Search

Many autonomous vehicles and advanced driver-assistance systems are equipped with front-facing cameras that detect and track objects using deep-learning-based algorithms. However, the localization capability of monocular cameras is often overlooked. In this paper, a novel method for estimating the pixel-wise error in a detected object's location versus its ground truth is proposed. As the object moves away from the camera, the pixel errors are shown to be normally distributed with unique spreads along the image's vertical axis (y-pixel). The pixel error appears to be smaller as objects get farther away, while at the same distance range, objects have similar error distribution across the camera's horizontal view. The horizontal axis (x-pixel) error appears to be smaller while the distance moves further away. However, the x-pixel location along a constant y-pixel row has no impact on the error distribution. The estimated x and y-pixel error distributions can in turn be used to form a spatial error distribution for finding the location of a detected object within a certain confidence interval. The spatial errors are then projected onto the world coordinate system using a camera transformation matrix to give a more realistic sense of what this error means. The results show that location estimation using monocular cameras generates an elliptical error distribution around the object with a larger error in the y-pixel direction compared to the x-pixel direction. This error distribution can be important to fuse information from multiple range-detecting sensors as well as multi-vehicle and multi-object tracking. The uncertainty characterization for position measurement, as demonstrated in this paper is an essential element of tracking and, is sensor and algorithm dependent. [ABSTRACT FROM AUTHOR]

Model-based state-of-charge (SOC) and state-of-health (SOH) estimation for lithium-ion batteries has been widely applied in electrified vehicles, while the SOC and SOH estimators are highly coupled and nonlinear in conventional techniques. This leads to a bulky design of observer network and complicates the stability analyses. In this article, a new reduced-decoupling SOC and SOH coestimation algorithm based on convex optimization is proposed. This scheme estimates the battery SOC from the battery model and does not require the classic Coulomb-counting method. Therefore, it can decouple the capacity estimation from the SOC estimator and reduce the strong interaction existing in conventional coestimation methods. Besides, all state variables can be solved together by one estimator, which is straightforward and avoids the complicated observer network. Owing to the decoupling design, the stability of the proposed method becomes more intuitive and can be always guaranteed according to the convexity analysis without using other stabilizing approaches. In consequence, a weak-interaction and robust coestimation algorithm of SOC and SOH can be realized by the proposed technique. The experiments on a 5.4-Ah lithium polymer battery are implemented to validate the feasibility of the algorithm. [ABSTRACT FROM AUTHOR]

Autonomous vehicles have been emerging over the past few years because of the sophisticated processing of data from different types of perception sensors, such as LiDAR, radar, and camera. Ground segmentation plays an important role in the sequence of data processing for environment perception tasks, as it can help to reduce the size of data to be processed and further decrease the overall computational time. However, the over-segmentation, under-segmentation, or slow-segmentation on non-flat surface usually occurs due to the characteristics of the 3D LIDAR data, such as occlusion in complex urban environment. To address these problems, in this paper, we proposed a probability occupancy grid-based approach for real-time ground segmentation by using a single LiDAR sensor. The effectiveness and robustness of our proposed method are evaluated and demonstrated by the real-time experiments that span different traffic scenarios from heavy traffic to light traffic. [ABSTRACT FROM AUTHOR]

Autonomous vehicles need a real-time traffic tracking system in order to interact with multiple moving vehicles in urban situations. Most existing works rely on camera sensors to interpret the surrounding environment. However, camera sensors degrade in conditions of lighting, shadows, and extreme weathers such that they can hardly detect objects. The light detection and ranging (LiDAR) sensors promise to be a good substitute, as they enable highly precise and robust localization across a wide range of conditions. This paper presents a new LiDAR-based online multiple maneuvering vehicle tracking problem and proposes a novel online multi-model smooth variable structure filter to address the problem. The real-time experiments show that our method is able to deliver superior performance compared to other conventional methods. [ABSTRACT FROM AUTHOR]

An important area of study for aerospace and electronic systems involves target tracking applications. To successfully track a target, state and parameter estimation strategies are used in conjunction with data association techniques. Even after 50 years, the Kalman filter (KF) remains the most popular and well-studied estimation strategy in the field. However, the KF adheres to a number of strict assumptions that leads to instabilities in some cases. The smooth variable structure filter (SVSF) is a relatively new method, which is becoming increasingly popular due to its robustness to disturbances and uncertainties. This paper presents a new formulation of the SVSF. The probabilistic and joint probabilistic data association techniques are combined with the SVSF and applied on multitarget tracking scenarios. In addition, a new covariance formulation of the SVSF is presented based on improving the estimation results of nonmeasured states. The results are compared and discussed with the popular KF method. [ABSTRACT FROM AUTHOR]

Autonomous self-drive requires intelligence and cognition that relies on observations and tracking of the state of motion of surrounding vehicles. This information can be acquired by using sensors; however, these are often affected by clutter and noise that, in turn, introduce the issues of estimation and data origin uncertainty into the tracking system. The most popular methods for estimation and tracking are based on the well-studied Kalman filter (KF). KF is optimal when noise is white and remains so despite uncertainties in the filter model; the robustness and stability of the KF is affected if this condition is not met. The smooth variable structure filter (SVSF) is a relatively new method that is more robust to disturbances and uncertainties. The SVSF ensures stability by using a discontinuous corrective term that maintains estimates to within a subspace of the true state trajectory. The discontinuous corrective term results in chattering that is removed by using a smoothing boundary layer. In this paper, a generalized covariance formulation of the SVSF and a generalized optimal time-varying smoothing boundary layer are proposed. The generalized optimal SVSF is then combined with a joint probabilistic data association technique for target tracking. The robustness and accuracy of the new form of filtering and data association is validated and comparatively analyzed by its application to an experimental traffic monitoring system based on Light Detection and Ranging. [ABSTRACT FROM PUBLISHER]

In this paper, an engine fault detection and classification technique using vibration data in the crank angle domain is presented. These data are used in conjunction with artificial neural networks (ANNs), which are applied to detect faults in a four-stroke gasoline engine built for experimentation. A comparative study is provided between the popular backpropagation (BP) method, the Levenberg–Marquardt (LM) method, the quasi-Newton (QN) method, the extended Kalman filter (EKF), and the smooth variable structure filter (SVSF). The SVSF is a relatively new estimation strategy, based on the sliding mode concept. It has been formulated to efficiently train ANNs and is consequently referred to as the SVSF-ANN. The accuracy of the proposed method is compared with the standard accuracy of the Kalman-based filters and the popular BP algorithms in an effort to validate the SVSF-ANN performance and application to engine fault detection and classification. The customizable fault diagnostic system is able to detect known engine faults with various degrees of severity, such as defective lash adjuster, piston chirp (PC), and chain tensioner (CT) problems. The technique can be used at any dealership or assembly plant to considerably reduce warranty costs for the company and manufacturer. [ABSTRACT FROM PUBLISHER]

The extended Kalman filter (EKF) and the unscented Kalman filter (UKF) are among the most popular estimation methods. The smooth variable structure filter (SVSF) is a relatively new sliding mode estimator. In an effort to use the accuracy of the EKF and the UKF and the robustness of the SVSF, the filters have been combined, resulting in two new estimation strategies, called the EK-SVSF and the UK-SVSF, respectively. The algorithms were validated by testing them on a well-known target tracking computer experiment. [ABSTRACT FROM AUTHOR]

The interacting multiple model (IMM) strategy is particularly useful for systems that behave according to a number of different operating modes. In this strategy, each operating mode is described by a model and has its own filter. The filters are run in parallel, and an overall operating mode probability is calculated that provides an indication of the current operating regime of the system. The smooth variable structure filter (SVSF) is a relatively new estimation method based on the sliding mode concept, formulated in a predictor-corrector form. For systems with modeling uncertainties, the SVSF has shown to be more accurate and robust when compared with other methods such as the extended Kalman filter (EKF). A newer form of the SVSF makes use of a time-varying smoothing boundary layer (SVSF-VBL). This paper introduces new model-based estimators; based on the IMM strategy combined with the SVSF and SVSF-VBL, referred to as the IMM-SVSF and IMM-SVSF-VBL, respectively. The new strategies are applied to a type of aerospace actuator referred to as an electrohydrostatic actuator, which provides a comprehensive system for fault detection and diagnosis. The results are compared with the popular IMM-EKF strategy. [ABSTRACT FROM PUBLISHER]

In this paper, a new method for state estimation, referred to as the smooth variable structure filter (SVSF), is presented. The SVSF method is model based and applies to smooth nonlinear dynamic systems. It allows for the explicit definition of the source of uncertainty and can guarantee stability given an upper bound for uncertainties and noise levels. The performance of the SVSF improves with more refined definition of upper bounds on parameter variations or uncertainties. Furthermore, most filtering methods provide as their measure of performance the filter innovation vector or (output) estimation error. However in addition to the innovation vector, the SVSF has a secondary set of performance indicators that correlate to the modeling errors specific to each state or parameter that is being estimated. The combined robustness and multiple indicators of performance allow for dynamic refinement of internal models in the SVSF. Dynamic refinement and robustness are features that are particularly advantageous in fault diagnosis and prediction. In this paper, the applications of the SVSF to linear and nonlinear systems, including one pertaining to fault detection, are provided. The characteristics of this filter in terms of its accuracy and rate of convergence are discussed. [ABSTRACT FROM AUTHOR]

The article presents a proposal for a neural network-based control system for fine control of the intake air/fuel ratio in a bi-fuel engine. The control system is a module for an existing vehicle manufacturer's electronic control units (ECUs). Effectiveness of the neural control system is demonstrated by a simulation of a Dodge four-stroke bi-fuel engine.