A novel spatio-temporal trajectory data-driven development approach for autonomous vehicles

Nowadays,autonomous driving has been attracted widespread attention from academia and industry.As we all know,deep learning is effective and essential for the development of AI components of Autonomous Vehicles(AVs).However,it is challenging to adopt multi-source heterogenous data in deep learning.Therefore,we propose a novel data-driven approach for the delivery of high-quality Spatio-Temporal Trajectory Data(STTD)to AVs,which can be deployed to assist the development of AI components with deep learning.The novelty of our work is that the meta-model of STTD is constructed based on the domain knowledge of autonomous driving.Our approach,including collection,preprocessing,storage and modeling of STTD as well as the training of AI components,helps to process and utilize huge amount of STTD efficiently.To further demonstrate the usability of our approach,a case study of vehicle behavior prediction using Long Short-Term Memory(LSTM)networks is discussed.Experimental results show that our approach facilitates the training process of AI components with the STTD.

Research on identification of potential knowledge growth points in information science

The scientific system’s complexity makes it impossible to solve social problems by a single discipline independently,and interdisciplinary knowledge cooperation and innovation become an indispensable research mode of modern science.Identifying the potential interdisciplinary knowledge association is the key to promoting interdisciplinary cooperation.In this paper,based on analyzing the growth points of science,"knowledge growth point"is defined as the growth point of science that produces new knowledge,and its fundamental attributes and evaluation indexes have been analyzed.In contrast,the"interdisciplinary knowledge growth point"is defined as the introduction of related interdisciplinary concepts,theories,techniques,and methods,to conduct integrated research of key knowledge points of active disciplines,to generate growth point of innovative knowledge,and analyze its related research status.The identification of"potential interdisciplinary knowledge growth points"is helpful to promote knowledge innovation.Therefore,it is intended to analyze the identification methods of the generation of key knowledge nodes of the element of disciplines and interdisciplinary related knowledge,and explore quantitative and qualitative consultation to identify potential interdisciplinary knowledge growth points.

A proof-based method of hybrid systems development using differential invariants

1 Introduction Event-B is a widely applied and proof-based language for incremental development via refinement [1]. Hybrid systems exhibit hybrid characteristics of discrete control and real-time continuous behaviors. However, Event-B is a discrete modeling language. It does not support the development of hybrid systems. So, the researchers are currently trying to make the extension of Event-B for the refinement development of hybrid systems [2, 3].