Course Information
COMP3356 Robotics

COMP3356 Robotics

2019-20
Instructor(s):Pan Jia
(Class A) No. of credit(s):6
Recommended Learning Hours:
Lecture: 26.0
Tutorial: 13.0
Pre-requisite(s):MATH1853 or MATH2014; and COMP2121 or STAT2601; and COMP2119
Co-requisite(s):  
Mutually exclusive with:  
Remarks:

Course Learning Outcomes

1. Understand the motivations and principles for building autonomous robotic system based on sensory perception, control principles, and AI algorithms; and how robotics relates to the broader field of artificial intelligence
2. Formulate problems associated with domain specific data (e.g., obstacle avoidance and robotic arm manipulation) in terms of abstract models of robotics and AI algorithms
3. Implement solutions to robotics problems using tools such as Matlab, apply numerical optimization and machine learning algorithms
Mapping from Course Learning Outcomes to Programme Learning Outcomes
 PLO aPLO bPLO cPLO dPLO ePLO fPLO gPLO hPLO iPLO j
CLO 1TT
CLO 2TT
CLO 3TT

T - Teach, P - Practice
For BEng(CompSc) Programme Learning Outcomes, please refer to here.

Syllabus

Calendar Entry:
This course provides an introduction to mathematics and algorithms underneath state-of-the-art robotic systems. The majority of these techniques are heavily based on probabilistic reasoning and optimization – two areas with wide applicability in modern AI. We will also cover some basic knowledge about robotics, namely geometry, kinematics, dynamics, control of a robot, as well as the mathematical tools required to describe the spatial motion of a robot will be presented. In addition, we will cover perception, planning, and learning for a robotic system, with the obstacle avoidance and robotic arm manipulation as typical examples.

Detailed Description:

Geometry and Mechanics Mapped to CLOs
Principles of robotics1
Transformation, robot state representation, configuration space1, 2
Kinematics, dynamics and basic control1, 2
Motion planning Mapped to CLOs
Search for a path2, 3
Trajectory optimization2, 3
Inverse kinematics2, 3
Perception Mapped to CLOs
Point clouds2, 3
Pose estimation2, 3
Multi-view geometry2, 3
Advanced topics and applications Mapped to CLOs
Multiple-robot system2, 3
Applications1, 2

Assessment:
Continuous Assessment: 50%
Written Examination: 50%

Teaching Plan

Please refer to the corresponding Moodle course.

Moodle Course(s)