TITLE:
Compare and Contrast LiDAR and Non-LiDAR Technology in an Autonomous Vehicle: Developing a Safety Framework
AUTHORS:
Benjamin Quito, Larbi Esmahi
KEYWORDS:
AI, ML, Image Classification, Safety Frameworks, LiDAR, Non-LiDAR
JOURNAL NAME:
Open Journal of Safety Science and Technology,
Vol.13 No.3,
September
4,
2023
ABSTRACT: Ensuring
safety has always been of utmost importance in vehicular operations, where
traditionally, human drivers have been solely responsible for driving. However,
with the emergence of advanced technologies, we are now on the brink of a new
era with the introduction of Autonomous Vehicles (AVs), in which control over
the vehicle gradually shifts to Artificial Intelligence (AI). The safety of
these vehicles has raised concerns among the public. In terms of safety, human
drivers heavily rely on visual perception. Key elements that contribute to safe
driving include situational awareness, vehicle control, reaction capabilities,
and anticipation of potential hazards. With the introduction of AVs, these
fundamental factors remain unchanged. AVs rely on two primary technologies, namely
LiDAR and Non-LiDAR, to perceive their surroundings. This research focuses on
three primary aspects. Firstly, it involves the development of an image
classification model to assess the safety of AVs. This model determines whether
the images captured by LiDAR and Non-LiDAR technologies can be accurately
predicted using supervised learning. An algorithm is employed to identify the
input images obtained from both LiDAR and Non-LiDAR technologies. The results
demonstrate that the model achieved a high accuracy rate of 94.63% in
predicting the images. Secondly, a Safety Framework is established to
facilitate the subsequent proposal for Experimental Research, which is the
third aspect. The Safety Framework incorporates the application of LiDAR and
Non-LiDAR technologies mounted on a vehicle that is operated in diverse weather
conditions by both a human driver and an autonomous system. The Scenario tables,
which are currently in a blank state, will be populated upon completion of the
Experimental Research. The Experimental Research aims to compare and contrast
the performance of LiDAR and Non-LiDAR technologies on a vehicle driven by a
human operator versus an Autonomous Vehicle. The findings of this research will
be documented in the Scenario table outlined within this study, ultimately
shedding light on the safety implications of implementing LiDAR and Non-LiDAR
technologies within an AV context.