Deep anticipation: lightweight intelligent mobile sensing for unmanned vehicles in IoT by recurrent architecture. Issue 10 (2nd July 2019)

• Record Type: Journal Article
• Authors: Chen, Guang; Liu, Shu; Ren, Kejia; Qu, Zhongnan; Fu, Changhong; Hinz, Gereon; Knoll, Alois
• Is Part Of: IET intelligent transport systems. Volume 13:Issue 10(2019)
• Page Start: 1468
• Page End: 1474
• Publication Date: 2019-07-02
• Subjects: remotely operated vehicles -- neural nets -- mobile computing -- learning (artificial intelligence) -- recurrent neural nets -- quality of service -- Kalman filters -- Internet of Things; IoT communication -- neural architecture -- deep anticipation -- lightweight intelligent mobile sensing -- unmanned vehicles -- things techniques -- automated vehicles -- intelligent transportation system -- on‐board sensor perception system -- individual mobile applications -- mobile‐sensing perception system -- extensive intelligent system -- mobile sensing perception -- IoT data -- mission‐critical services -- quality of service -- communication challenge -- packet delay variation -- measurement noise -- recurrent neural networks; Intelligent transportation systems -- Periodicals; Electronics in transportation -- Periodicals; 388.31205
• DOI: 10.1049/iet-its.2019.0208
• Languages: English
• ISSNs: 1751-956X

Abstract

Abstract : Integrating Internet of things (IoT) techniques into automated vehicles has been a vision in intelligent transportation system, there is however seldom researches addressing it. To this end, we envision a scenario: short‐range on‐board sensor perception system attached to individual mobile applications such as vehicles are connected via IoT and transferred to long‐range mobile‐sensing perception system, which can be used as part of a more extensive intelligent system surveilling the environment. However, the mobile sensing perception brings new challenges for how to efficiently analyse and intelligently interpret the deluge of IoT data in mission‐critical services. Among these challenges, one bottelneck is the quality of service of IoT communication. In this article, we model the communication challenge as latency, packet delay variation and measurement noise which severely deteriorate the reliability and quality of IoT data. We propose a novel architecture that leverages recurrent neural networks and Kalman filtering to anticipate motions and interactions between objects. The model learns to develop a biased belief between prediction and measurement in different situations. We validate our neural architecture with synthetic and real‐world datasets with noise that mimics the challenges of IoT communications. The proposed neural architecture outperforms state‐of‐the‐art work in both computation time and model complexity.