Passive and Active Learning of Driver Behavior from Electric Vehicles

03/04/2022
by   Federica Comuni, et al.
0

Modeling driver behavior provides several advantages in the automotive industry, including prediction of electric vehicle energy consumption. Studies have shown that aggressive driving can consume up to 30 moderate driving, in certain driving scenarios. Machine learning methods are widely used for driver behavior classification, which, however, may yield some challenges such as sequence modeling on long time windows and lack of labeled data due to expensive annotation. To address the first challenge, passive learning of driver behavior, we investigate non-recurrent architectures such as self-attention models and convolutional neural networks with joint recurrence plots (JRP), and compare them with recurrent models. We find that self-attention models yield good performance, while JRP does not exhibit any significant improvement. However, with the window lengths of 5 and 10 seconds used in our study, none of the non-recurrent models outperform the recurrent models. To address the second challenge, we investigate several active learning methods with different informativeness measures. We evaluate uncertainty sampling, as well as more advanced methods, such as query by committee and active deep dropout. Our experiments demonstrate that some active sampling techniques can outperform random sampling, and therefore decrease the effort needed for annotation.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/01/2023

A Novel Driver Distraction Behavior Detection Based on Self-Supervised Learning Framework with Masked Image Modeling

Driver distraction causes a significant number of traffic accidents ever...
research
02/11/2021

Driving Style Representation in Convolutional Recurrent Neural Network Model of Driver Identification

Identifying driving styles is the task of analyzing the behavior of driv...
research
06/07/2020

How useful is Active Learning for Image-based Plant Phenotyping?

Deep learning models have been successfully deployed for a diverse array...
research
06/26/2018

Dropout-based Active Learning for Regression

Active learning is relevant and challenging for high-dimensional regress...
research
07/02/2018

Semi-supervised Learning: Fusion of Self-supervised, Supervised Learning, and Multimodal Cues for Tactical Driver Behavior Detection

In this paper, we presented a preliminary study for tactical driver beha...
research
03/17/2023

Hierarchical-Hyperplane Kernels for Actively Learning Gaussian Process Models of Nonstationary Systems

Learning precise surrogate models of complex computer simulations and ph...
research
08/11/2021

Unsupervised Driver Behavior Profiling leveraging Recurrent Neural Networks

In the era of intelligent transportation, driver behavior profiling has ...

Please sign up or login with your details

Forgot password? Click here to reset