Pre-trained models for Natural Languages (NL) like BERT and GPT have been recently shown to transfer well to Programming Languages (PL) and largely benefit a broad set of code-related tasks. Despite their success, most current methods either rely on an encoder-only (or decoder-only) pre-training that is suboptimal for generation (resp. understanding) tasks or process the code snippet in the same way as NL, neglecting the special characteristics of PL such as token types. We present CodeT5, a unified pre-trained encoder-decoder Transformer model that better leverages the code semantics conveyed from the developer-assigned identifiers. Our model employs a unified framework to seamlessly support both code understanding and generation tasks and allows for multi-task learning. Besides, we propose a novel identifier-aware pre-training task that enables the model to distinguish which code tokens are identifiers and to recover them when they are masked. Furthermore, we propose to exploit the user-written code comments with a bimodal dual generation task for better NL-PL alignment. Comprehensive experiments show that CodeT5 significantly outperforms prior methods on understanding tasks such as code defect detection and clone detection, and generation tasks across various directions including PL-NL, NL-PL, and PL-PL. Further analysis reveals that our model can better capture semantic information from code. Our code and pre-trained models are released at https: //github.com/salesforce/CodeT5.

No abstract

Information-aware connected and automated vehicles (CAVs) have drawn great attention in recent years due to its potentially significant positive impacts on roadway safety and operational efficiency. In this paper, we conduct an in-depth review of three basic and key interrelated aspects of a CAV: sensing and communication technologies, human factors, and information-aware controller design. First, different vehicular sensing and communication technologies and their protocol stacks, to provide reliable information to the information-aware CAV controller, are thoroughly discussed. Diverse human factor issues, such as user comfort, preferences, and reliability, to design the CAV systems for mass adaptation are also discussed. Then, different layers of a CAV controller (route planning, driving mode execution, and driving model selection) considering human factors and information through connectivity are reviewed. In addition, critical challenges for the sensing and communication technologies, human factors, and information-aware controller are identified to support the design of a safe and efficient CAV system while considering user acceptance and comfort. Finally, promising future research directions of these three aspects are discussed to overcome existing challenges to realize a safe and operationally efficient CAV.Automated vehicle (AV) field testing began in 1986 in the United States when the Partners for Advanced Transit and Highways (PATH) program at the University of California Berkley developed a platooning application of six AVs in specially guided highway sections [1]. Since, the most significant AV development was prompted by the Defense Advanced Research Projects Agency (DARPA) Urban Challenge 2007, which accelerated private sector AV research and development. Since then, major automobile companies including internet giant Google have developed the prototypes of AVs that need no special highway infrastructure to operate in mixed traffic scenarios [2,3]. In a research by Bhavsar et al. concluded that although there is a considerable risk of AV sensor failure, future innovations in computation and communication technologies as well as backup sensors can significantly reduce the failure probability of AVs in a mixed traffic stream (which includes AVs and non-AVs) [4]. To facilitate the development of AV technologies, several US states issued special permits to AV technology manufactures conducting pilot testing, most notably in California, automated vehicle laws was issued on February 26, 2018 [5]. This interest in AV technology from both the automotive industry and the public sector will advance the development of fully automated (i.e., autonomous or level 5 automation) vehicle development in the next decade.The Society of Automotive Engineers (SAE) has a classification scheme for automated vehicles with six levels from no-automation (level 0) to full automation (level 5) [6]. Full vehicle automation enables maximum benefit in terms of traffic safety, efficiency, and environmental impacts. According to a r...

No abstract

No abstract