NUS
 
ISS
 
NUS ISS

Practice Module for Intelligent Robotic Systems

Overview

Part of Graduate Certificate in Intelligent Robotic Systems
Duration 10 days
Course Time
Enquiry Please contact ask-iss@nus.edu.sg for more details.

Please indicate your interest at this link

The goal of the Graduate Certificate in “Intelligent Robotic Systems” (IROS) is to teach participants the skills, knowledge and industry best practices to develop intelligent robotic systems.

It is targeted at engineering professionals, managers and decision makers who wish to gain specialised knowledge in the integration of robotic components and complex control algorithms to enable a system that functions independently and alongside man.  This certificate consists of three component courses and a practice module.

The main aim of the practice module is for the students to assimilate the knowledge gained through the three component courses and to be able to apply them in a holistic manner to solve real-world robotics-related problems. The practice module consists of two parts i.e.; a Practice Project and an Examination.

Objectives

The objective of the practice module is twofold:

• Firstly, to expose participants to real world problems so that they may practice the use of the skills they have learned during the component courses in a holistic manner.

Intended Audience• Secondly, to enable participants to demonstrate their proficiency across all the skills that they have learned in the course modules and hence obtain a grade at the Graduate Certificate Level.



Intended Audience

This practice module is targeted at participants who wish to complete the certification process for the Graduate Certificate in “Intelligent Robotic Systems”.



Prerequisites

Participants must have successfully obtained a competent score (or have been exempted) from the three component courses for the Graduate Certificate in Intelligent Robotic Systems as listed in the introduction to the Graduate Certificate page.



Components

There are two parts to the Practice Module.

  1. Practice Project: Participants will need to undertake one or more projects to gain practical experience and demonstrate their understanding and mastery of the skills taught in the three component courses. The practice project will require each participant to expend an estimated 10 days of effort. These days are not expected to be contiguous and may stretch over many weeks. These projects may be conducted by individual participants or in teams depending on the nature of the project requirements.
  2. Examination: Each participant is required to sit for an examination on a stipulated date and time.
  3. The overall grade for the participant will be based on the Practice project and Examination.

      Typical examples of projects to be undertaken

  1. Problem description:

Today’s drones are filled with features that could take up to 8K shots and 4K high quality videos with the ability to zoom and change apertures when necessary. Autonomous flight controls are also becoming commonplace, making it easier for Professionals and Amateurs alike to control and take great footage. For the professionals working on “live” events, the higher risks of multiple Drones working on the same event push our research looking into potential autonomous flight formation control for multiple Drones while tracking the same target. There is a need for a control system that allows the drones to maintain formation and prevent collision is required.

Deliverables and success criteria:

  • Identify the business requirement or real-world need
  • Identify the current systems, approaches and/or models used and their limitations
  • Formulate the requirement, approach and/or model required to address the need and current limitation(s)
  • Perform modelling and simulation of the proposed method to get results
  • Compare performances of the results with the state-of-the-art
  • Discuss the work done and its implications
  • Identify the limitations in your work and how to address them in future

     

  • Problem description:

    • Robotic grasping is an essential ability for automated robotic applications, such as the picking and sorting of items in recycling activities. Computer vision-based and reinforcement learning approaches have been proposed, but often require large training datasets. In this project, a simulation-based approach to perform robotic grasping of objects for recycling using reinforcement learning algorithms is explored. Utilizing opensource simulation environment, MARA from Acutronic Robotics, various control and machine learning algorithms can be tested to train a robot to predict optimal joint angles and gripper width to complete the grasping task.

    Deliverables and success criteria:

  • Identify the business requirement or real-world need
  • Identify the current systems, approaches and/or models used and their limitations
  • Formulate the requirement, approach and/or model required to address the need and current limitation(s)
  • Perform modelling and simulation of the proposed method to get results
  • Compare performances of the results with the state-of-the-art
  • Discuss the work done and its implications
  • Identify the limitations in your work and how to address them in future


loading

Course Resources

Develop your Career in the Following
Training Roadmap(s)

Please click on the discipline(s) to view the training roadmap of related courses to assess your training needs and goals.

You Might be Interested in...

A+
A-
Scrolltop