Explore the vast range of titles available.

Autonomous vehicles (AVs) rely heavily on sensors to perceive their surrounding environment and then make decisions and act on them. However, these sensors have weaknesses, and are prone to failure, resulting in decision errors by vehicle controllers that pose significant challenges to their safe operation. To mitigate sensor failures, it is necessary to understand how they occur and how they affect the vehicle’s behavior so that fault-tolerant and fault-masking strategies can be applied. This survey covers 108 publications and presents an overview of the sensors used in AVs today, categorizes the sensor’s failures that can occur, such as radar interferences, ambiguities detection, or camera image failures, and provides an overview of mitigation strategies such as sensor fusion, redundancy, and sensor calibration. It also provides insights into research areas critical to improving safety in the autonomous vehicle industry, so that new or more in-depth research may emerge.

This paper develops a new fault-tolerant control (FTC) of wireless sensor network in vehicle that aims to solve three problems in engineering practice: lack of data in sensor failure state, high system complexity and multiple sensors concurrent failure. In the new FTC framework, a new belief rule base expert system for concurrent events is developed to aggregate the data and knowledge and handle the concurrent events. In the FTC framework, fault detection and diagnosis (FDD) part is firstly conducted, and then, the output of the failure sensors is reconstructed based on the output reconstruction strategy by the observation information from the available sensors. In the FDD model, the fault diagnosis strategy of proximity classification based on distance is applied in the FDD model. To further improve the performance of the FTC framework, a new optimization model is proposed. A case study is conducted to illustrate the effectiveness of the proposed framework.

This paper proposes a fault-tolerant control (FTC) strategy using the current space vectors to diagnose sensor failures and enhance the sustained operation of a field-oriented (FO) controlled induction motor drive (IMD). Three space vectors are established for the sensor fault diagnosis technique, including one converted from the measured currents and the other two calculated from the current estimation technique, respectively, measured and with reference speeds. A mixed mathematical model using three space vectors and their components is proposed to accurately determine the fault condition of each sensor in the motor drive. After determining the operating status of each sensor, if the sensor signal is in good condition, the feedback signal to the controller will be the measured signal; otherwise, the estimated signal will be used instead of the failed signal. Failure states of the various sensors were simulated to check the effectiveness of the proposed technique in the Matlab/Simulink environment. The simulation results are positive: the IMD system applying the proposed FTC technique accurately detected the failed sensor and maintained stability during the operation.

This paper presents a novel approach for detecting sensor failures using image-based feature representation and the Convolutional Variational Autoencoder (CVAE) model. Existing methods are limited when analyzing multiple failure modes simultaneously or adapting to diverse sensor data. This limitation may compromise decision-making and system performance, hence the need for more flexible and resilient models. The proposed approach transforms sensor data into image-based feature representations of statistics such as mean, variance, kurtosis, entropy, skewness, and correlation. The CVAE is trained on such image representations, and the corresponding reconstruction error leads to a Health Index (HI) for detecting multiple sensor failures. Moreover, the CVAE latent space is used to define a complementary HI and a convenient visualization tool, enhancing the interpretability of the proposed approach. The evaluation of the proposed detection approach with data comprising diverse configurations of faulty sensors showed encouraging results. The proposed approach is illustrated in an industrial case study emerging from the aeronautical domain, with data from a complex electromechanical system comprising nearly 80 sensor measurements at a 1 Hz sampling rate. The results demonstrate the potential of the proposed method in detecting multiple sensor failures.

DC microgrids have become a viable solution for modern power distribution systems because they offer better control, improved efficiency, and simpler integration with renewable energy sources and energy storage systems. However, the performance of low-voltage DC microgrids can suffer from stability issues related to unpredictable sensor faults, parameter uncertainty, and equipment failure. In recent years, disturbance-rejection methods and robust control methods have been effective in improving microgrid resilience during these situations. This paper proposes a decentralized sensor fault-tolerant control approach for an islanded low-voltage DC (LVDC) microgrid using the active disturbance rejection control (ADRC). The ADRC control preserves the DC grid stability in the presence of unknown and time variant sensor faults by estimating and compensating for lumped disturbances through an extended state observer without the need for fault detection or reconfiguration of the system. A thorough mathematical model and an analytical control formulation are provided and thoroughly examined through single, consecutive, and simultaneous sensor-fault scenarios. Time-domain nonlinear simulation studies on a multi-DG DC microgrid show that the proposed controller provides better voltage regulation, faster transient recovery, and better robustness compared to other proposed methods in the literature, such as the conventional autotune PI controllers and the attractive ellipsoidal–based methods. The simulation studies’ results verified that the proposed ADRC scheme noticeably increases the reliability and resilience of the DC microgrid under realistic simulation conditions of sensor faults.

To address the challenges of high structural noise, unstable operating conditions, and susceptibility to single-channel failure in multi-sensor monitoring of industrial robot transmission components, this paper proposes a cross-machines domain generalized fault diagnosis method based on fault intrinsic representation and channel self-healing. This method aims to extract essential fault characteristics from distinctive public datasets and transfer them to complex industrial robot target scenarios. First, considering the characteristics of single-point multi-directional monitoring of robot joints, a dual-channel vibration feature extraction framework is constructed. Information enhancement and splicing are used to generate intra-domain and cross-domain joint features. Combined with a set-level class-prototype regularized mechanism, the distribution differences specific to the operating conditions are decoupled and eliminated from multi-source domain data, extracting the common fault intrinsic representations across datasets. Second, to solve the monitoring blind spot problem caused by single sensor failure, a semantically supervised channel self-heal module is designed. This module uses the feature distribution of intact channels to deduce the semantic information of missing channels, achieving signal self-healing and complementation during the testing phase. Finally, rigorous cross-machines transfer experiments are designed using three public datasets containing basic fault characteristics as source domains. Zero-shot tests are conducted on the gearbox dataset characterized by high structural noise and the bearing dataset featuring extreme non-stationary start-stop conditions. Experimental results demonstrate that the proposed method effectively overcomes cross-machines distribution shifts and maintains high-precision fault diagnosis, even under extreme conditions of complete single-channel sensor failure, verifying the feasibility and robustness of transferring laboratory data to complex robot application scenarios.

Local Positioning Systems are collecting high research interest over the last few years. Its accurate application in high-demanded difficult scenarios has revealed its stability and robustness for autonomous navigation. In this paper, we develop a new sensor deployment methodology to guarantee the system availability in case of a sensor failure of a five-node Time Difference of Arrival (TDOA) localization method. We solve the ambiguity of two possible solutions in the four-sensor TDOA problem in each combination of four nodes of the system by maximizing the distance between the two possible solutions in every target possible location. In addition, we perform a Genetic Algorithm Optimization in order to find an optimized node location with a trade-off between the system behavior under failure and its normal operating condition by means of the Cramer Rao Lower Bound derivation in each possible target location. Results show that the optimization considering sensor failure enhances the average values of the convergence region size and the location accuracy by 31% and 22%, respectively, in case of some malfunction sensors regarding to the non-failure optimization, only suffering a reduction in accuracy of less than 5% under normal operating conditions.

Deep Reinforcement learning (DRL) is used to enable autonomous navigation in unknown environments. Most research assumes perfect sensor data, but real-world environments may contain natural and artificial sensor noise and denial. Here, we present a benchmark of both well-used and emerging DRL algorithms in two navigation tasks - Lidar + position, and vision end-to-end - with configurable sensor denial effects. In particular, we are interested in comparing how different DRL methods (e.g. model-free, on-policy PPO vs. model-free off-policy TD3, vs. model-based DreamerV3) are affected by imperfect sensor readings. We show that DreamerV3 outperforms other methods in the visual end-to-end navigation task with a dynamic goal. Furthermore, DreamerV3 generally outperforms other methods in sensor-denied environments. In order to improve robustness, we use adversarial training and demonstrate an improved performance in denied environments, although we show that this may lead to the agent learning to choose high-risk actions in case of uncertain sensor readings, which is not appropriate for safety-critical scenarios. We anticipate this benchmark of different DRL methods and the usage of adversarial training to be a starting point for the development of more elaborate navigation strategies that are capable of dealing with uncertain and denied sensor readings.

DC Microgrids are becoming increasingly popular for their efficiency and suitability for integrating renewable energy source and energy storage systems. However, unexpected sensor faults can severely compromise voltage regulation, current sharing, and overall system stability, posing a risk, especially for critical applications. Existing resilient control schemes for DC Microgrids often relies on hardware redundancy, multiple observers, or communication-based fault mitigation, leading to slow fault mitigation, increased cost, complexity, and vulnerability to cyber threat. To address the limitations of existing methods this paper proposes real-time reconfiguration framework to tolerate adverse sensor faults in islanded DC Microgrids. The proposed scheme leverages a single Proportional Integral Unknown Input Observer (PI-UIO) to reconstruct sensor faults and reconfigure a decentralized Passivity Based Control (PBC) at the primary level and a distributed consensus based current sharing controller at the secondary level. Unlike conventional methods, the proposed scheme operates autonomously without communication, thus enhancing the scalability, reliability and resilience against cyberattacks. Moreover, the design of the PI-UIO and PBC is achieved with decentralized parameters to enable seamless plug-and-play integration. Extensive simulation and real time simulation results validate the effectiveness and superiority of the proposed FTC framework compared with the recent methods.

This paper studies the H ∞ filtering problem of discrete-time singular nonlinear systems in encrypted state which are represented by Takagi-Sugeno (T-S) fuzzy model, meantime, quantization, signal missing and filter failure are considered. This paper selects the measurement output and the filter output for quantization, the sensor failure of the systems, the loss of the estimated signal and filter output signals are considered. Then, the admissible condition of the filtering error system is calculated and verified, and the condition meets the specific H ∞ performance index. By quoting a new Lyapunov function, the design conditions of the filter and the adjustment parameters of the quantizers are obtained. Finally, the feasibility of this method is verified by a circuit example.