View Proposal

Proposer
Marta Vallejo
Title
Digital Twins for Optimal Indoors Multi-Sensor Placement
Goal
Learn 3D smart home simulator: using a predefined (e.g., OpenSHS) or designing a new one, Sensor modelling, Single and multi-objective optimisation, GUI interface (optional)
Description
Social care throughout the UK is under unprecedented pressure due to our ageing population. It is essential to facilitate elderly people's longer-term living independently at home. Internet of Things (IoT) and artificial intelligence (AI) technology can be used to automatically ensure their safety by using sensors that could monitor and alert them about different risks. For instance, it has become possible to determine whether a person is present, detect falls and abnormalities in behaviours, and the misuse of appliances like gas stoves or fires. However, there are still some issues that need to be overcome in order to implement such systems more practically. Careful sensor selection and placement are critical issues in the design of an effective health monitoring system. An effective deployment requires sensor selection and placement that ensures adequate coverage. Ideally, an optimal sensor placement is reachable such that the deployment cost is minimised but the level of protection afforded is maximised. However, in some cases, the location of sensors is restricted and integrated into hubs. Meanwhile, individual sensors need to be dispersed throughout the environment to maximise performance. This project proposes a solution using digital twins of a set of objective homes and a corresponding set of sensors and/or robots. Their optimal location should be determined using multi-objective optimisation techniques. The developed digital solutions will be finally validated and deployed in the Lara lab (National Robotarium). The developed tool should allow for uploading/creating environment layouts through a (simple) user interface. It should also automatically select appropriate sensors based on desired targets (e.g., user location or specific activities) and subsequently optimise the placement of those sensors.
Resources
Background
Optimisation, metaheuristics, IoT
Url
Difficulty Level
High
Ethical Approval
InterfaceOnly
Number Of Students
3
Supervisor
Marta Vallejo
Keywords
Degrees
Bachelor of Science in Computer Science
Master of Engineering in Software Engineering
Master of Science in Artificial Intelligence
Master of Science in Data Science
Master of Science in Robotics
Master of Science in Software Engineering
Bachelor of Engineering in Robotics
Master of Science in Robotics with Industrial Application
Bachelor of Science in Statistical Data Science
Back to List