WM295-15 Machine Perception with Artificial Intelligence
Introductory description
This module introduces students to the fundamental principles of perception systems and how that information can be utilised to produce a response with a particular emphasis on robotics. Students will explore a range of sensing technologies and control architecture, gaining an understanding of their applications in the context of robotics. Basic machine learning techniques will also be introduced to aid the analysis and modelling of perception data. The module will equip students to critically evaluate and compare various sensing and control approaches.
Module aims
The purpose of this module is to introduce students to the key principles of perception systems, machine learning (a type of artifical intelligence), and basic control architectures with a specific focus on autonomous robotics applications.
Perception sensor data is analysed using machine learning to improve perception performance and it is the key technology for autonmous robots to learn how to interact with unstructured (or real) environments.
On completion of this module, students will be able to critically compare and contrast different sensing architectures and technologies, machine learning algorithms, for robotics control.
Outline syllabus
This is an indicative module outline only to give an indication of the sort of topics that may be covered. Actual sessions held may differ.
Perception systems e.g. lidar, radar, camera, gps, ultrasonic.
Classic AI control architectures, e.g. FSM, subsumption.
Basic Machine Learning, e.g. Introduction to data preprocessing; data extraction, data loading, data transformation, clustering, regression.
Examples of real world system architectures, e.g. ROS, AUTOSAR.
Learning outcomes
By the end of the module, students should be able to:
- Interpret and evaluate the role of different sensors and sensor fusion in autonomous robotics systems and the impact of sensors’ limitations on the system [AHEP:4-C2, C6].
- Differentiate control architectures and technologies, algorithms relevant to machine perception [AHEP:4-C1, C3].
- Evaluate the coverage of different sensors and analyse the effects of different external factors [AHEP:4-C13].
- Investigate machine perception systems within a real world robotics context, with consideration for future developments [AHEP:4-C13].
Indicative reading list
Reading lists can be found in Talis
Subject specific skills
Programming microcontrollers and microprocessors.
Data processing and analysis for machine perception.
Implementing machine learning and artificial intelligence for perception.
Transferable skills
This module will contribute to the development of the following from the Warwick Core Skills framework:
Communication: Professional writing
Critical Thinking: Interpreting, analysing
Digital literacy: IT skills
Problem Solving: Problem creation, logical reasoning
Study time
| Type | Required |
|---|---|
| Lectures | 12 sessions of 1 hour (8%) |
| Seminars | 12 sessions of 1 hour (8%) |
| Practical classes | 6 sessions of 1 hour (4%) |
| Online learning (independent) | 30 sessions of 1 hour (20%) |
| Private study | 30 hours (20%) |
| Assessment | 60 hours (40%) |
| Total | 150 hours |
Private study description
Online learning (independent): Engagement with provided study materials and signposted resources - review, interpretation and application to example problems and case studies.
Private study: Creation of own study materials - e.g. notes, flashcards, summaries, etc.
Engagement with self-identified materials - industry reports, technical videos, podcasts, journal articles, etc.
Costs
No further costs have been identified for this module.
You must pass all assessment components to pass the module.
Assessment group A
| Weighting | Study time | Eligible for self-certification | |
|---|---|---|---|
Assessment component |
|||
| Assessment 1 | 30% | 18 hours | Yes (extension) |
|
Individual report on the suitability of various machine perception technologies to real world robotics applications. |
|||
Reassessment component |
|||
| Assessment 1 reassessment | No | ||
|
Individual report on the suitability of various machine perception technologies to real world robotics applications. |
|||
Assessment component |
|||
| Assessment 2 | 70% | 42 hours | No |
|
Group report covering the testing and evaluation of a variety of sensors and their implementation to a robot perception problem. Subject to peer marking in line with WMG policy. |
|||
Reassessment component |
|||
| Assessment 2 reassessment | No | ||
|
Individual report covering the testing and evaluation of a variety of sensors and their implementation to a robot perception problem. |
|||
Feedback on assessment
Formative: Verbal feedback during interactive class sessions and practical sessions; Verbal feedback during ad hoc meetings.
Summative: Written feedback and marks aligned with University 20 point marking scale.
There is currently no information about the courses for which this module is core or optional.