Aims

The aims of the course are to:

• Provide a unified view of information engineering showing how signal processing, computer vision, machine learning and control relate to one another.
• Use example applications drawn from autonomous driving to provide concrete examples of important concepts and subareas of information engineering including computer vision, machine learning and reinforcement learning
• Introduce computer vision including algorithms for 3D reconstruction, registration and object recognition
• Introduce basic concepts in inference, learning and optimisation including maximum-likelihood estimation, Bayes’ rule and gradient descent.
• Introduce basic algorithms for planning and the general area of sequential decision making / reinforcement learning

Objectives

As specific objectives, by the end of the course students should be able to:

• Provide example applications of machine perception, machine learning, and autonomous decision making systems.
• Understand the mathematical basis for perspective projection and feature detection; neural networks and parameter estimation; basic planning and reinforcement learning.
• Implement methods to solve simple computer vision and machine learning problems including object detection and segmentation and sequential decision making.

Content

A: Introduction to Autonomous Driving (1L) (A. Kendall - Guest lecturer from industry)

• The anatomy of a self-driving car (Autonomous Vehicle) with description of autonomous driving hardware (the car, sensors, interfaces and actuators) 
• Motivate the need for machine perception (computer vision), learning and decision making systems
• Important sub-problems in the data processing pipeline: object detection, localisation and mapping, prediction, planning and action
• Examples of self-driving cars

B: Machine Perception: Introduction to Computer Vision (5L) (Lecturer R. Cipolla)

• An introduction to computer vision: reconstruction, registration and recognition
• Perspective projection
• Convolution with gaussians and derivatives of gaussians to provide bandpass filters.
• Edge detection using directional filters.
• Scale-space and image pyramids for feature detection
• The SIFT feature descriptor for matching image features.
• Demonstration of state-of-the-art object detection, semantic segmentation and localisation systems
• Examples paper and class

C: Machine Learning: Introduction to Deep Learning (5L) (D. Krueger)

• Training a simple classifier: logistic regression and gradient descent
• Neural networks: Multi-layer perceptrons and back propagation
• Neural networks: convolutional neural networks
• Anatomy and training of a convolutional neural network in Tensorflow or PyTorch - network architecture, loss function, weight initialization, batch size, learning rate, epochs.
• Examples paper and class 

D: Autonomous Decision Making: Introduction to Planning and Reinforcement Learning (5L) (G. Vinnicombe and one Guest Lecture)

• Introduction to planning: Shortest path problems, value functions and dynamic programming
• Introduction to reinforcement learning: Q-learning, actor-critic methods, approximations using neural networks
• Identification of open problems
• Examples paper and class

Aims

The aims of the course are to:

• Provide a unified view of information engineering showing how signal processing, computer vision, machine learning and control relate to one another.
• Use example applications drawn from autonomous driving to provide concrete examples of important concepts and subareas of information engineering including computer vision, machine learning and reinforcement learning
• Introduce computer vision including algorithms for 3D reconstruction, registration and object recognition
• Introduce basic concepts in inference, learning and optimisation including maximum-likelihood estimation, Bayes’ rule and gradient descent.
• Introduce basic algorithms for planning and the general area of sequential decision making / reinforcement learning

Objectives

As specific objectives, by the end of the course students should be able to:

• Provide example applications of machine perception, machine learning, and autonomous decision making systems.
• Understand the mathematical basis for perspective projection and feature detection; neural networks and parameter estimation; basic planning and reinforcement learning.
• Implement methods to solve simple computer vision and machine learning problems including object detection and segmentation and sequential decision making.

Content

A: Introduction to Autonomous Driving (1L) (A. Kendall - Guest lecturer from industry)

• The anatomy of a self-driving car (Autonomous Vehicle) with description of autonomous driving hardware (the car, sensors, interfaces and actuators) 
• Motivate the need for machine perception (computer vision), learning and decision making systems
• Important sub-problems in the data processing pipeline: object detection, localisation and mapping, prediction, planning and action
• Examples of self-driving cars

B: Machine Perception: Introduction to Computer Vision (5L) (Lecturer R. Cipolla)

• An introduction to computer vision: reconstruction, registration and recognition
• Perspective projection
• Convolution with gaussians and derivatives of gaussians to provide bandpass filters.
• Edge detection using directional filters.
• Scale-space and image pyramids for feature detection
• The SIFT feature descriptor for matching image features.
• Demonstration of state-of-the-art object detection, semantic segmentation and localisation systems
• Examples paper and class

C: Machine Learning: Introduction to Deep Learning (5L) (D. Krueger)

• Training a simple classifier: logistic regression and gradient descent
• Neural networks: Multi-layer perceptrons and back propagation
• Neural networks: convolutional neural networks
• Anatomy and training of a convolutional neural network in Tensorflow or PyTorch - network architecture, loss function, weight initialization, batch size, learning rate, epochs.
• Examples paper and class 

D: Autonomous Decision Making: Introduction to Planning and Reinforcement Learning (5L) (G. Vinnicombe and one Guest Lecture)

• Introduction to planning: Shortest path problems, value functions and dynamic programming
• Introduction to reinforcement learning: Q-learning, actor-critic methods, approximations using neural networks
• Identification of open problems
• Examples paper and class

Aims

The aims of the course are to:

• Provide a unified view of information engineering showing how signal processing, computer vision, machine learning and control relate to one another.
• Use example applications drawn from autonomous driving to provide concrete examples of important concepts and subareas of information engineering including computer vision, machine learning and reinforcement learning
• Introduce computer vision including algorithms for 3D reconstruction, registration and object recognition
• Introduce basic concepts in inference, learning and optimisation including maximum-likelihood estimation, Bayes’ rule and gradient descent.
• Introduce basic algorithms for planning and the general area of sequential decision making / reinforcement learning

Objectives

As specific objectives, by the end of the course students should be able to:

• Provide example applications of machine perception, machine learning, and autonomous decision making systems.
• Understand the mathematical basis for perspective projection and feature detection; neural networks and parameter estimation; basic planning and reinforcement learning.
• Implement methods to solve simple computer vision and machine learning problems including object detection and segmentation and sequential decision making.

Content

A: Introduction to Autonomous Driving (1L) (Guest lecturer from industry)

• The anatomy of a self-driving car with description of autonomous driving hardware (the car, sensors, interfaces and actuators) 
• Motivate the need for machine perception (computer vision), learning and decision making systems
• Important sub-problems in the data processing pipeline: object detection, localisation and mapping, prediction, planning and action
• Interaction with an example of a self-driving car in Cambridge

It is likely that there will be one guest lecture at the start of the course and one at the end.

B: Machine Perception: Introduction to Computer Vision (5L) (Lecturer Dr. I. Budvytis)

• An introduction to computer vision: reconstruction, registration and recognition
• Perspective projection
• Convolution with gaussians and derivatives of gaussians to provide bandpass filters.
• Edge detection using directional filters.
• Scale-space and image pyramids for feature detection
• The SIFT feature descriptor for matching image features.
• Demonstration of state-of-the-art object detection, semantic segmentation and localisation systems
• Examples paper and class

C: Machine Learning: Introduction to Deep Learning (5L) (R. E. Turner)

• Training a simple classifier: logistic regression and gradient descent
• Neural networks: Multi-layer perceptrons and back propagation
• Neural networks: convolutional neural networks
• Anatomy and training of a convolutional neural network in Tensorflow or PyTorch - network architecture, loss function, weight initialization, batch size, learning rate, epochs.
• Examples paper and class 

D: Autonomous Decision Making: Introduction to Planning and Reinforcement Learning (5L) (G. Vinnicombe and one Guest Lecture)

• Introduction to planning: Shortest path problems, value functions and dynamic programming
• Introduction to reinforcement learning: Q-learning, actor-critic methods, approximations using neural networks
• Application of these methods to a self-driving car
• Demonstration of perception and planning algorithms running on a self-driving car
• Identification of open problems
• Examples paper
• One Guest Lecture from Industry

Aims

The aims of the course are to:

• Provide a unified view of information engineering showing how signal processing, computer vision, machine learning and control relate to one another.
• Use example applications drawn from autonomous driving to provide concrete examples of important concepts and subareas of information engineering including computer vision, machine learning and reinforcement learning
• Introduce computer vision including algorithms for 3D reconstruction, registration and object recognition
• Introduce basic concepts in inference, learning and optimisation including maximum-likelihood estimation, Bayes’ rule and gradient descent.
• Introduce basic algorithms for planning and the general area of sequential decision making / reinforcement learning

Objectives

As specific objectives, by the end of the course students should be able to:

• Provide example applications of machine perception, machine learning, and autonomous decision making systems.
• Understand the mathematical basis for perspective projection and feature detection; neural networks and parameter estimation; basic planning and reinforcement learning.
• Implement methods to solve simple computer vision and machine learning problems including object detection and segmentation and sequential decision making.

Content

A: Introduction to Autonomous Driving (1L) (Guest lecturer from industry - J. Hawkes)

• The anatomy of a self-driving car with description of autonomous driving hardware (the car, sensors, interfaces and actuators) 
• Motivate the need for machine perception (computer vision), learning and decision making systems
• Important sub-problems in the data processing pipeline: object detection, localisation and mapping, prediction, planning and action
• Interaction with an example of a self-driving car in Cambridge

B: Machine Perception: Introduction to Computer Vision (6L) (R. Cipolla)

• An introduction to computer vision: reconstruction, registration and recognition
• Perspective projection
• Convolution with gaussians and derivatives of gaussians to provide bandpass filters.
• Edge detection using directional filters.
• Scale-space and image pyramids for feature detection
• The SIFT feature descriptor for matching image features.
• Demonstration of state-of-the-art object detection, semantic segmentation and localisation systems
• Examples paper and class

C: Machine Learning: Introduction to Deep Learning (5L) (R. Turner)

• Training a simple classifier: logistic regression and gradient descent
• Neural networks: Multi-layer perceptrons and back propagation
• Neural networks: convolutional neural networks
• Anatomy and training of a convolutional neural network in Tensorflow or PyTorch - network architecture, loss function, weight initialization, batch size, learning rate, epochs.
• Examples paper and class 

D: Autonomous Decision Making: Introduction to Planning and Reinforcement Learning (4L) (G. Vinnicombe and A. Kendall)

• Introduction to planning: Shortest path problems, value functions and dynamic programming
• Introduction to reinforcement learning: Q-learning, actor-critic methods, approximations using neural networks
• Application of these methods to a self-driving car
• Demonstration of perception and planning algorithms running on a self-driving car
• Identification of open problems
• Examples paper

Aims

The aims of the course are to:

• Act as a shop window for the techniques and technologies of civil engineering seen as a practical and scientific discipline.
• Create interest in the design, construction and maintenance of the built environment, using floating offshore wind turbines as an example.
• Provide illustrations from real life schemes, and in combining theory in context with real life examples, highlight the role of the professional.
• Introduce the topics of structural materials (with more detailed introduction to structural concrete), structural stability, geotechnical engineering, and using data for smart infrastructure and construction.

Objectives

As specific objectives, by the end of the course students should be able to:

• Introduce students to the range of disciplines within civil engineering;
• Develop awareness of the integrated civil engineering projects that they might work on as professional engineers;
• Learn to use Part I theory in simple integrated design applications;
• Recognise limitations with Part I theory; and
• Develop an awareness of potential courses of study that will address these limitation in Part II.

Content

The course focuses on a Civil Engineering mega-project - in this case the design of Floating Offshore Wind Turbines (FOWT). This will illustrate how the knowledge you have gained in Part I knowledge might be used immediately. Their enormous scale makes FOWTs a very exciting prospect for making a major contribution to tackllng the world's energy demand in a sustainable manner.

The course will also highlight a wide spectrum of Division D Part II module offerings that will provide extensions to specialist knowledge in specifc areas. 

There will be four sub-topics, and these will be covered by lectures in the first half of the course.

- Concrete Design

- Hydrostatic Stability

- Geotechnical Engineering (Ground anchor design)

- Smart Infrastructure & Construction (Systems thinking and Digital Twins)

The second half of the course will be informal workshop sessions with the lecturers, where students can undertake their own research into these issues and prepare coursework for submission.

Students should attend all lectures but only need to submit coursework on TWO of the four topics. 

Integrated Civil Engineering Introduction

The course will begin with an introductory lecture, explaining how the course works. It will also give a background to the wider topic of Floating Offshore Wind Turbines (FOWTs). This will be given by Ari Liddell, an alumna of the department, who now works on the design of FOWTs and associated green energy infrastructure in the Celtic Sea.

Structural Materials (2L + 2 Design Workshops)

• Lectures: overview of structural aspects related to FOWT design (steel for turbine, and an introduction to concrete for base design); development of simple analysis techniques from Part I material, highlighting limitations and scope for knowledge extension in Part II through the design of reinforced concrete sections; 

• Design classes: two hours of interactive design classes to help students work through producing a design for the FOWT base.

Hydrostatic Stability (2L + 2 Design Workshops)

• Lectures: an introduction to ship stability and the buoyancy considerations related to FOWT design, extending basic stability from Part I to how a FOWT floats and how it can be moved safely into place; 

• Design classes: two hours of interactive design classes to help students work through to determine the stabilty of various shapes, to better  understand the design for the FOWT main section.

Geotechnical Engineering (2L + 2 Design Workshops)

• Lectures: overview of geotechnical aspects related to FOWT design (seabed); development of simple analysis techniques from Part I material, highlighting limitations and scope for knowledge extension in Part II; 

Smart Infrastructure and Construction (2L + 2 Design Workshops)

• Lectures: overview of sensing and data aspects related to FOWT design (Big Data, smart sensing, data-driven approaches and systems thinking, digital twins); developing an understanding of how we can derive value from data, rather than simply collecting it.