Handbook home
AI for Robotics (ELEN90095)
Graduate courseworkPoints: 12.5On Campus (Parkville)
To learn more, visit 2023 Course and subject delivery.
About this subject
- Overview
- Eligibility and requirements
- Assessment
- Dates and times
- Further information
- Timetable(opens in new window)
Contact information
Semester 2
Paul Beuchat paul.beuchat@unimelb.edu.au
Overview
Availability | Semester 2 |
---|---|
Fees | Look up fees |
AIMS:
The key focus of this subject is the foundations of systems analysis for designing and certifying learning-based and artificial intelligence (AI) algorithms for robotics applications. These foundations are based on the formulations and frameworks for the modelling and analysis of cyber-physical systems, such as the feedback interconnection of the physical robot, the noisy sensor data it uses to understand its environment, and the algorithm it runs to learn through exploration and to exploit its knowledge to maximise performance. The subject focuses on both existing applications of decision-making and learning algorithms to consumer and industrial robotics, as well as emerging applications of reinforcement learning and AI for robotics.
INDICATIVE CONTENT:
Topics covered are at the intersection of automatic control and artificial intelligence, including:
- Cyber-physical feedback system formulation, such as: black-box and grey-box modelling, stability and robustness safety requirements, hierarchical and network control architectures.
- Safety and convergence guarantees for model-based methods, such as: learning models from data; adaptive control schemes; stability and robustness of PID and MPC control approaches.
- Connections between optimal control and reinforcement learning formulations for robotics.
- Reinforcement learning for robotics, such as: actor-critic methods, on-policy versus off-policy learning, sample efficiency, transferring simulation-based learning to real-world robots
Intended learning outcomes
On completion of this subject, students should be able to:
- Contrast and critique systems-level formulations and architectures for robotic systems to perform tasks, using tools such as block diagrams and Markov decision processes.
- Analyse and implement model-based methods for providing stability and performance, such as: PID, MPC, system identification, or adaptive control schemes
- Analyse and implement reinforcement learning (RL) methods for discrete-time dynamical systems with continuous spaces
- Compare and contrast the complexities of implementing decision-making and learning algorithms on real-world systems
- Communicate and collaborate on AI and decision-making projects through formats such as: technical reports, presentations, and informational videos, and reflection
- Review and compare the variety of definitions, applications, and safety implications of AI for engineering systems
Generic skills
- Ability to identify, formulate, analyse and solve complex problems using a systems approach
- Capacity for independent critical thought, rational inquiry, creativity, and innovation
- Ability to communicate effectively through verbal and written means with a variety of target audiences, including with one's direct team, other engineers and professions, and with the community at large
- Ability to function effectively in multi-disciplinary and multi-cultural teams of various sizes, with the capacity to be an effective leader, manager, and team member as appropriate to the context
- Ability to scope and plan project work and manage competing demands on time to deliver a substantial outcome, including any self-directed learning necessary
Last updated: 20 April 2024
Eligibility and requirements
Prerequisites
Option 1
Admission into or selection of one of the following:
- MC-ELECENG Master of Electrical Engineering
- MC-MTRNENG Master of Mechatronics Engineering
AND
Note: the following subject/s can also be taken concurrently (at the same time)
Code | Name | Teaching period | Credit Points |
---|---|---|---|
ELEN90066 | Embedded System Design |
Semester 2 (On Campus - Parkville)
Semester 1 (On Campus - Parkville)
|
12.5 |
Option 2
Admission into or selection of one of the following:
- MC-IT Master of Information Technology
- MC-SOFTENG Master of Software Engineering
- MC-CS Master of Computer Science
AND
Note: the following subject/s can also be taken concurrently (at the same time)
Code | Name | Teaching period | Credit Points |
---|---|---|---|
COMP90054 | AI Planning for Autonomy |
Semester 1 (Dual-Delivery - Parkville)
Semester 2 (On Campus - Parkville)
|
12.5 |
Corequisites
None
Non-allowed subjects
None
Inherent requirements (core participation requirements)
The University of Melbourne is committed to providing students with reasonable adjustments to assessment and participation under the Disability Standards for Education (2005), and the Assessment and Results Policy (MPF1326). Students are expected to meet the core participation requirements for their course. These can be viewed under Entry and Participation Requirements for the course outlines in the Handbook.
Further details on how to seek academic adjustments can be found on the Student Equity and Disability Support website: http://services.unimelb.edu.au/student-equity/home
Last updated: 20 April 2024
Assessment
Description | Timing | Percentage |
---|---|---|
Continuous individual assessment of team project work, in the form of reports, presentations and/or videos, not exceeding 40 pages per student over the semester. Approximately 60 hours of work per student. 4 submissions between Weeks 3-14, spaced approximately 3-4 weeks. Intended Learning Outcomes (ILOs) 1-5 are addressed in this assessment.
| From Week 3 to Week 14 | 50% |
Individual presentation. ILO 5-6 are addressed in this assessment
| From Week 4 to Week 5 | 10% |
Progress Test. ILOs 1-3 are addressed in this assessment.
| From Week 7 to Week 8 | 10% |
Final Exam. ILOs 1-4 are addressed in this assessment.
| During the examination period | 30% |
Last updated: 20 April 2024
Dates & times
- Semester 2
Principal coordinator Paul Beuchat Mode of delivery On Campus (Parkville) Contact hours 48 hours, comprising of two hours of lectures and two hours of tutorials/workshops per week for 12 weeks Total time commitment 200 hours Teaching period 24 July 2023 to 22 October 2023 Last self-enrol date 4 August 2023 Census date 31 August 2023 Last date to withdraw without fail 22 September 2023 Assessment period ends 17 November 2023 Semester 2 contact information
Paul Beuchat paul.beuchat@unimelb.edu.au
What do these dates mean
Visit this webpage to find out about these key dates, including how they impact on:
- Your tuition fees, academic transcript and statements.
- And for Commonwealth Supported students, your:
- Student Learning Entitlement. This applies to all students enrolled in a Commonwealth Supported Place (CSP).
Subjects withdrawn after the census date (including up to the ‘last day to withdraw without fail’) count toward the Student Learning Entitlement.
Last updated: 20 April 2024
Further information
- Texts
Prescribed texts
There are no specifically prescribed or recommended texts for this subject.
- Related Handbook entries
This subject contributes to the following:
Type Name Course Master of Computer Science Course Master of Mechatronics Engineering Course Master of Information Technology Course Master of Software Engineering Course Master of Electrical Engineering - Available through the Community Access Program
About the Community Access Program (CAP)
This subject is available through the Community Access Program (also called Single Subject Studies) which allows you to enrol in single subjects offered by the University of Melbourne, without the commitment required to complete a whole degree.
Entry requirements including prerequisites may apply. Please refer to the CAP applications page for further information.
- Available to Study Abroad and/or Study Exchange Students
This subject is available to students studying at the University from eligible overseas institutions on exchange and study abroad. Students are required to satisfy any listed requirements, such as pre- and co-requisites, for enrolment in the subject.
Last updated: 20 April 2024