arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.05777cs.DC
收藏

下一代汽车平台上ADAS管线的智能显示

Intelligent Orchestration of ADAS Pipelines on Next Generation Automotive Platforms

Anirban Ghose, Srijeeta Maity, Arijit Kar, Kaustubh Maloo, Soumyajit Dey

摘要:

高级驾驶辅助系统(ADAS)是在这个互联移动时代提高自主性和驾驶舒适性的主要驱动力之一。然而,这样的系统的性能是执行率的函数,需要板载平台级的支持。随着GPGPU平台进入汽车领域,存在一个机会,通过利用架构异构性,牢记热可靠性和长期平台老化,自适应地支持ADAS任务的高执行速率。我们提出了一个面向未来的,基于学习的自适应调度框架,利用强化学习来发现合适的基于场景的任务映射决策,以适应增加的任务级吞吐量要求。

英文摘要:

Advanced Driver-Assistance Systems (ADAS) is one of the primary drivers behind increasing levels of autonomy, driving comfort in this age of connected mobility. However, the performance of such systems is a function of execution rate which demands on-board platform-level support. With GPGPU platforms making their way into automobiles, there exists an opportunity to adaptively support high execution rates for ADAS tasks by exploiting architectural heterogeneity, keeping in mind thermal reliability and long-term platform aging. We propose a future-proof, learning-based adaptive scheduling framework that leverages Reinforcement Learning to discover suitable scenario based task-mapping decisions for accommodating increased task-level throughput requirements.

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。

↑