Modular Vehicle Control for Transferring Semantic Information Between Weather Conditions Using GANs

TL;DR

This paper presents a modular vehicle control approach that uses GANs to transfer semantic information across different weather conditions, enabling robust steering prediction without retraining on new weather data.

Contribution

It introduces a novel modular framework with GAN-based semantic transfer and a master-servant architecture for weather-invariant vehicle control.

Findings

Achieves similar steering accuracy across 15 weather conditions as end-to-end models trained on all conditions.

Uses unsupervised GANs to generate semantic data for unseen weather scenarios.

Demonstrates effective transfer learning with minimal additional data.

Abstract

Even though end-to-end supervised learning has shown promising results for sensorimotor control of self-driving cars, its performance is greatly affected by the weather conditions under which it was trained, showing poor generalization to unseen conditions. In this paper, we show how knowledge can be transferred using semantic maps to new weather conditions without the need to obtain new ground truth data. To this end, we propose to divide the task of vehicle control into two independent modules: a control module which is only trained on one weather condition for which labeled steering data is available, and a perception module which is used as an interface between new weather conditions and the fixed control module. To generate the semantic data needed to train the perception module, we propose to use a generative adversarial network (GAN)-based model to retrieve the semantic information for the new conditions in an unsupervised manner. We introduce a master-servant architecture, where the master model (semantic labels available) trains the servant model (semantic labels not available). We show that our proposed method trained with ground truth data for a single weather condition is capable of achieving similar results on the task of steering angle prediction as an end-to-end model trained with ground truth data of 15 different weather conditions.