Semi-autonomous driving, as it is already available today and will eventually
become even more accessible, implies the need for driver and automation system
to reliably work together in order to ensure safe driving. A particular
challenge in this endeavour are situations in which the vehicle's automation is
no longer able to drive and is thus requesting the human to take over. In these
situations the driver has to quickly build awareness for the traffic situation
to be able to take over control and safely drive the car. Within this context
we present a software and hardware framework to asses how aware the driver is
about the situation and to provide human-centred assistance to help in building
situation awareness. The framework is developed as a modular system within the
Robot Operating System (ROS) with modules for sensing the environment and the
driver state, modelling the driver's situation awareness, and for guiding the
driver's attention using specialized Human Machine Interfaces (HMIs).
A particular focus of this paper is on an Answer Set Programming (ASP) based
approach for modelling and reasoning about the driver's interpretation and
projection of the scene. This is based on scene data, as well as eye-tracking
data reflecting the scene elements observed by the driver. We present the
overall application and discuss the role of semantic reasoning and modelling
cognitive functions based on logic programming in such applications.
Furthermore we present the ASP approach for interpretation and projection of
the driver's situation awareness and its integration within the overall system
in the context of a real-world use-case in simulated as well as in real
driving.

软件和硬件框架评估驾驶员对交通状况的感知能力，并提供人机界面辅助以增强感知能力，重点介绍基于答案集规划的驾驶员场景解释和预测方法。

半自动驾驶车辆中评估驾驶员情境感知能力：基于 ASP 的驾驶动力学特征建模场景解释与预测

Assessing Drivers' Situation Awareness in Semi-Autonomous Vehicles: ASP  based Characterisations of Driving Dynamics for Modelling Scene  Interpretation and Projection

With the escalated demand of human-machine interfaces for intelligent
systems, development of gaze controlled system have become a necessity. Gaze,
being the non-intrusive form of human interaction, is one of the best suited
approach. Appearance based deep learning models are the most widely used for
gaze estimation. But the performance of these models is entirely influenced by
the size of labeled gaze dataset and in effect affects generalization in
performance. This paper aims to develop a semi-supervised contrastive learning
framework for estimation of gaze direction. With a small labeled gaze dataset,
the framework is able to find a generalized solution even for unseen face
images. In this paper, we have proposed a new contrastive loss paradigm that
maximizes the similarity agreement between similar images and at the same time
reduces the redundancy in embedding representations. Our contrastive regression
framework shows good performance in comparison to several state of the art
contrastive learning techniques used for gaze estimation.

通过使用半监督对比学习框架，本文提出了一种新的对比损失范式，从而实现了基于注视方向的估计，该框架在使用少量带有标签的注视数据集时，可以找到泛化解决方案，即使对于未见过的人脸图像也能有良好的性能表现，与其他用于注视估计的最先进对比学习技术相比，我们的对比回归框架表现良好。