Safety is a paramount concern in the realm of autonomous vehicles. Developing precise safety assessment is challenging due to the need to blend qualitative and quantitative analyses of various safety factors. To address this challenge, this paper presents an innovative safety assessment method based on the cloud model. This method employs fundamental cloud model elements like expectation, entropy, and ultra-entropy. It also employs a sophisticated double conditional single rule generator to integrate multiple assessment indicators, resulting in an integrated risk assessment cloud. This cloud dynamically represents varying risk levels based on indicator characteristics. The method evaluates the real-time safety level by assessing the proximity between the integrated risk assessment cloud and the standard cloud. This proximity analysis reveals the prevailing risk level. Empirical validation involves rigorous testing within typical scenarios, demonstrating the utility and potential of the method to assess safety for decision-making of autonomous vehicles. The capacity of the method to monitor and assess autonomous vehicle decision-making systems makes it a significant contribution to the field. Beyond empirical contributions, this paper offers theoretical insights that can shape the future of safety assessment methods for autonomous vehicles. In summary, this paper emphasizes the importance of safety for autonomous vehicles and paves the way for evolving safety assessment methods in this dynamic field.

Continual learning aims to learn a series of tasks sequentially without forgetting the knowledge acquired from the previous ones. In this work, we propose the Hessian Aware Low-Rank Perturbation algorithm for continual learning. By modeling the parameter transitions along the sequential tasks with the weight matrix transformation, we propose to apply the low-rank approximation on the task-adaptive parameters in each layer of the neural networks. Specifically, we theoretically demonstrate the quantitative relationship between the Hessian and the proposed low-rank approximation. The approximation ranks are then globally determined according to the marginal change of the empirical loss estimated by the layer-specific gradient and low-rank approximation error. Furthermore, we control the model capacity by pruning less important parameters to diminish the parameter growth. We conduct extensive experiments on various benchmarks, including a dataset with large-scale tasks, and compare our method against some recent state-of-the-art methods to demonstrate the effectiveness and scalability of our proposed method. Empirical results show that our method performs better on different benchmarks, especially in achieving task order robustness and handling the forgetting issue.

Nowadays, human-oriented has already become the direction of the development of the intelligent vehicle, among which, the cabin, in constant contact with drivers, is getting more and more attention. Intelligent assisted systems have alleviated the burden on drivers during long journeys and provided a remedy for operational errors. As the trend towards increasingly intelligent vehicles, the issue of human-machine co-driving is receiving attention from scientific researchers. The technologies of human-machine interactions usually contain two parts, the human-to-vehicle and vehicle-to-human. This paper analyzes the potential innovation of human-machine systems from the perspective of human sensing, including visual, auditory, tactile, and olfactory. Based on the review of human-machine technologies, the current intelligentization of vehicles is divided into driver interaction and crew service systems. Then, the structure of a future intelligent interaction system considering multi-sensing is proposed and further discussed. Finally, by analyzing the relationship between the system for human and autonomous systems, a classification of the intelligence level for interaction systems is presented.