The purpose of this study was to quantitatively assess the pupillary light reflex (PLR) in normal and anesthetized dogs using a pupillometer. Eleven dogs (20 eyes) of various breeds were included. PLRs were measured with a handheld pupillometer in dim light before and during anesthesia. Anesthesia was conducted with atropine, xylazine and ketamine. Parameters of pupillometry included neurological pupil index (NPi), pupil size, percent of change (%CH), latency (LAT), constriction velocity (CV), maximum constriction velocity (MCV) and dilation velocity (DV). NPi,%CH, CV and MCV were significantly decreased during anesthesia compared with the pre-anesthesia data. The results suggest that atropine-xylazine-ketamine combination anesthesia depresses the PLR. Additionally, this study demonstrates the feasibility of the use of a pupillometer in dogs.

No abstract

No abstract

Applying reinforcement learning algorithms to autonomous driving is difficult because of mismatches between the simulation in which the algorithm was trained and the real world. To address this problem, data from global navigation satellite systems and inertial navigation systems (GNSS/INS) were used to gather pseudolabels for semantic segmentation. A very simple dynamics model was used as a simulator, and dynamic parameters were obtained from the linear regression of manual driving records. Segmentation and a dynamic calibration method were found to be effective in easing the transition from a simulation to the real world. Pseudosegmentation labels are found to be more suitable for reinforcement learning models. We conducted tests on the efficacy of our proposed method, and a vehicle using the proposed system successfully drove on an unpaved track for approximately 1.8 km at an average speed of 26.57 km/h without incident.

A vast amount of labeled data is required for deep neural network training. A typical strategy to improve the performance of a neural network given a training data set is to use data augmentation technique. The goal of this work is to offer a novel image augmentation method for improving object detection accuracy. An object in an image is removed, and a similar object from the training data set is placed in its area. An in-painting algorithm fills the space that is eliminated but not filled by a similar object. Our technique shows at most 2.32 percent improvements on mAP in our testing on a military vehicle dataset using the YOLOv4 object detector.