Embodied artificial intelligence

What it covers

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.

Assessment

When and where