Research on Lane a Compensation Method Based on Multi-Sensor Fusion.

The curvature of the lane output by the vision sensor caused by shadows, changes in lighting and line breaking jumps over in a period of time, which leads to serious problems for unmanned driving control. It is particularly important to predict or compensate the real lane in real-time during sensor jumps. This paper presents a lane compensation method based on multi-sensor fusion of global positioning system (GPS), inertial measurement unit (IMU) and vision sensors. In order to compensate the lane, the cubic polynomial function of the longitudinal distance is selected as the lane model. In this method, a Kalman filter is used to estimate vehicle velocity and yaw angle by GPS and IMU measurements, and a vehicle kinematics model is established to describe vehicle motion. It uses the geometric relationship between vehicle and relative lane motion at the current moment to solve the coefficient of the lane polynomial at the next moment. The simulation and vehicle test results show that the prediction information can compensate for the failure of the vision sensor, and has good real-time, robustness and accuracy.

Hierarchical Lateral Control Scheme for Autonomous Vehicle with Uneven Time Delays Induced by Vision Sensors.

Vision-based sensors are widely used in lateral control of autonomous vehicles, but the large computational cost of the visual algorithms often induces uneven time delays. In this paper, a hierarchical vision-based lateral control scheme is proposed, where the upper controller is designed by robust H∞-based linear quadratic regulator (LQR) algorithm to compensate sensor-induced delays, and the lower controller is based on logic threshold method, in order to achieve strong convergence of the steering angle. Firstly, the vehicle lateral model is built, and the nonlinear uncertainties induced by time delays are linearized with Taylor expansion. Secondly, the state space of the system is augmented to describe such uncertainties with polytopic inclusions, which is controlled by an H∞-based LQR controller with a low cost of online computation. Then, a lower controller is designed for the control of the steering motor. According to the results of the vehicle experiment as well as the hardware-in-the-loop (HIL) experiment, the proposed control scheme shows good performance in vehicle's lateral control task, and exhibits better robustness compared with a conventional LQR controller. The proposed control scheme provides a feasible solution for the lateral control of autonomous driving.

Identification of miRNAs Involved in the Protective Effect of Sevoflurane Preconditioning Against Hypoxic Injury in PC12 Cells.

The mechanism of sevoflurane preconditioning-induced neuroprotection is poorly understood. This study was aimed at identifying microRNAs (miRNAs) involved in the protective effect of sevoflurane preconditioning against hypoxic injury using the miRCURYTM LNA Array. The screened differentially expressed miRNAs were further validated using qRT-PCR. Finally, after transfection of miRNA (miR-101a or miR-34b) mimics or inhibitor, MTT and flow cytometry assays were used to evaluate cell survival and apoptosis in sevoflurane preconditioning. qRT-PCR confirmed the changes in expression of differentially expressed miRNAs that were screened by the microarray: down-regulation of rno-miR-101a, rno-miR-106b, and rno-miR-294 and up-regulation of rno-miR-883, rno-miR-16, and rno-miR-34b. MiR-101a and miR-34b were the most differentially expressed miRNAs. Sevoflurane preconditioning-inhibited apoptosis and preconditioning-enhanced cell viability of PC12 cells were significantly attenuated by transfection of miR-101a mimetic or miR-34b inhibitors, but were significantly enhanced by transfection of miR-34b mimetic. Therefore, a number of miRNAs, including miR-101a and miR-34b, might play important roles in the neuroprotection induced by sevoflurane preconditioning. Such miRNAs might provide novel targets for preventive and therapeutic strategies against cerebral ischemia-reperfusion injury.

Simulated effects of head movement on contact pressures between headforms and N95 filtering facepiece respirators-part 1: headform model and validation.

In a respirator fit test, a subject is required to perform a series of exercises that include moving the head up and down and rotating the head left and right. These head movements could affect respirator sealing properties during the fit test and consequently affect fit factors. In a model-based system, it is desirable to have similar capability to predict newly designed respirators. In our previous work, finite element modeling (FEM)-based contact simulation between a headform and a filtering facepiece respirator was carried out. However, the headform was assumed to be static or fixed. This paper presents the first part of a series study on the effect of headform movement on contact pressures-a new headform with the capability to move down (flexion), up (extension), and rotate left and right-and validation. The newly developed headforms were validated for movement by comparing the simulated cervical vertebrae rotation angles with experimental results from the literature.

Simulated effects of head movement on contact pressures between headforms and N95 filtering facepiece respirators part 2: simulation.

Finite element (FE) filtering facepiece respirators (FFRs) were developed and mated to the new headforms with a cervical spine model. The FFRs from three manufacturers included three sizing systems: (i) a single one-size-fits all, (ii) an FFR with two sizes (S/M and M/L), and (iii) an FFR with three sizes (S, L/M, XL). Finite element method (FEM) simulations of 16 headform and respirator combinations (5 headforms and 6 respirators) were used to examine maximum contact pressure changes for five cases: static head, flexion, extension, left rotation, and right rotation. For each of the 16 headform and respirator combinations, maximum contact pressures of the static headform and motile headforms were compared using t-tests. Significant differences on the maximum contact pressures were found in the extension, left rotation and right rotation at the nose (P < 0.005), the left rotation at the top of right cheek (P = 0.03), and the extension at the bottom of left/right cheek (P = 0.01). When separately considering each headform and each FFR manufacturer, the effects of the four head movement cases on the nose maximum contact pressure changes were observed in the simulations with all five headforms and all FFR manufacturers. The effects of the left and right rotations on the chin maximum contact pressure changes were observed in the simulations with the small headform. It was also found that the use of a nose clip could reduce the impact of the head left/right rotations on nose maximum contact pressure changes. In addition, head movements changed pressure contours of the key nose area. Caused by the head movements, the maximum contact pressure changes may affect seal quality, and the increase of the maximum contact pressures could reduce the facial comfort level.

Robust Multiobjective Reinforcement Learning Considering Environmental Uncertainties.

Numerous real-world decision or control problems involve multiple conflicting objectives whose relative importance (preference) is required to be weighed in different scenarios. While Pareto optimality is desired, environmental uncertainties (e.g., environmental changes or observational noises) may mislead the agent into performing suboptimal policies. In this article, we present a novel multiobjective optimization paradigm, robust multiobjective reinforcement learning (RMORL) considering environmental uncertainties, to train a single model that can approximate robust Pareto-optimal policies across the entire preference space. To enhance policy robustness against environmental changes, an environmental disturbance is modeled as an adversarial agent across the entire preference space via incorporating a zero-sum game into a multiobjective Markov decision process (MOMDP). Additionally, we devise an adversarial defense technique against observational perturbations, which ensures that policy variations, perturbed by adversarial attacks on state observations, remain within bounds under any specified preferences. The proposed technique is assessed in five multiobjective environments with continuous action spaces, showcasing its effectiveness through comparisons with competitive baselines, which encompass classical and state-of-the-art schemes.

Effects of Siraitia grosvenorii Fruits Extracts on Physical Fatigue in Mice.

In this study, the effects of Siraitia grosvenorii fruits extracts (SGFE) on physical fatigue were investigated. One hundred and forty-four mice were randomly divided into four groups: control group, low-dose SGE-treated group, middle-dose SGE-treated group and high-dose SGFE-treated group. The animals of control group received an oral administration of physiological saline in a volume of 2.5 mL, and the animals of treated group received the same volume of SGFE (100, 200 and 400 mg/Kg bodyweight, once a day) for 28 days. After 28 days, anti-fatigue effects of SGFE were assessed 10 h after the last treatment by forced swimming test and some biochemical parameters related to fatigue, including blood lactic acid, serum urea nitrogen, liver glycogen and muscle glycogen were measured. The data showed that SGFE can extend the swimming time of the mice, as well as increasing the liver and muscle glycogen contents, but decrease the blood lactic acid and serum urea nitrogen levels. These results indicated that Siraitia grosvenorii fruits extracts had significant anti-fatigue effects on mice and these effects were dose-dependent.