Transport Systems

Permanent URI for this collection

https://dspace.lib.cranfield.ac.uk/handle/1826/20719

Browse

Browsing Transport Systems by Author "Cecotti, Marco"

Now showing 1 - 4 of 4
  • Thumbnail Image
    ItemOpen Access
    CAVE GDP 2022 Photos
    (Cranfield University, 2022-07-01 14:54) Cecotti, Marco
    Just some pictures of the Group Design Project for the MSc in Connected and Autonomous Vehicle Engineering
  • Thumbnail Image
    ItemOpen Access
    CogShift - Typical Trial
    (Cranfield University, 2023-12-11 15:47) Cecotti, Marco
    This is the video of one of the vehicle trials for the CogShift project. CogShift, one of five projects which are part of an £11 million UK Government investment in autonomous vehicle research, studied driver attention and cognitive control characteristics. The project developed an optimal control-authority shifting system which takes driver attention into account. More information can be found at https://www.cranfield.ac.uk/research-projects/cogshift.
  • No Thumbnail Available
    ItemOpen Access
    Dataset "Results of centreline extraction based on maximal disks"
    (Cranfield University, 2025-03-03) Cecotti, Marco; Yin, Chenhui
    Maps of road layouts play an essential role in autonomous driving, and it is often advantageous to represent them in a compact form, using a sparse set of surveyed points of the lane boundaries. While lane centrelines are valuable references in the prediction and planning of trajectories, most centreline extraction methods only achieve satisfactory accuracy with high computational cost and limited performance in sparsely described scenarios. This paper explores the problem of centreline extraction based on a sparse set of border points, evaluating the performance of different approaches on both a self-created and a public dataset, and proposing a novel method to extract the lane centreline by searching and linking the internal maximal circles along the lane. Compared with other centreline extraction methods producing similar numbers of centre points, the proposed approach is significantly more accurate: in our experiments, based on a self-created dataset of road layouts, it achieves a max deviation below 0.15 m and an overall RMSE less than 0.01 m, against the respective values of 1.7 m and 0.35 m for a popular approach based on Voronoi tessellation, and 1 m and 0.25 m for an alternative approach based on distance transform.
  • Thumbnail Image
    ItemOpen Access
    Results of Centreline Extraction Based on Maximal Disks
    (Cranfield University, 2023-06-07 11:28) Yin, Chenhui; Cecotti, Marco; Auger, Daniel; Fotouhi, Abbas
    Results of centreline extraction based on maximal disks in a chosen lanelet2 map.