COMP34212 Cognitive Robotics Angelo Cangelosi
COMP34212: Coursework on Deep Learning and Robotics
34212-Lab-S-Report
Release: February 2025
Submission deadline: 27 March 2025, 18:00 (BlackBoard)
Aim and Deliverable
The aim of this coursework is (i) to analyse the role of the deep learning approach within the
context of the state of the art in robotics, and (ii) to develop skills on the design, execution and
evaluation of deep neural networks experiments for a vision recognition task. The assignment will
in particular address the learning outcome LO1 on the analysis of the methods and software
technologies for robotics, and LO3 on applying different machine learning methods for intelligent
behaviour.
The first task is to do a brief literature review of deep learning models in robotics. You can give a
summary discussion of various applications of DNN to different robotics domains/applications.
Alternatively, you can focus on one robotic application, and discuss the different DNN models used
for this application. In either case, the report should show a good understanding of the key works in
the topic chosen.
The second task is to extend the deep learning laboratory exercises (e.g. Multi-Layer Perceptron
(MLP) and/or Convolutional Neural Network (CNN) exercises for image datasets) and carry out and
analyse new training simulations. This will allow you to evaluate the role of different
hyperparameter values and explain and interpret the general pattern of results to optimise the
training for robotics (vision) applications.
You can use the standard object recognition datasets (e.g. CIFAR, COCO, not the simple MNIST) or
robotics vision datasets (e.g. iCub World1
, RGB-D Object Dataset2
). You are also allowed to use
other deep learning models beyond those presented in the lab.
The deliverable to submit is a report (max 5 pages including figures/tables and references) to
describe and discuss the training simulations done and their context within robotics research and
applications. The report must also include the link to the Code/Notebook, or add the code as
appendix (the Code Appendix is in addition to the 5 pages of the core report). Do not use AI/LLM
models to generate your report. Demonstrate a credible analysis and discussion of your own
simulation setup and results, not of generic CNN simulations. And demonstrate a credible,
personalised analysis of the literature backed by cited references.
COMP34212 Cognitive Robotics Angelo Cangelosi
Marking Criteria (out of 30)
1. Contextualisation and state of the art in robotics and deep learning, with proper use of
citations backing your academic review and statements (marks given for
clarity/completeness of the overview of the state of the art, with spectrum of deep learning
methods considered in robotics; credible personalised critical analysis of the deep learning
role in robotics; quality and use of the references cited) [10]
2. A clear introductory to the DNN classification problem and the methodology used, with
explanation and justification of the dataset, the network topology and the hyperparameters
chosen; Add Link to the code/notebook you used or add the code in appendix. [3]
3. Complexity of the network(s), hyperparameters and dataset (marks given for complexity
and appropriateness of the network topology; hyperparameter exploration approach; data
processing and coding requirements) [4]
4. Description, interpretation, and assessment of the results on the hyperparameter testing
simulations; include appropriate figures and tables to support the results; depth of the
interpretation and assessment of the quality of the results (the text must clearly and
credibly explain the data in the charts/tables); Discussion of alternative/future simulations
to complement the results obtained) [13]
5. 10% Marks lost if report longer than the required maximum of 5 pages: 10% Marks lost if
code/notebook (link to external repository or as appendix) is not included.
Due Date: 27 March 2025, 18:00, pdf on Blackboard. Use standard file name: 34212-Lab-S-Report
請加QQ：99515681 郵箱：99515681@qq.com WX：codinghelp
