Course description
In modern sensor systems, estimation and sensor fusion play a significant part in the design of the multiple sensors.
Therefore, this course focuses on fundamental understanding, demonstration, and applications of basic and advanced estimation theories, multiple sensor fusion techniques, and their architectures, algorithms, and applications. This should enable you to critically select and design appropriate estimation and multiple sensor fusion techniques to your specific problems depending on the types of sensor systems and noise characteristics of sensors.
Upcoming start dates
Suitability - Who should attend?
This course is ideal for engineers with interest in estimation theories, sensor fusion and their architecture, algorithms and applications.
Outcome / Qualification etc.
What you will learn
The aim of this course is to acquaint you with the basic principles of estimation theory, and critically understand the pros and cons of filtering and fusion theories when applied to the problem of sensor fusion.
On successful completion, you will be able to:
- Demonstrate the nature, purpose, and design procedures of estimation theory and sensor fusion
- Critically understand challenging problems in the conventional estimation and sensor fusion approaches
- Critically select and apply an appropriate filtering technique and sensor fusion method to a specific problem depending on the types of system/sensor dynamics and noise characteristics.
Training Course Content
Core content
Topics covered by the course include:
- Introduction on estimation theories and sensor fusion
- Statistical analysis: Gaussian distributions, expectation operator, means and variances, maximum likelihood
- Observers: Principle of internal model matching, using outputs to match internal model, full state observer, reduced state observer
- Estimators: Linear Kalman Filter, Extended Kalman Filter, Unscented Kalman Filter, Adaptive Filter (IMM Filter), Information Filter, Particle Filter
- Sensor integration architectures: central, hierarchical, and decentralised fusion architectures
- Multiple sensor fusion: Covariance intersection, State-vector fusion (track-to-track fusion), Information fusion.
Course delivery details
Course structure
This course consists of lectures, case studies, and lab sessions on estimation and fusion algorithms. Matlab will be used during lab sessions. All delegates will receive a Certificate of Attendance at the end of the course.
Request info
Cranfield University
Cranfield is a specialist postgraduate university that is a global leader for education and transformational research in technology and management. We have many world-class, large-scale facilities, including our own global research airport, which offers a unique environment for transformational education...