Trailer detection and articulation estimation for driving-assistance systems 

Supervisor: Dr Leonardo Guevara 

What you will be doing 

Fig 1. Illustration of (a) a simulated articulated vehicle (b) rear view of the trailer captured by a camera (c) 2D LiDAR beams colliding with the trailer.

In this project, the student is going to develop a method for trailer detection and articulation angle measurement based on image and/or cloud point data from a rear-end camera and/or 2D/3D LiDAR sensors (see Fig. 1). The student will focus mainly on the articulation angle estimation, however, by already having this angle, the student can also propose a driver assistance system that gives visual feedback to drivers when manoeuvring the trailer(s) in reverse for parking purposes. The student is expected to complete the project using a simulated articulated vehicle in Gazebo Sim. The initial plan is to simulate a vehicle with a single trailer, however, escalating the solution for more trailers can be part of the scope. Moreover, if the student is interested in real implementation, an existing robotic system with a trailer that can be used. 

What skills would be useful to have for this project 

Necessary skills: Python, computer vision, machine learning, ROS2, Gazebo  

Desirable skills: 3d modelling, Fiducial Markers For Perception, Point cloud segmentation, Arduino (in case of real implementations) 

How to get more information and apply 

The prospective candidates can apply by sending an email to Dr Leonardo Guevara (lguevara@lincoln.ac.uk) and providing a short background summary focusing on relevant interests and skills together with a CV. All candidates meeting the skills requirements will be accepted and in case of multiple expressions of interest, the project scope will be negotiated with individual candidates. The application deadline is 25th of June and the candidates will be informed about the selection outcome by the 28th of June with an anticipated project start on the 1st of July (this is negotiable).