Yuan Ze University

Robot control and AI Lab

Syed Humayoon Shah
Under development

Research Field

Control Engineering

Introduction

Syed Humayoon Shah is a highly accomplished researcher and Assistant Professor at Yuan Ze University, with a distinguished career spanning over several years. Mr. Shah was born in Pakistan, and his research journey commenced in 2017 when he pursued a Master's degree in Mechatronics Engineering at the University of Engineering and Technology, Peshawar, Pakistan. During his studies, Mr. Shah displayed a deep passion and talent for engineering and developed a keen interest in the field of robotics, control, computer vision, deep learning. After completing his Master's degree in 2019, Mr. Shah embarked on a Ph.D. program in Mechanical Engineering, specializing in control and robotics, at the National Taiwan University of Science and Technology.

Throughout his doctoral studies, Mr. Shah exhibited an exceptional aptitude for research and innovation, and he distinguished himself by contributing significantly to the development of several groundbreaking research projects. As part of his research work, Mr. Shah worked as a Research Assistant at the Advanced Robotics Lab for three years, where he demonstrated an exceptional ability to design, implement, and execute complex research projects. His work was highly regarded and recognized by his colleagues and peers, earning him numerous accolades and honors.

Mr. Shah has also authored/co-authored several top-tier research journal and conference proceedings, showcasing his expertise and innovative thinking in the areas of robotics, control, and automation. His research has been widely cited, and his work has been highly influential in the field of engineering and technology. Mr. Shah's research interests lie in the areas of robotics, control, computer vision, deep learning, and he is continually seeking new and innovative ways to advance the fields. His research has great potential to transform the way we approach various engineering problems and has the potential to impact many industries positively.

Welcome to the Robot Control and AI Lab

The Robot Control and AI Lab is a cutting-edge research facility dedicated to pioneering advancements in the fields of robotics, control systems, computer vision, and deep learning. Situated at the forefront of technological innovation, our lab is committed to driving transformative breakthroughs in these dynamic disciplines.

Our Vision: At the Robot Control and AI Lab, our vision is to unravel the boundless potential of robotics and artificial intelligence to reshape the way we perceive, interact with, and harness technology. We strive to be at the vanguard of scientific discovery, pushing the boundaries of what is possible and fostering a profound impact on various industries and societal domains.

Research Focus Areas:

Robotics: Our lab delves into the intricate world of robotics, investigating the creation of intelligent machines capable of executing tasks autonomously and efficiently. We explore robotic systems' design, kinematics, dynamics, and real-time control strategies, aiming to unlock unprecedented levels of precision and functionality.

Control Systems: We specialize in the development and optimization of advanced control systems that enable seamless interaction between humans and machines. Our research spans classical and modern control techniques, encompassing adaptive control, optimal control, and robust control strategies to enhance system stability and performance.

Computer Vision: The lab is dedicated to unraveling the complexities of computer vision, with a focus on enabling machines to perceive and interpret visual information like never before. Through innovative algorithms and techniques, we strive to enhance object recognition, image processing, and scene understanding, revolutionizing industries that rely on visual data analysis.

Deep Learning: Leveraging the power of artificial neural networks, our lab is committed to unraveling the immense potential of deep learning methodologies. By training intricate models on vast datasets, we seek to develop intelligent systems capable of making informed decisions, learning patterns, and adapting to changing environments.


Research Topics

Robotics:

  1. Intelligent Robotic Manipulation: Developing algorithms for precise and adaptive robotic manipulation tasks, enhancing dexterity and object handling in various applications.
  2. Autonomous Navigation and Exploration: Creating advanced navigation strategies that enable robots to autonomously navigate and explore complex environments, overcoming obstacles and optimizing path planning.
  3. Human-Robot Collaboration: Investigating methods to enhance human-robot collaboration, enabling seamless interaction and cooperative task execution in shared workspaces.

Control Systems:

  1. Adaptive Control for Dynamic Systems: Researching adaptive control techniques to enhance the stability and performance of dynamic systems in the presence of uncertainties and disturbances.
  2. Optimal Control for Energy Efficiency: Designing optimal control strategies to minimize energy consumption and improve efficiency in industrial processes and systems.
  3. Robust Control for Resilient Systems: Developing robust control methodologies that ensure system stability and performance despite variations, uncertainties, and external disturbances.

Computer Vision:

  1. Object Recognition and Tracking: Advancing computer vision algorithms for robust and real-time object recognition and tracking in dynamic and cluttered environments.
  2. Image Segmentation for Medical Imaging: Exploring image segmentation techniques to assist in accurate diagnosis and treatment planning in medical imaging applications.
  3. Scene Understanding and Contextual Analysis: Developing methods for scene understanding and context-aware analysis to enable machines to interpret visual data in complex scenarios.

Deep Learning:

  1. Generative Adversarial Networks (GANs) for Data Augmentation: Exploring GAN-based techniques to augment and synthesize data, enhancing the performance of machine learning models with limited training samples.
  2. Transfer Learning and Domain Adaptation: Researching transfer learning strategies to enable models trained on one task or domain to be efficiently adapted to related tasks or different domains.

Honor

Fully Funded Scholarships:

  • Master's and Ph.D. Degrees: Privileged recipient of fully funded scholarships for Master's and Ph.D. degrees, demonstrating exceptional academic merit and dedication to advanced education and research.

Partial Scholarship:

  • Undergraduate Degree: Recognized with a partial scholarship during undergraduate studies, reflecting early academic distinction and potential.

Educational Background
  • Ph.D. in Mechanical Engineering (Robotics and Control), National Taiwan University of Science and Technology.
  • MS in Mechatronics Engineering (Robotics and Control), University of Engineering and Technology, Peshawar.
  • BS in Electronics Engineering, BUITEMS, Quetta. 

 


2 Vacancies

Job Description

Path Planning and Trajectory Generation:

  • Implement intelligent path planning algorithms that guide the robot to the target position while avoiding obstacles.

Simulation and Testing in ROS Environment:

  • Translate control algorithms, object detection, and path planning techniques into a simulated environment using the Robot Operating System (ROS).
  • Conduct thorough simulations to validate the effectiveness of the integrated system across various scenarios.
  • Analyze simulation results to refine and improve the control algorithms, detection, and path planning strategies as necessary.

Preferred Intern Education Level

Enrolled in bachelor's or higher degree in Robotics, Computer Engineering, Electrical Engineering, or a related field.

Skill sets or Qualities

  • Experience with ROS and simulation environments for robotics.
  • Solid programming skills in languages such as Python, C++, Matlab, etc.