Search

Fault tolerance is a critical aspect of modern computing systems, ensuring correct functionality in the presence of faults. This paper presents a comprehensive survey of fault tolerance methods and mitigation techniques in embedded systems, with a focus on both software and hardware faults. Emphasis is placed on real-time embedded systems, considering their resource constraints and the increasing interconnectivity of computing systems in commercial and industrial applications. The survey covers various fault tolerance methods, including hardware, software, and hybrid redundancy. Particular attention is given to software faults, acknowledging their significance as a leading cause of system failures, while also addressing hardware faults and their mitigation. Moreover, the paper explores the challenges posed by soft errors in modern computing systems. The survey concludes by emphasizing the need for continued research and development in fault tolerance methods, specifically in the context of real-time embedded systems, and highlights the potential for extending fault tolerance approaches to diverse computing environments.

The current trends of the automotive industry, namely Automation, Connection, and Electrification, place novel challenges in product development. In particular, the industry needs to increase vehicle computational power availability, trying to keep the same costs as in the past. Of course, since automotive applications can affect people’s safety, there is also the need to keep the same reliability levels with fewer hardware components to limit costs. Another advantage is that considering the usage of Commercial-Off-The-Shelf chiplets featuring multiple cores with diverse levels of integrities, it allows the use of lower-integrity ones, increasing the overall computation capabilities for a given component. This paper proposes a novel approach based on Software-Implemented Hardware Fault Tolerance, such as Control Flow Checking and Data Hardening, to move forward in this direction, addressing mixed-criticality multi-core systems. The main focus is exploiting the computational power of lower-integrity cores or hardware accelerators to execute safety-critical tasks without increasing the risk level. The effectiveness of the proposed approach has been demonstrated by fault injection campaigns on a real, yet simplified, AUTOSAR-compliant automotive application. Considering the Control Flow Checking Algorithms, the approach moved the DC from around 10% (without multi-core timeout detection strategy) up to around 45% (with timeout detection). For the hybrid data hardening, the approach Diagnostic Coverage is around 15% for integer and floating point values. The absence of residual faults shows that the proposed solution can complement other functional safety strategies, even if insufficient to guarantee the metrics for an ASIL D application.

Random hardware failures (RHFs) may result in data corruption and Control Flow Errors (CFEs). Hardening strategies are employed to mitigate RHFs in embedded systems, either by adding specialized hardware or using Software-Implemented Hardware Fault Tolerance (SIHFT) methods. Numerous SIHFT methods have been presented over the years to improve the reliability of embedded systems. However, evaluating these methods can be challenging in terms of the introduced overhead to the code size and, particularly important for real-time application execution time. Most of them are implemented in the literature using low-level languages such as Assembly. Unfortunately, writing Assembly code is not the preferred development flow for embedded systems applications since functional safety standards require adopting high-level programming languages such as C. Nowadays, there is still a non-negligible portion of code written in the Assembly language where the compiler can automatically insert the SIHFT methods, but these are limited to some high-optimized routines or device drivers. It is possible to compile an application code and then harden the obtained assembly code. But this introduces a greater overhead than just protecting a single statement in the high-level programming language before compiling. Hence, the approach we present in this paper is to apply SIHFT methods against CFEs, known in the literature as Control Flow Checking (CFC), to the application code written in C language, before compiling the application code. To illustrate the proposal, two established software-based control flow error detection techniques implemented in the C programming language were compared, also considering the effects of the optimizations introduced by the compiler. Most SIHFT methods target only soft errors, such as single-event upsets, which typically appear as bit flips. As a result, the diagnostic figures provided in the literature are insufficient to characterize the techniques effectively. To address this gap, in this paper, we consider a scenario from the automotive industry in which the primary concern is permanent random hardware faults, particularly stuck-at faults. Moreover, we propose a classification compliant with ISO26262 to benefit those developers involved in the automotive market, where software-only strategies may be used to balance cost and safety requirements.

Traffic accidents due to drivers falling asleep while driving is an important cause of death, and effective techniques for coping with this phenomenon are needed. In this paper we present a simple, yet effective algorithm, based on heart rate variability analysis. Results of the experimental validation are reported: two test sessions were performed, one in domestic environments and one in realistic driving environments by using a dynamic driving simulator. The results confirm the results obtained in the previous work (Groppo et al., 2020), and the capability of the proposed algorithm in predicting sleep while driving using a physiological signal that can be collected at the wrist of the driver.

Mechatronic systems, like mobile robots, are fairly complex. They are composed of electromechanical actuation components and sensing elements supervised by microcontrollers running complex embedded software. This paper proposes a novel approach to aid mobile robotics developers in adopting a rigorous development process to design and verify the robot’s detection and mitigation capabilities against random hardware failures affecting its sensors or actuators. Unfortunately, assessing the interactions between the various safety/mission-critical subsystem is quite complex. The failure mode effect analysis (FMEA) alongside an analysis of the failure detection capabilities (FMEDA) are the state-of-the-art methodologies for performing such an analysis. Various guidelines are available, and the authors decided to follow the one released by AIAG&VDA in June 2019. Since the robot’s behavior is based on embedded software, the FMEA has been integrated with the hardware/software interaction analysis described in the ECSS-Q-ST-30-02C manual. The core of this proposal is to show how a simulation-based approach, where the mechanical and electrical/electronic components are simulated alongside the embedded software, can effectively support FMEA. As a benchmark application, we considered the mobility system of a proof-of-concept assistance rover for Mars exploration designed by the D.I.A.N.A. student team at Politecnico di Torino. Thanks to the adopted approach, we described how to develop the detection and mitigation strategies and how to determine their effectiveness, with a particular focus on those affecting the sensors.

Teaching is an activity that requires understanding the class’s reaction to evaluate the teaching methodology effectiveness. This operation can be easy to achieve in small classrooms, while it may be challenging to do in classes of 50 or more students. This paper proposes a novel Internet of Things (IoT) system to aid teachers in their work based on the redundant use of non-invasive techniques such as facial expression recognition and physiological data analysis. Facial expression recognition is performed using a Convolutional Neural Network (CNN), while physiological data are obtained via Photoplethysmography (PPG). By recurring to Russel’s model, we grouped the most important Ekman’s facial expressions recognized by CNN into active and passive. Then, operations such as thresholding and windowing were performed to make it possible to compare and analyze the results from both sources. Using a window size of 100 samples, both sources have detected a level of attention of about 55.5% for the in-presence lectures tests. By comparing results coming from in-presence and pre-recorded remote lectures, it is possible to note that, thanks to validation with physiological data, facial expressions alone seem useful in determining students’ level of attention for in-presence lectures.