Post Diploma Certificate in Intelligent Autonomous Robot - Part of Specialist Diploma in Robotics Engineering (SDRE)
About This Course
This certificate provides systematic training in machine learning, autonomous robot navigation and computer vision. Students will learn in-depth knowledge and skills necessary for them to be able to design a robot product for various industries.
Module 4: Autonomous Robot Navigation (30 hours)
Participants will gain essential technical skills to develop and deploy autonomous mobile robots for various applications. Topics that will be covered are: Hardware for Robot Navigation System, TF, URDF, Simultaneous Localization and Mapping (SLAM) in ROS Navigation Stack, Mapping, Localization, Path Planning, Path Execution, Obstacle Avoidance, Waypoint Management, Odometry Kinematics, and configuration and programming of real robots.
Module 5: Machine Learning for Robotics (30 hours)
This Machine Learning module offers an in-depth overview of Machine Learning topics that include: Working with Real Data, Developing Algorithms using Supervised, Unsupervised and Reinforcement Learning, Regression, Classification, Time Series Modelling, Using State-of-the-art Machine Learning Frameworks to Solve Problems Efficiently.
Module 6: Computer Vision and Deep Learning for Robotics (30 hours)
Students will acquire computer vision and deep learning skills to solve real-word problems. The topics in this module are: Overview of Computer Vision, OpenCV Functions for Image Processing and Object Detection, Convolutional Neural Networks (CNN), Image Classification using Deep Learning, Building CNN Models with Tensorflow 2, Classifying images using Keras; Transfer Learning, Object Detection using Deep Learning, Object Detection Algorithms including SSD, YOLO and Faster R-CNN, Real-Time Object Detection Application with Tensorflow 2, and Case Study: Person Re-Identification.
Module 7: Robotics Real-world Project (30 hours)
This capstone project allows trainees to integrate the acquired skills into a robot product. The project involves the development of key modules of a concierge robo
What You'll Learn
Module 4: Autonomous Robot Navigation (30 hours)
Participants will gain essential technical skills to develop and deploy autonomous mobile robots for various applications. Topics that will be covered are: Hardware for Robot Navigation System, TF, URDF, Simultaneous Localization and Mapping (SLAM) in ROS Navigation Stack, Mapping, Localization, Path Planning, Path Execution, Obstacle Avoidance, Waypoint Management, Odometry Kinematics, and configuration and programming of real robots.
Module 5: Machine Learning for Robotics (30 hours)
This Machine Learning module offers an in-depth overview of Machine Learning topics that include: Working with Real Data, Developing Algorithms using Supervised, Unsupervised and Reinforcement Learning, Regression, Classification, Time Series Modelling, Using State-of-the-art Machine Learning Frameworks to Solve Problems Efficiently.
Module 6: Computer Vision and Deep Learning for Robotics (30 hours)
Students will acquire computer vision and deep learning skills to solve real-word problems. The topics in this module are: Overview of Computer Vision, OpenCV Functions for Image Processing and Object Detection, Convolutional Neural Networks (CNN), Image Classification using Deep Learning, Building CNN Models with Tensorflow 2, Classifying images using Keras; Transfer Learning, Object Detection using Deep Learning, Object Detection Algorithms including SSD, YOLO and Faster R-CNN, Real-Time Object Detection Application with Tensorflow 2, and Case Study: Person Re-Identification.
Module 7: Robotics Real-world Project (30 hours)
This capstone project allows trainees to integrate the acquired skills into a robot product. The project involves the development of key modules of a concierge robo
Entry Requirements
At least a recognised local Polytechnic diploma in engineering or a degree in relevant areas.
Recognition of Prior Learning (RPL)
Applicants who do not meet the entry requirements may be considered for admission to the course based on evidence of at least 3 years of relevant working experience or supporting evidence of competency readiness.