Both response time and reliability are important functional safety properties that must be simultaneously satisfied learning from the automotive functional safety standard ISO 26262. Safety verification pertains to checking if an application meets a safe set of design specifications and complies with regulations. Introducing verification in the early design phase not only complies with the latest automotive functional safety standard but also avoids unnecessary design effort or reduces the design burden of the late design optimization phase. This study presents a fast functional safety verification (FFSV) method for a distributed automotive application during the early design phase. The first method FFSV1 finds the solution with the minimum response time under the reliability requirement, and the second method FFSV2 finds the solution with the maximum reliability under the response time requirement. We combine FFSV1 and FFSV2 to create union FFSV (UFFSV), which can obtain acceptance ratios higher than those of current methods. Experiments on real-life and synthetic distributed automotive applications show that UFFSV can obtain higher acceptance ratios than their existing counterparts.
29 August 2022 in IEEE Transactions on Industrial Informatics
Intelligent connected vehicle is rapidly growing with the 5-G technology; the diversity of functional interfaces has significantly expanded the avenues of attack, making automotive controller area network (CAN) more vulnerable to cyberthreats. Automotive CAN network attacks are a direct threat to traffic safety, and in this study, we explore the use of intrusion detection techniques for mitigating cyberattacks. However, most automotive CAN network intrusion detection technologies are not capable of defending against sophisticated attacks, making it extremely challenging for detecting intrusions in practice. In this article, we propose a novel time interval conditional entropy method for detecting intrusions in automotive CAN networks. The time interval conditional entropy intrusion detection method is not susceptible to interference and is capable of detecting a variety of attacks. In our experiments, the conditional entropy values of regular communication messages are collected and utilized to distinguish and detect the attacks. The time interval conditional entropy detection method is implemented and evaluated in our controller area net-work bus (CAN-BUS) network platform. The experiments show that our method has higher detection accuracy and is easier to deploy compared to existing automotive CAN network intrusion detection methods.
ISO 26262 is a functional safety standard specifically made for automotive systems, in which the automotive safety integrity level (ASIL) is the representation of the criticality level. Recently, most studies have used ASIL decomposition to reduce the development cost of automotive functions. However, these studies have not paid special attention to the problem that the reliability goal may not be satisfied when ASIL decomposition is performed. In this study, we solve the problem of minimizing the development cost of a distributed automotive function while satisfying its reliability goal during the design phase by presenting two heuristic algorithms, reliabilitycalculation of scheme (RCS) and minimizing development cost with reliability goal (MDCRG). We first use RCS to calculate the reliability value of each ASIL decomposition scheme; then, the MDCRG is used to select the scheme with the minimum development cost while satisfying the reliability goal. Real-life benchmark and simulated functions based on real parameter values are used in experiments, and results show the effectiveness of the proposed algorithms.
Multi-Agent Reinforcement Learning (MARL) is extensively utilized for addressing intricate tasks that involve cooperation and competition among agents in Multi-Agent Systems (MAS). However, learning such tasks from scratch is challenging and often unfeasible, especially for MASs with a large number of agents. Hence, leveraging knowledge from prior experiences can effectively expedite the MARL learning process. Prior work has shown that we successfully facilitated transfer learning for MARL by consolidating various state spaces into fixed-size inputs, enabling a single unified deep-learning policy applicable to several scenarios within the StarCraft Multi-Agent Challenge (SMAC) environment. In this study, we expand SMAC to Multi-Player enabled SMAC (MP-SMAC) by enabling the dynamic selection of training opponents and introducing a co-evolving MARL framework, which creates a co-evolutionary arena where multiple policies learn simultaneously. Our arena comprised the simultaneous training of multiple policies in diverse scenarios, pitting them against both static AI opponents and their peers within MP-SMAC. Furthermore, we integrate co-evolution with curriculum transfer learning into Co-MACTRL framework, enabling our MARL policies to systematically acquire knowledge and skills across predetermined scenarios organized by varying difficulty levels, including evolving opponents. The results revealed significant enhancements in MARL learning performance, demonstrating the advantage of leveraging the co-evolving opponents and maneuvering skills obtained from different scenarios. Additionally, the Co-MACTRL learners consistently attained high performance across a range of SMAC scenarios, showcasing the robustness and generalizability of Co-MACTRL.