Fabry-Perot etalon-based ultraviolet trifrequency high-spectral-resolution lidar for wind, temperature, and aerosol measurements from 0.2 to 35 km altitude.

A novel ultraviolet trifrequency high-spectral-resolution lidar (HSRL) based on a triple Fabry-Perot etalon (FPE) and polarization discrimination technique is proposed, to the best of our knowledge, for measuring atmospheric wind, temperature, and aerosol optical properties simultaneously from the troposphere to low stratosphere. The measurement principle of wind speed, temperature, and aerosol is analyzed, and the structure of the proposed HSRL is designed. The parameters of the triple FPE are optimized. The multiparameter inversion method based on the nonlinear iterative approach and cubic spline interpolation method is also discussed, and the specific iteration steps are given. Finally, the detection performance of the proposed HSRL is simulated. The simulation results show that for 0.3 WSr-1 m-2 nm-1 at 355 nm sky brightness, by using a 350 mJ pulse energy, a 50 Hz repetition frequency laser, and a 0.45 m aperture telescope, the measurement errors of temperature, aerosol backscattering ratio and vertical wind speed are below 2.1 K, 2.5×10-3, and 2.2 m/s in nighttime and below 3.2 K, 3.4×10-3, and 2.6 m/s in daytime from 0.2 to 35 km with a temporal resolution of 5 min for temperature and aerosol, 1 min for vertical wind, and a vertical resolution of 30 m at 0.2-10 km, 100 m at 10-20 km, 200 m at 20-35 km; the measurement error of two other orthogonal line-of-sight wind speeds with a fixed zenith angle of 30° is below 2.9 m/s in nighttime and 3.9 m/s in daytime in the range of ±50 m/s from 0.2 to 35 km with a temporal resolution of 1 min and a vertical resolution of 26 m at 0.2-8.6 km, 87 m at 8.6-17.3 km, and 173 m at 17.3-35 km. Compared with the traditional double-edge wind-detection technique with the same complete instrumental parameters including those of the FPEs and FPE-based high-spectral-resolution temperature-detection technique with the optimal parameter values of FPEs for the same laser power and telescope aperture, the wind accuracy of the proposed technique improved by 1.5 times at night and by 1.5-1.9 times during the day, and the temperature accuracy of the proposed technique improved by 2.2-2.6 times at night and by 1.7-2.6 times during the day.

Machine vision-based autonomous road hazard avoidance system for self-driving vehicles.

The resolution of traffic congestion and personal safety issues holds paramount importance for human's life. The ability of an autonomous driving system to navigate complex road conditions is crucial. Deep learning has greatly facilitated machine vision perception in autonomous driving. Aiming at the problem of small target detection in traditional YOLOv5s, this paper proposes an optimized target detection algorithm. The C3 module on the algorithm's backbone is upgraded to the CBAMC3 module, introducing a novel GELU activation function and EfficiCIoU loss function, which accelerate convergence on position loss lbox, confidence loss lobj, and classification loss lcls, enhance image learning capabilities and address the issue of inaccurate detection of small targets by improving the algorithm. Testing with a vehicle-mounted camera on a predefined route effectively identifies road vehicles and analyzes depth position information. The avoidance model, combined with Pure Pursuit and MPC control algorithms, exhibits more stable variations in vehicle speed, front-wheel steering angle, lateral acceleration, etc., compared to the non-optimized version. The robustness of the driving system's visual avoidance functionality is enhanced, further ameliorating congestion issues and ensuring personal safety.

Study on a risk model for prediction and avoidance of unmanned environmental hazard.

Comprehensive research is conducted on the design and control of the unmanned systems for electric vehicles. The environmental risk prediction and avoidance system is divided into the prediction part and the avoidance part. The prediction part is divided into environmental perception, environmental risk assessment, and risk prediction. In the avoidance part, according to the risk prediction results, a conservative driving strategy based on speed limit is adopted. Additionally, the core function is achieved through the target detection technology based on deep learning algorithm and the data conclusion based on deep learning method. Moreover, the location of bounding box is further optimized to improve the accuracy of SSD target detection method based on solving the problem of imbalanced sample categories. Software such as MATLAB and CarSim are applied in the system. Bleu-1 was 67.1, bleu-2 was 45.1, bleu-3 was 29.9 and bleu-4 was 21.1. Experiments were carried out on the database flickr30k by designing the algorithm. Bleu-1 was 72.3, bleu-2 was 51.8, bleu-3 was 37.1 and bleu-4 was 25.1. From the comparison results of the simulations of unmanned vehicles with or without a system, it can provide effective safety guarantee for unmanned driving.