Module Code - Title:

EE5052 - ROBOTIC SENSING & PERCEPTION

Year Last Offered:

2024/5

Hours Per Week:

Lecture

2

Lab

2

Tutorial

1

Other

0

Private

5

Credits

6

Grading Type:

N

Prerequisite Modules:

Rationale and Purpose of the Module:

Sensors are used to estimate a robot's environment and position, to enable appropriate behaviour. This module will describe in detail the different sensor types and processing methods available for intelligent mobile robotic scene interpretation. This module will introduce the students to the fundamentals of sensor fusion and use within autonomous systems.

Syllabus:

Laser scanner types: Velodyne, rotating mirror, scan lines, angle resolution, solid state laser scanner, XYZ reflectivity Radar sensing type: depth, angular resolution, object velocity (doppler) Ultrasonic sensing: cheap as chips, severely limited, depth, angular resolution Stereo camera: design of stereo cameras, how is depth extracted Case studies in the deployment of sensors: automotive, aerial robotics, underwater robotics Processing sensor information: extracting planes, shape identification, identifying obstacles, sensor free space, road segmentation Robotic motion: iterative closest point, simultaneous localization and mapping, loop closure, Kalman filter Sensor fusion: Fusion network, centralised, decentralized, hierarchical, iterative A probabilistic understanding of sensor output: noise variance, confidence, spatial uncertainty Central Limit Theorem, Kalman Filter, Bayesian Fusion, Dempster Shafer, Particle Filter

Learning Outcomes:

Cognitive (Knowledge, Understanding, Application, Analysis, Evaluation, Synthesis)

On successful completion of this module, students will be able to: 1. Demonstrate a significant understanding of how to process sensor information 2. Critically appraise the strengths and weaknesses of different sensor types for solving different problems 3. Describe the most appropriate means for estimating robotic motion from sensor inputs 4. Demonstrate an understanding of multi-sensor data fusion in applications such as mobile autonomous robotics 5. Describe some of the main areas in which multi-sensor data fusion plays an important role

Affective (Attitudes and Values)

On successful completion of this module, students will be able to: 1. Differentiate from various design techniques that could be used and be able to justify an appropriate sensor and processing technique 2. Practice an objective approach to the selection of sensors, processing methods and design of sensor fusion system to solve specific problems. 3. Effect a design of multi-sensor system to solve problems in robotics and vehicle autonomy

Psychomotor (Physical Skills)

On successful completion of this module, students will be able to: N/A

How the Module will be Taught and what will be the Learning Experiences of the Students:

The module will be delivered in a blended learning format, with online pre-recorded video lectures and interactive Q+A tutorials. The students will also complete a series of exercises and through their own time with online moderator support.

Research Findings Incorporated in to the Syllabus (If Relevant):

Prime Texts:

H.B. Mitchell (2007) Multi-Sensor Data Fusion: An Introduction , Springer

Roland Siegwart (2011) Introduction to Autonomous Mobile Robots, second edition, , Mitpress