- Student Records
Programme & Unit Catalogues


CM50230: Intelligent control and cognitive systems

[Page last updated: 10 August 2020]

Follow this link for further information on academic years Academic Year: 2020/1
Further information on owning departmentsOwning Department/School: Department of Computer Science
Further information on credits Credits: 6      [equivalent to 12 CATS credits]
Further information on notional study hours Notional Study Hours: 120
Further information on unit levels Level: Masters UG & PG (FHEQ level 7)
Further information on teaching periods Period:
Semester 2
Further information on unit assessment Assessment Summary: CW 100%
Further information on supplementary assessment Supplementary Assessment:
CM50230 OTHER - Coursework (where allowed by programme regulations)
Further information on requisites Requisites: Before taking this unit you must have taken Advanced Programming Principles or equivalent.
Description: Aims:

* To provide the students with an in-depth knowledge of practical artificial intelligence to control real-time autonomous systems, including autonomous robots, scientific simulations, and virtual-reality characters.
* To develop fundamental vocational skills in constructing the three types of intelligent system covered, advancing to research and evaluation skills in one area as chosen by the student.
* To provide students with sufficient knowledge of intelligence in nature in order for them to critically evaluate and compare natural and artificial intelligent systems.
* To develop research and information retrieval skills sufficient to develop the writing of short conference papers, in order to take advantage of cutting-edge research and to disseminate findings.

Learning Outcomes:

* Students should be able to evaluate available options for mechanical real-world perception, and to critically evaluate and recommend appropriate technologies for informing robotic control.
* Students should be able to compare, contrast and evaluate a number of mechanisms for sequencing actions, and to implement appropriate mechanisms of action selection on a variety of platforms.
* Students should be able to form predictions of the consequences of simple actions being performed by a large number of agents.
* Students should be able to synthesise and critically evaluate the state of the art in acquiring and generating primitive actions for virtual reality, and to choose appropriate technologies for particular animation tasks.
* Students should be able to identify and evaluate intelligent control algorithms from journal and conference literature.
* Students should be able to communicate their knowledge by writing short conference-style publications.

Skills:

* Written communication: writing skills appropriate for postgraduate students entering academic fields (T, F,A).
* Self-learning: study skills appropriate for technology professionals (F,A).
* IT: programming skills useful for addressing contemporary commercial and scientific applications (T, F, A).
* Oral Communication (F, A)

Content:

* Why intelligent control is (computationally) hard, outline / review of historic strategies (proof / search based, reactive / dynamic planning, machine learning, hybrids of these). Course structure, introduction to labs. Sensing: sonar, IR, lazer range finding, vision, touch. strengths, weaknesses, and approaches to use each.
* Action: mechanisms for sequencing, goal arbitration, problem spaces and contexts. Where do action primitives come from, how does morphology do work for you. Redundancy & degrees of freedom.
* Perception and Learning: sensor fusion, memory, and learning. The beginnings of cognition.
* Introduction to agent-based modelling; the impact of concurrency and society; simulations in policy and science; models, simplicity and explanation.
* Natural intelligence: Evolution and cognitive control, variation in cognitive strategies found in nature, individual variation in nature; perception and action selection in nature.
* Writing for science and engineering: special concerns for conferences, the use & nature of evidence. experiment, proof or argument? Picking conferences, knowing a literature.
* Sensing & Action primitives II: Animation and Virtual Reality. Motion capture, segment smoothing. Motion planning and basic AI for games.
* Complex planning systems, achieving multiple goals, agents with emotions and personality. Likeability, believability and engagement.
* Ethics and philosophy of AI, can we build consciousness? What should our users believe about our agents?
Further information on programme availabilityProgramme availability:

CM50230 is Compulsory on the following programmes:

Department of Computer Science

CM50230 is Optional on the following programmes:

Department of Computer Science
  • RSCM-AFM51 : Integrated PhD Accountable, Responsible and Transparent Artificial Intelligence
  • TSCM-AFM51 : MRes Accountable, Responsible and Transparent Artificial Intelligence
  • TSCM-AFM52 : MSc Accountable, Responsible and Transparent Artificial Intelligence
  • TSCM-AFM39 : MSc Computer Science
  • TSCM-AFM21 : MSc Software Systems
  • TSCM-AWM35 : MSc Software Systems
  • USCM-AFM01 : MComp(Hons) Computer Science (Year 4)
  • USCM-AAM02 : MComp(Hons) Computer Science with Study year abroad (Year 5)
  • USCM-AKM02 : MComp(Hons) Computer Science with Year long work placement (Year 5)
Department of Electronic & Electrical Engineering

Notes: