To learn more, visit 2023 Course and subject delivery.
|Fees||Look up fees|
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.
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
- 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: 25 May 2023