FIT3203 · Embodied artificial intelligence

Overview

Intelligence becomes more complex when artificial intelligence systems must perceive, move and act in the world. This unit explores embodied intelligence through the design of artificial intelligence systems for robots and physically situated agents, where sensing, perception, planning, learning and action must work together in dynamic environments. You will examine how embodied agents use sensors to interpret their surroundings, build representations of the world, plan actions, adapt behaviour and pursue goals under uncertainty. The unit introduces key approaches in robotic perception, sensor fusion, planning, reinforcement learning, learned policies, simulation and agent architectures. Building on prior deep learning capability, you will apply machine learning methods to perception and decision-making tasks, while also considering how embodied systems interact with people, places and physical constraints.

Offerings

Assessment

The Handbook does not list a final examination among the assessment items. That is not a guarantee there is none.

Assessment details may change. Please refer to the assessment information in Moodle closer to the start of the teaching period.

Requisites

Learning outcomes

1. Design embodied intelligence systems that integrate sensors, perception, learned models, planning, action and environmental constraints to achieve defined goals.
2. Use robotics, simulation, perception, planning and embodied intelligence tools to develop and evaluate physically situated artificial intelligence systems.
3. Apply machine learning and deep learning methods to support perception, sensor interpretation, policy learning or adaptive behaviour in embodied artificial intelligence systems.
4. Formulate and solve complex embodied intelligence problems involving uncertainty, dynamic environments, physical constraints, agent goals and action selection.
5. Evaluate how embodied artificial intelligence systems can be designed and applied to support social good, including safety, accessibility, sustainability, human benefit and responsible interaction with people and environments.

Workload

Minimum total expected workload to achieve the learning outcomes for this unit is 144 hours per semester typically comprising a mixture of scheduled online and face to face learning activities and independent study. Independent study may include associated reading and preparation for scheduled teaching activities.

Student experience, not official rules. Nothing here changes what the Handbook says.