English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Autonomous vehicles rely heavily upon their perception subsystems to see theenvironment in which they operate. Unfortunately, the effect of variableweather conditions presents a significant challenge to object detectionalgorithms, and thus it is imperative to test the vehicle extensively in allconditions which it may experience. However, development of robust autonomousvehicle subsystems requires repeatable, controlled testing - while real weatheris unpredictable and cannot be scheduled. Real-world testing in adverseconditions is an expensive and time-consuming task, often requiring access tospecialist facilities. Simulation is commonly relied upon as a substitute, withincreasingly visually realistic representations of the real-world beingdeveloped. In the context of the complete autonomous vehicle control pipeline,subsystems downstream of perception need to be tested with accurate recreationsof the perception system output, rather than focusing on subjective visualrealism of the input - whether in simulation or the real world. This studydevelops the untapped potential of a lightweight weather augmentation method inan autonomous racing vehicle - focusing not on visual accuracy, but rather theeffect upon perception subsystem performance in real time. With minimaladjustment, the prototype developed in this study can replicate the effects ofwater droplets on the camera lens, and fading light conditions. This approachintroduces a latency of less than 8 ms using compute hardware well suited tobeing carried in the vehicle - rendering it ideal for real-time implementationthat can be run during experiments in simulation, and augmented reality testingin the real world.

Worsening Perception: Real-time Degradation of Autonomous Vehicle Perception Performance for Simulation of Adverse Weather Conditions