|Owning Department/School:||Department of Computer Science|
|Credits:||6 [equivalent to 12 CATS credits]|
|Notional Study Hours:||120|
|Level:||Masters UG & PG (FHEQ level 7)|
|Assessment Summary:||CW 100%|
|Assessment Detail:|| |
|Requisites:||Before taking this unit you must have taken Advanced Programming Principles or equivalent.|
* 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 sufficent to develop the writing of short conference papers, in order to take advantage of cutting-edge research and to disseminate findings.
* 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. (Ass cw1)
* 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. (Ass cw1-3)
* Students should be able to form predictions of the consequences of simple actions being performed by a large number of agents. (Ass cw 2)
* 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. (Ass cw 3)
* Students should be able to identify and evaluate intelligent control algorithms from journal and conference literature. (Ass cw 4)
* Students should be able to communicate their knowledge by writing short conference-style publications. (Ass cw 4).
* Written communication: writing skills appropriate for postrgradute students entering academic fields (T, F,A).
* Self-learning: study skills appropriate for technology professionals (F,A).
* IT: programming skills useful for adressing contemporary commercial and scientific applications (T, F, A).
* Oral Communication (F, A).
* why intelligent control is (computationally) hard, outline / review of historic strategies (proof / search based, reactive / dynamic planning, machine learning, hybrids of these). Course structure, introduciton to labs. Sensing: sonar, IR, lazer range finding, vision, touch. strenghts, 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 beginings 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, believeability and engagement.
* Ethics and philosophy of AI, can we build consciousness? What should our users believe about our agents?
CM50230 is Optional on the following programmes:Department of Computer Science