used for trajectory tracking of a robot arm, ensuring accurate and smooth movements during operation. 🎯
-
Search Method – A-star and Planning Method – RRT Approaches
Learn about search algorithms like A-star for finding the shortest paths and RRT (Rapidly-exploring Random Tree) for planning feasible routes in complex spaces. 🗺️ -
Introduction to Reinforcement Learning (RL) – Environment, Reward, Agent
Gain a primer on reinforcement learning, where an agent learns optimal behaviors through trial and error within an environment, guided by rewards and penalties. 🎓 -
Application on 2-DOF, 3-DOF Non-planar Robots for Position/Force Control
See practical applications where robots with two or three degrees of freedom are controlled for precise positioning and force application, bridging theory with real-world tasks. 🤖