Measuring Novelty in Autonomous Vehicles Motion Using Local Outlier Factor Algorithm
This work addresses safety issues for autonomous vehicles by enabling real-time novelty detection, but it is incremental as it applies an existing algorithm to a new domain.
The paper tackled the problem of autonomous vehicles (AVs) encountering unexpected conditions by proposing a method to measure the novelty of their motions in real-time, using the Local Outlier Factor (LOF) algorithm on IMU sensor data, and demonstrated its ability to quantify novelty to some extent with performance evaluation confirming practicality.
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.