ROBOT LEARNING - 2028/9

Module Overview

This module teaches advanced concepts and skills in robot learning for embodied robotic systems. Students will develop a strong understanding of how learning-based methods interact with perception, decision-making, and control, and how these can be used to test, analyse, and improve robot behaviour on representative tasks.

Through lectures and lab activities, the curriculum focuses on core approaches such as learning from demonstration, reinforcement learning, and related methods, while enabling students to systematically evaluate their performance and appraise their suitability for real-life applications. By engaging with both foundational ideas and current research directions, students will build confidence in selecting, implementing, and critically assessing these methods, including their strengths and limitations. A strong emphasis is placed on practical experimentation and critical evaluation, preparing students to develop robust and effective robot learning systems.

Please note that the information detailed within this record is accurate at the time of publishing and may be subject to change. This record contains information for the most up to date version of the programme / module for the 2028/9 academic year.

Module provider

Computer Science and Electronic Eng

Module Leader

WANG Peng (CS & EE)

Number of Credits: 15

ECTS Credits: 7.5

Framework: FHEQ Level 6

Module cap (Maximum number of students): N/A

Module Availability

Semester 2

Prerequisites / Co-requisites

N/A

Module content

This module introduces advanced robot learning in the context of embodied robotic systems.

Indicative topics include:

• robot learning problem formulations;
• the interaction between perception, decision-making, control, and learning in robotic systems;
• learning paradigms like learning from demonstration and reinforcement learning for robot behaviour acquisition and improvement;
• representation and observation design for learning-based control;
• policy models, training strategies, and performance evaluation; 
• experimentation and evaluation for robot learning;
• considerations of robustness, generalisation, safety, etc. in representative robotic applications.

The module also includes critical engagement with contemporary research, practical challenges, and emerging directions in robot learning.

Assessment pattern

Alternative Assessment

N/A

Assessment Strategy

The assessment strategy is designed to:

Provide students with the opportunity to demonstrate knowledge and understanding of core concepts, methods, and applications in robot learning for embodied robotic systems. It is intended to assess students' understanding of key approaches, with particular emphasis on imitation learning and reinforcement learning, and their ability to distinguish between methods, interpret their use in robotic contexts, and evaluate their strengths, limitations, and practical considerations. 

Thus, the summative assessment for this module consists of:

Examination: an open-book exam (Students may bring one A4 page of notes into the assessment. Internet access is not permitted.) assessing students' knowledge and understanding of the core concepts, methods, and challenges in robot learning, including the relationship between learning, perception, decision-making, and control, as well as key principles of learning paradigms like imitation learning and reinforcement learning. This assessment addresses the learning outcomes 1, 2, 3, 4 and 5.

Formative assessment and Feedback:

Formative assessment is embedded throughout the module to support students' learning and preparation for the summative assessment. - Weekly laboratory activities will be used to check understanding of key concepts and provide immediate feedback. - In-class polls and similar activities will provide regular opportunities for formative feedback throughout the module. - Verbal feedback will be given during lectures, tutorials, and laboratory sessions as students work through practical exercises. - The online discussion forum will provide an additional channel for ongoing feedback, clarification, and support. - Deployment and testing in simulation will support students in developing confidence in applying robot learning concepts in practice, and feedback will be provided to support their understanding and ongoing development of relevant knowledge and skills.

Module aims

• Develop students¿ understanding of advanced robot learning methods and their role within modern robotic systems.
• Enable students to analyse, test, and evaluate robot learning methods in representative robotics environments.
• Develop students¿ ability to interpret experimental evidence, compare alternative approaches, and identify limitations in robot learning systems.
• Foster critical engagement with contemporary robot learning literature, methods, and applications.

Learning outcomes

Methods of Teaching / Learning

The learning and teaching strategy is designed to: 

Develop students' conceptual understanding of robot learning, connect theory with implementation, and support critical evaluation of methods used in contemporary robotics research and practice. It will support students in applying theoretical and practical knowledge to analyse, implement, evaluate learning-based methods for robotic systems, and adapt their skills to a fast-developing area of robotics and AI. 

The learning and teaching methods include:

The lectures will introduce core theoretical concepts in robot learning, reinforced by examples from contemporary research and real-world robotic applications. These sessions will examine how learning-based methods interact with perception, decision-making, and control, with particular emphasis on learning paradigms like imitation learning and reinforcement learning. 

The labs will offer students the opportunity to apply and extend their knowledge through practical works, progressing from guided exercises to more open-ended experimentation and evaluation. Lab activities will support the implementation, testing, and analysis of robot learning methods in representative robotics settings and appraise their suitability for real tasks.

Captured content from lectures, together with supporting materials, will be provided through the SurreyLearn system to support preparation, consolidation, and revision. SurreyLearn will also host additional learning resources to support engagement with module content, practical challenges, relevant research literature, and assessment-related guidance.

Formative feedback will be provided through teaching sessions, lab activities, and online discussion to support students' ongoing learning.

Indicated Lecture Hours (which may also include seminars, tutorials, workshops and other contact time) are approximate and may include in-class tests where one or more of these are an assessment on the module. In-class tests are scheduled/organised separately to taught content and will be published on to student personal timetables, where they apply to taken modules, as soon as they are finalised by central administration. This will usually be after the initial publication of the teaching timetable for the relevant semester.

Reading list

https://readinglists.surrey.ac.uk
Upon accessing the reading list, please search for the module using the module code: EEE3046

Other information

The School of Computer Science and Electronic Engineering is committed to developing graduates with strengths in Employability, Digital Capabilities, Global and Cultural Capabilities, Sustainability, and Resourcefulness and Resilience. This module is designed to develop students¿ knowledge, skills, and capabilities in the following areas: Digital Capabilities: This module develops advanced digital capabilities in robot learning for embodied robotic systems. Students engage with contemporary robot learning methods, such as imitation learning and reinforcement learning, and explore how these interact with perception, decision-making, and control. Through lectures and laboratory activities, students build confidence in using robotics software environments, interpreting experimental results, and evaluating learning-based robotic systems. Employability: This module equips students with knowledge and analytical skills relevant to contemporary robotics and AI practice. By studying advanced robot learning methods and their application to representative robotic tasks, students develop capabilities valued in areas such as robotics, autonomous systems, machine learning, and intelligent systems engineering. The module also strengthens transferable skills in critical analysis, problem-solving, and the evaluation of technical approaches in applied settings. Global and Cultural Capabilities: Robot learning is an internationally active area of research and development, with applications across a wide range of sectors and societal contexts. This module supports students in understanding how robot learning methods are developed and applied globally and encourages critical awareness of the broader implications of deploying intelligent robotic systems in diverse real-world environments. Sustainability: This module supports understanding of sustainable technological development through consideration of the efficiency, robustness, and practical deployment of robot learning systems. By examining the strengths and limitations of alternative robot learning approaches, students develop awareness of the importance of selecting methods that are technically appropriate, resource-conscious, and suitable for real-world use. Resourcefulness and Resilience: Robot learning often involves uncertainty, experimental iteration, and the need to interpret and respond to imperfect outcomes. This module develops students¿ resourcefulness and resilience by encouraging them to analyse results critically, compare alternative methods, and reflect on the limitations and practical challenges of learning-based robotic systems. Lab activities and formative feedback support students in building confidence when engaging with complex technical material.