Measuring Novelty in Autonomous Vehicles Motion Using Local Outlier Factor Algorithm

04/24/2021
by   Hassan Alsawadi, et al.
0

Under unexpected conditions or scenarios, autonomous vehicles (AV) are more likely to follow abnormal unplanned actions, due to the limited set of rules or amount of experience they possess at that time. Enabling AV to measure the degree at which their movements are novel in real-time may help to decrease any possible negative consequences. We propose a method based on the Local Outlier Factor (LOF) algorithm to quantify this novelty measure. We extracted features from the inertial measurement unit (IMU) sensor's readings, which captures the vehicle's motion. We followed a novelty detection approach in which the model is fitted only using the normal data. Using datasets obtained from real-world vehicle missions, we demonstrate that the suggested metric can quantify to some extent the degree of novelty. Finally, a performance evaluation of the model confirms that our novelty metric can be practical.

READ FULL TEXT
research
08/30/2023

High Performance Networking Layer for Simulation Applications

Autonomous vehicles are one of the most popular and also fast-growing te...
research
08/05/2020

Activity and mood-based routing for autonomous vehicles

A significant amount of our daily lives is dedicated to driving, leading...
research
06/05/2020

Unsupervised Abnormality Detection Using Heterogeneous Autonomous Systems

Anomaly detection in a surveillance scenario is an emerging and challeng...
research
06/24/2019

Internet of Autonomous Vehicles: Architecture, Features, and Socio-Technological Challenges

Mobility is the backbone of urban life and a vital economic factor in th...
research
04/13/2021

Inertial Collaborative Localisation for Autonomous Vehicles using a Minimum Energy Filter

Collaborative Localisation has been studied extensively in recent years ...
research
06/17/2019

Normalizing flows for novelty detection in industrial time series data

Flow-based deep generative models learn data distributions by transformi...
research
05/27/2020

An Entropy Based Outlier Score and its Application to Novelty Detection for Road Infrastructure Images

A novel unsupervised outlier score, which can be embedded into graph bas...

Please sign up or login with your details

Forgot password? Click here to reset