Survey on Multi-Task Learning in Smart Transportation

Abstract

Artificial Intelligence (AI) has been widely adopted in numerous fields and enabled various smart systems because of its strong ability to perform tasks, including prediction, event detection, and status estimation, among others. As one of the typical smart systems empowered by AI and Internet of Things (IoT) technologies, the smart transportation system has made dramatic progress for traditional transportation in numerous aspects, including autonomous driving, smart traffic lights, navigation, and traffic forecasting, among others. Deep learning is an essential component to enable such smart systems. Typically, specific deep learning models, e.g., Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN), can be trained on collected transportation data for a particular task. However, traditional deep learning techniques rely on data sufficiency to build an effective model. Additionally, each trained model can only work on one single task. This has limited the efficacy of deep learning techniques in numerous application scenarios. To this end, multi-task learning (MTL) has been studied to train a single model that can work for multiple tasks. This technique effectively allows the learning model to expand to specific tasks with only a limited amount of data affiliated. In the meantime, MTL significantly reduces the training time of each task. The success of MTL requires that there are potential relationships among different tasks. Many tasks in the smart transportation system are related. For instance, traffic speed and vehicle volume estimations for each road are highly correlated. Based on this, research on applying MTL in smart transportation systems has been studied recently. This paper reviews the recent efforts to use MTL in smart transportation systems and conducts an extensive survey to provide insights. In particular, we categorize the MTL applications in smart transportation systems into traffic forecasting, traffic sign recognition, vehicle recognition, travel time estimation, road safety estimation, taxi demand prediction, and autonomous driving. Ultimately, we discuss challenges and future research directions in applying MTL in smart transportation systems.

Keywords

• Multi-task learning (MTL)
• smart transportation
• deep learning