Comprehensive Course Listing Across Eight Semesters

Detailed Overview of Advanced Departmental Electives

Artificial Intelligence: This course introduces students to the foundational concepts of AI, including search algorithms, knowledge representation, and expert systems. Students learn to implement decision-making frameworks using logic-based approaches and develop intelligent agents capable of autonomous behavior in complex environments.

Machine Learning: Focused on supervised and unsupervised learning techniques, this course explores regression models, classification algorithms, clustering methods, and deep neural networks. Practical assignments involve building predictive models using real-world datasets.

Computer Vision: This course covers image processing, feature extraction, object detection, and recognition systems. Students gain proficiency in OpenCV and TensorFlow while working on projects involving facial recognition, autonomous vehicle navigation, and medical imaging analysis.

Reinforcement Learning: Designed for advanced learners, this subject delves into Markov Decision Processes, Q-learning, policy gradients, and actor-critic methods. Students implement reinforcement learning agents in simulated environments and apply them to robotics tasks.

Neural Networks: A comprehensive study of artificial neural networks, including feedforward, recurrent, convolutional, and generative adversarial networks (GANs). The course emphasizes practical implementation using Python libraries like PyTorch and Keras.

Embedded Systems: This elective focuses on designing and developing embedded software for microcontrollers. Students learn real-time programming, hardware-software integration, and IoT connectivity using platforms such as Arduino and Raspberry Pi.

Control Systems: An in-depth exploration of feedback control theory, system modeling, stability analysis, and controller design. Practical components include designing controllers for robotic systems and simulating them using MATLAB/Simulink.

Sensors and Actuators: Students study various types of sensors (e.g., accelerometers, gyroscopes, proximity sensors) and actuators (e.g., servos, stepper motors). The course includes lab sessions where students integrate sensor data into control systems for robotics applications.

Robot Kinematics: This course examines the geometric aspects of robot motion, including forward and inverse kinematics, workspace analysis, and trajectory planning. Students use mathematical tools to solve complex robotic positioning problems.

Human-Robot Interaction: Explores how robots can effectively communicate and collaborate with humans through speech recognition, gesture interpretation, and emotional computing. Case studies include assistive robotics for elderly care and social robots in educational settings.

Project-Based Learning Philosophy

The department strongly advocates for project-based learning as a core pedagogical method. Projects are structured to encourage interdisciplinary thinking and practical application of theoretical knowledge. Students begin with guided mini-projects in the third year, progressing to independent capstone projects in their final year.

Mini-projects involve team collaboration on tasks like building a line-following robot or designing a simple manipulator arm. These projects help students understand real-world constraints and develop essential problem-solving skills.

The final-year thesis/capstone project is a significant milestone, requiring students to define a research question, conduct literature review, propose solutions, build prototypes, and present findings. Faculty mentors guide students throughout the process, ensuring alignment with industry standards and academic rigor.

Students can choose their projects based on personal interests or proposed by faculty members working on active research grants. The selection process involves interviews with potential advisors to ensure compatibility between student aspirations and mentor expertise.