自動運転のEnd-to-End制御における走行経験の転移手法
Driving Experience Transfer Method for End-to-End Control of Self-Driving Cars
CNNに車線逸脱度を出力するモジュールを追加し、ソースドメインで学習した特徴を目標ドメインの操舵制御に転移する手法を提案。シミュレータ間の転移実験で安定かつ安全な走行を実現した。
著者: Dooseop Choi, Taeg-Hyun An, Kyounghwan Ahn, Jeongdan Choi
分類: cs.CV, cs.RO
原文アブストラクト
In this paper, we present a transfer learning method for the end-to-end control of self-driving cars, which enables a convolutional neural network (CNN) trained on a source domain to be utilized for the same task in a different target domain. A conventional CNN for the end-to-end control is designed to map a single front-facing camera image to a steering command. To enable the transfer learning, we let the CNN produce not only a steering command but also a lane departure level (LDL) by adding a new task module, which takes the output of the last convolutional layer as input. The CNN trained on the source domain, called source network, is then utilized to train another task module called target network, which also takes the output of the last convolutional layer of the source network and is trained to produce a steering command for the target domain. The steering commands from the source and target network are finally merged according to the LDL and the merged command is utilized for controlling a car in the target domain. To demonstrate the effectiveness of the proposed method, we utilized two simulators, TORCS and GTAV, for the source and the target domains, respectively. Experimental results show that the proposed method outperforms other baseline methods in terms of stable and safe control of cars.
