Vehicle Lateral Velocity Estimation Based on Long Short-Term Memory Network

Lateral velocity is an important parameter to characterize vehicle stability. The acquisition of lateral velocity is of great significance to vehicle stability control and the trajectory following control of autonomous vehicles. Aiming to resolve the problems of poor estimation accuracy caused by the insufficient modeling of traditional model-based methods and significant decline in performance in the case of a change in road friction coefficient, a deep learning method for lateral velocity estimation using an LSTM, long-term and short-term memory network, is designed. LSTM can well reflect the inertial characteristics of vehicles. The training data set contains sensor data under various working conditions and roads. The simulation results show that the prediction model has high accuracy in general and robustness to the change of road friction coefficient.

Machine Learning Enabled Traveltime Inversion Based on the Horizontal Source Location Perturbation

Gradient based traveltime tomography, which aims to minimize the difference between modeled and observed first arrival times, is a highly non-linear optimization problem. Stabilization of this inverse problem often requires employing regularization. While regularization helps avoid local minima solutions, it might cause low resolution tomograms because of its inherent smoothing property. On the other hand, although conventional ray-based tomography can be robust in terms of the uniqueness of the solution, it suffers from the limitations inherent in ray tracing, which limits its use in complex media. To mitigate the aforementioned drawbacks of gradient and ray-based tomography, we approach the problem in a completely novel way leveraging data-driven inversion techniques based on training deep convolutional neural networks (DCNN). Since DCNN often face challenges in detecting high level features from the relatively smooth traveltime data, we use this type of network to map horizontal changes in observed first arrival traveltimes caused by a source shift to lateral velocity variations. The relationship between them is explained by a linearized eikonal equation. Construction of the velocity models from this predicted lateral variation requires information from, for example, a vertical well-log in the area. This vertical profile is then used to build a tomogram from the output of the network. Both synthetic and field data results verify that the suggested approach estimates the velocity models reliably. Because of the limited depth penetration of first arrival traveltimes, the method is particularly favorable for near-surface applications.

A Variable-Sampling Time Model Predictive Control Algorithm for Improving Path-Tracking Performance of a Vehicle

This paper proposes a novel model predictive control (MPC) algorithm that increases the path tracking performance according to the control input. The proposed algorithm reduces the path tracking errors of MPC by updating the sampling time of the next step according to the control inputs (i.e., the lateral velocity and front steering angle) calculated in each step of the MPC algorithm. The scenarios of a mixture of straight and curved driving paths were constructed, and the optimal control input was calculated in each step. In the experiment, a scenario was created with the Automated Driving Toolbox of MATLAB, and the path-following performance characteristics and computation times of the existing and proposed MPC algorithms were verified and compared with simulations. The results prove that the proposed MPC algorithm has improved path-following performance compared to those of the existing MPC algorithm.

The role of premorbid transthoracic echocardiogram in identifying adverse clinical outcomes in patients admitted with COVID-19

Background/Introduction The novel coronavirus disease (COVID-19) inpatient mortality rate is approximately 20% in the United States. Reports have described a wide pattern of abnormalities in echocardiograms performed in patients admitted with COVID-19. The role of premorbid transthoracic echocardiogram (TTE) in the prediction of COVID-19 severity and mortality is yet to be fully assessed. Purpose To assess whether a pre-COVID TTE can identify patients at high risk of adverse outcomes who are admitted with COVID-19. Methods All patients who underwent a TTE from one year to one month prior to an index inpatient admission for COVID-19 were retrospectively enrolled across five clinical sites. Demographic information, medical history, and laboratory data were included for analysis. Echocardiograms were analyzed by an observer blinded to clinical data. Linear and logistic regressions were performed to detect the association of variables with death, invasive mechanical ventilation, initiation of dialysis, and a composite of these endpoints during the COVID-19 admission. Outcomes were then adjusted for a risk score using inverse propensity weighting incorporating age, sex, diabetes, hypertension, obstructive sleep apnea, history of atherosclerotic cardiovascular disease, atrial fibrillation, diuretic use, and angiotensin-converting enzyme inhibitor or angiotensin receptor blocker use. Results There were 104 patients (68±15 years old, 49% male, BMI 31.4±9.1kg/m2) who met inclusion criteria (baseline characteristics in Table 1). Mean time from TTE to positive SARS-CoV-2 PCR test was 139±91 days. Twenty-nine (28%) participants died during the index COVID-19 admission. There was no association of pre-COVID echocardiographic measures of systolic ventricular function with any endpoint. Diastolic function, as assessed by LV e', was associated with mortality (Table 2). There were 25 patients (24%) with a normal lateral e' (≥10cm/s); none died. There were 35 (34%) patients with LV e' lateral velocity <8 cm/s, of whom 15 (43%) died. LV e' lateral velocity <8 cm/s was associated with an unadjusted odds ratio of 7.69 (95% confidence interval [CI] 2.26–26.19) for death and 3.25 (95% CI 1.11–9.54) for the composite outcome. The odds ratio for death was 4.76 (95% CI 1.10–20.61) and 3.78 (95% CI 0.98–14.6) for the composite outcome after adjustment for clinical risk factors (Table 2). Conclusion In patients with an echocardiogram prior to COVID-19, impaired diastolic function as represented by an abnormal LV e' lateral velocity was associated with both inpatient COVID-19 mortality and a composite outcome of death, mechanical ventilation, and initiation of dialysis, even after adjustment for multiple co-morbidities and medication use. Knowledge of the pre-COVID TTE results may help clinicians identify patients at higher risk of adverse outcomes during an admission for COVID-19. FUNDunding Acknowledgement Type of funding sources: None.

Implementation of an Autonomous Overtaking System Based on Time to Lane Crossing Estimation and Model Predictive Control

According to statistics, the majority of accidents are attributed to driver negligence, especially when a driver intends to lane change or to overtake another vehicle, which is most likely to cause accidents. In addition, overtaking is one of the most difficult and complex functions for the development of autonomous driving technologies because of the dynamic and complicated task involved in the control strategy and electronic control systems, such as steering, throttle, and brake control. This paper proposes a safe overtaking maneuver procedure for an autonomous vehicle based on time to lane crossing (TLC) estimation and the model predictive control scheme. As overtaking is one of the most complex maneuvers that require both lane keeping and lane changing, a vision-based lane-detection system is used to estimate TLC to make a timely and accurate decision about whether to overtake or remain within the lane. Next, to maintain the minimal safe distance and to choose the best timing to overtake, the successive linearization-based model predictive control is employed to derive an optimal vehicle controller, such as throttle, brake, and steering angle control. Simultaneously, it can make certain that the longitudinal acceleration and steering velocity are maintained under constraints to maintain driving safety. Finally, the proposed system is validated by real-world experiments performed on a prototype electric golf cart and executed in real-time on the automotive embedded hardware with limited computational power. In addition, communication between the sensors and actuators as well as the vehicle control unit (VCU) are based on the controller area network (CAN) bus to realize vehicle control and data collection. The experiments demonstrate the ability of the proposed overtaking decision and control strategy to handle a variety of driving scenarios, including a lane-following function when a relative yaw angle exists and an overtaking function when the approaching vehicle has a different lateral velocity.

Field measurements of wake meandering at a utility-scale wind turbine with nacelle-mounted Doppler LiDARs

Wake meandering is a low-frequency oscillation of the entire wind turbine wake that can contribute to power and load fluctuations of downstream turbines in wind farms. Field measurements of two Doppler LiDARs mounted on the nacelle of a utility-scale wind turbine were used to investigate relationships between the inflow and the wake meandering as well as the effect of wake meandering on the temporally averaged wake. A correlation analysis showed a linear relationship between the instantaneous wake position and the lateral velocity that degraded with the evolution of the turbulent wind field during the time of downstream advection. A low-pass filter proportional to the advection time delay is recommended to remove small scales that become decorrelated even for distances within the typical spacing of wind turbine rows in a wind farm. The results also showed that the velocity at which wake meandering is transported downstream was slower than the inflow wind speed, but faster than the velocity at the wake center. This indicates that the modelling assumption of the wake as an passive scalar should be revised in the context of the downstream advection. Further, the strength of wake meandering increased linearly with the turbulence intensity of the lateral velocity and with the downstream distance. Wake meandering reduced the maximum velocity deficit of the temporally averaged wake and increased its width. Both effects scaled with the wake meandering strength. Lastly, we found that the fraction of the wake turbulence intensity that was caused by wake meandering decreased with downstream distance contrary to the wake meandering strength.

Driving Behavior at Signalized Intersections Operating under Disordered Traffic Conditions

A higher degree of heterogeneity in vehicle class and drivers, coupled with non-lane-based driving habits, creates several challenges in traffic flow analysis. This study investigates vehicles’ microscopic driving behavior at signalized intersections operating under weak lane discipline with mixed traffic (disordered) conditions. For this purpose, a comprehensive vehicular trajectory data set is developed from field-recorded video footage using a semi-automated tool for data extraction. Microscopic parameters such as relative velocity, spacing between vehicles, following time, lane preference, longitudinal and lateral speed profile, hysteresis evidence, and lateral movement of different vehicle classes during different traffic phases are presented in the study. The data is then segregated into three flow conditions: stopped flow, saturated flow, and unaffected flow. It is found that smaller vehicles prefer near-side lanes over far-side lanes. Motorized three-wheeler (3W) and motorized two-wheeler (2W) vehicle classes exhibit the greatest lateral velocity, lateral movement, and aggressiveness. This results in several interactions between vehicles as a function of different leader–follower vehicle pairs. Signalized intersections with more heterogeneity in traffic composition, especially higher composition of 2W and 3W vehicle classes, exhibit higher levels of aggressive driving behavior that might lower safety standards. As a practical application, ranges of various driving behavior parameter values for different leader–follower combinations and traffic conditions are quantified in the study. The observations and results are expected to help better understand prevailing driving behavior in disordered traffic and contribute toward robust calibration of microscopic traffic flow models for better replicating disordered traffic conditions at signalized intersections.

Coupled Lateral and Longitudinal Control for Trajectory Tracking, Lateral Stability, and Rollover Prevention of High-Speed Automated Vehicles Using Minimum-Time Model Predictive Control

Most controllers concerning lateral stability and rollover prevention for autonomous vehicles are designed separately and used simultaneously. However, roll motion influences lateral stability in cornering maneuvers, especially at high speed. Typical rollover prevention control stabilizes the vehicle with differential braking to create an understeering condition. Although this method can prevent rollover, it can also lead to deviation from a reference path specified for an autonomous vehicle. This contribution proposes and implements a coupled longitudinal and lateral controller for path tracking via model predictive control (MPC) to simultaneously enforce constraints on control input, state output, lateral stability, and rollover prevention. To demonstrate the approach in simulation, an 8 degrees of freedom (DOF) vehicle model is used as the MPC prediction model, and a high-fidelity 14-DOF model as the plant. The MPC-based lateral control generates a sequence of optimal steering angles, while a PID speed controller adjusts the driving or braking torque. The lateral stability envelope is determined by the phase plane of yaw rate and lateral velocity, while the roll angle threshold is derived from the load transfer ratio (LTR) and tire vertical force under the condition of quasi-steady-state rollover. To track the desired trajectory as fast as possible, a minimum-time velocity profile is determined using a forward-backward integration approach, subject to tire friction limit constraints. We demonstrate the approach in simulation, by having the vehicle track an arbitrary course of continuously varying curvature thus highlighting the accuracy of the controller and its ability to satisfy lateral and roll stability requirements. The MATLAB® code for the 8-DOF and 14-DOF vehicle models, along with the implementation of the proposed controller are available as open source in the public domain.

Feasibility study of fracture interpretation using multicomponent seismic data: SEAM II Barrett model

Several P-wave azimuthal anisotropy studies have been conducted for the SEAM II Barrett model data. However, these analyses provide fracture property estimation that is inconsistent with the actual model properties. Therefore, we perform a feasibility study to understand the influence of the overburden and reservoir properties, and the processing and inversion steps, which together determine the success of the fracture interpretation from seismic data. 1D model properties (orthorhombic for both overburden and reservoir) are first extracted from the actual Barrett model properties at two locations. Anisotropic prestack reflectivity modeling exposes the true orthorhombic response of the 1D medium in the form of Common Offset and Common Azimuth (COCA) gathers. The true anisotropic response is obscured in the Barrett data (generated by finite element modeling) due to the mild lateral velocity variations and orthorhombic anisotropy in the overburden. We then expose the reservoir anisotropic response by using an isotropic overburden in the reflectivity modeling. This shows that the P-wave VVAZ responses generated by the reservoir itself are weak, which leads to an unstable VVAZ inversion to estimate the interval NMO velocity anisotropy. The reservoir thickness (125m or 65ms TWT) or NMO velocity anisotropy (6-7%) needs to be at least doubled to obtain a stable VVAZ inversion. Anisotropic geometrical-spreading correction improves the amplitude-versus-azimuth (AVAZ) inversion results when reflectivity modeling models orthorhombic overburden. The converted wave ( C-wave) has a stronger VVAZ response compared to the P-wave. We suggest that the C-wave data could be useful to constrain fracture interpretation in the Barrett model. We conclude that the results of previous studies are due to the combination of the residual influence of overburden after processing and imaging, and the weak anisotropy responses from the reservoir.

Understanding the Lateral Dimension of Traffic: Measuring and Modeling Lane Discipline

There is growing interest in understanding the lateral dimension of traffic. This trend has been motivated by the detection of phenomena unexplained by traditional models and the emergence of new technologies. Previous attempts to address this dimension have focused on lane-changing and non-lane-based traffic. The literature on vehicles keeping their lanes has generally been limited to simple statistics on vehicle position while models assume vehicles stay perfectly centered. Previously the author developed a two-dimensional traffic model aiming to capture such behavior qualitatively. Still pending is a deeper, more accurate comprehension and modeling of the relationships between variables in both axes. The present paper is based on the Next Generation SIMulation (NGSIM) datasets. It was found that lateral position is highly dependent on the longitudinal position, a phenomenon consistent with data capture from multiple cameras. A methodology is proposed to alleviate this problem. It was also discovered that the standard deviation of lateral velocity grows with longitudinal velocity and that the average lateral position varies with longitudinal velocity by up to 8 cm, possibly reflecting greater caution in overtaking. Random walk models were proposed and calibrated to reproduce some of the characteristics measured. It was determined that drivers’ response is much more sensitive to the lateral velocity than to position. These results provide a basis for further advances in understanding the lateral dimension. It is hoped that such comprehension will facilitate the design of autonomous vehicle algorithms that are friendlier to both passengers and the occupants of surrounding vehicles.