arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1902.03466cs.LGcs.CVcs.ROstat.ML
收藏

面向端到端驱动的分层多任务深度神经网络架构

Hierarchical Multi-task Deep Neural Network Architecture for End-to-End Driving

Greenfield Labs(格林菲尔德实验室);Ford Motor Company(福特汽车公司)

Jose Solomon, Francois Charette

摘要:

提出了一种新的分层深度神经网络(DNN)模型来解决端到端驱动的任务。该模型由主分类器网络组成,该主分类器网络从输入立体图像确定所需的驾驶任务,并将所述图像引导到一组从属网络回归模型中的一个,该从属网络回归模型执行推理并输出转向命令。这些从属网络是为特定的驾驶任务设计和训练的:直行、急转弯、急转弯、缓转弯和减速弯。使用这种模块化网络策略有两个主要优点:训练整个系统所需的数据量的总体减少,以及模型定制,其中更复杂的模型可以用于更具挑战性的任务,而简化的网络可以处理更平凡的任务。这是模型的后一个方面,使得该方法对当前车辆转向策略之外的许多应用具有吸引力。

英文摘要:

A novel hierarchical Deep Neural Network (DNN) model is presented to address the task of end-to-end driving. The model consists of a master classifier network which determines the driving task required from an input stereo image and directs said image to one of a set of subservient network regression models that perform inference and output a steering command. These subservient networks are designed and trained for a specific driving task: straightaway, swerve maneuver, tight turn, gradual turn, and chicane. Using this modular network strategy allows for two primary advantages: an overall reduction in the amount of data required to train the complete system, and for model tailoring where more complex models can be used for more challenging tasks while simplified networks can handle more mundane tasks. It is this latter facet of the model that makes the approach attractive to a number of applications beyond the current vehicle steering strategy.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑