University of Twente Student Theses
Bike trajectory prediction with onboard sensors
Arlauskas, Ą. (2025) Bike trajectory prediction with onboard sensors.
|
PDF
631kB |
| Abstract: | As the number of cyclist casualties rises, it is essential to make the bike a safer option of transport. This can be done by making the bike a “smarter” device. However, bicycles are severely behind in the smart vehicle industry. Whilst the automobile industry is already creating autonomous cars, research on smart bikes is few and far between. An intelligent bicycle solution would allow for a safer environment for every smart vehicle in the system. One of the key features of an intelligent bike is trajectory prediction as it allows for safer navigation, lane keeping, obstacle detection and more. The current state of the art solutions are not made for bicycles as they are limited in space and processing power. The study compares different approaches to path prediction with the goal of finding an effective LSTM architecture for the purpose of a bike’s trajectory prediction using on-board sensors. The described model lays the ground work for further research in the field of smart bicycles by offering an effective LSTM model and plenty of ways to improve upon it with the goal of bridging the gap between the high-tech autonomous cars and comparably low-tech everyday bikes. |
| Item Type: | Essay (Bachelor) |
| Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
| Subject: | 54 computer science |
| Programme: | Computer Science BSc (56964) |
| Awards: | Best presentation award |
| Link to this item: | https://purl.utwente.nl/essays/105104 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page