Towards Autonomous Driving of Personal Mobility with Small and Noisy Dataset using Tsallis-statistics-based Behavioral Cloning

TL;DR

This paper proposes a Tsallis-statistics-based loss function for behavioral cloning in autonomous driving, enabling effective learning from small, noisy personal datasets by excluding non-optimal data and aligning the vehicle's focus with the driver.

Contribution

It introduces a novel loss function based on Tsallis statistics for robust behavioral cloning from limited, noisy datasets in personal mobility autonomous driving.

Findings

The proposed method successfully learned robust driving behavior from small, noisy datasets.

It achieved better alignment with the driver's focus compared to conventional methods.

Experimental results demonstrated successful autonomous driving with attention to the driver's region of interest.

Abstract

Autonomous driving has made great progress and been introduced in practical use step by step. On the other hand, the concept of personal mobility is also getting popular, and its autonomous driving specialized for individual drivers is expected for a new step. However, it is difficult to collect a large driving dataset, which is basically required for the learning of autonomous driving, from the individual driver of the personal mobility. In addition, when the driver is not familiar with the operation of the personal mobility, the dataset will contain non-optimal data. This study therefore focuses on an autonomous driving method for the personal mobility with such a small and noisy, so-called personal, dataset. Specifically, we introduce a new loss function based on Tsallis statistics that weights gradients depending on the original loss function and allows us to exclude noisy data in the optimization phase. In addition, we improve the visualization technique to verify whether the driver and the controller have the same region of interest. From the experimental results, we found that the conventional autonomous driving failed to drive properly due to the wrong operations in the personal dataset, and the region of interest was different from that of the driver. In contrast, the proposed method learned robustly against the errors and successfully drove automatically while paying attention to the similar region to the driver. Attached video is also uploaded on youtube: https://youtu.be/KEq8-bOxYQA