While it is well known that rain may influence the performance of automotive LIDAR sensors commonly used in ADAS applications, there is a lack of quantitative analysis of this effect. In particular, there is very little published work on physically-based simulation of the influence of rain on terrestrial LIDAR performance. Additionally, there have been few quantitative studies on how rain-rate influences ADAS performance. In this work, we develop a mathematical model for the performance degradation of LIDAR as a function of rain-rate and incorporate this model into a simulation of an obstacle-detection system to show how it can be used to quantitatively predict the influence of rain on ADAS that use LIDAR.

Machine learning techniques have accelerated the development of autonomous navigation algorithms in recent years, especially algorithms for on-road autonomous navigation. However, off-road navigation in unstructured environments continues to challenge autonomous ground vehicles. Many off-road navigation systems rely on LIDAR to sense and classify the environment, but LIDAR sensors often fail to distinguish navigable vegetation from non-navigable solid obstacles. While other areas of autonomy have benefited from the use of simulation, there has not been a real-time LIDAR simulator that accounted for LIDAR–vegetation interaction. In this work, we outline the development of a real-time, physics-based LIDAR simulator for densely vegetated environments that can be used in the development of LIDAR processing algorithms for off-road autonomous navigation. We present a multi-step qualitative validation of the simulator, which includes the development of an improved statistical model for the range distribution of LIDAR returns in grass. As a demonstration of the simulator’s capability, we show an example of the simulator being used to evaluate autonomous navigation through vegetation. The results demonstrate the potential for using the simulation in the development and testing of algorithms for autonomous off-road navigation.

An experiment to search for the $\alpha$ decay of ${}^{112}$Cs has been performed at the Holifield Radioactive Ion Beam Facility (HRIBF) at Oak Ridge National Laboratory. The $\alpha$ decay of ${}^{112}$Cs was not observed, thus setting the upper limit of the $\alpha$ branching ratio at 0.26$\%$. The half-life of ${}^{112}$Cs was measured as $506\pm 55\mu$s. In the same measurement the decay properties of its proton decay daughter ${}^{111}$Xe were also reinvestigated. The newly measured $\alpha$ branching ratio for ${}^{111}$Xe is $10.4\pm 1.9\%$. The experimental proton separation energies $S_p$ for odd-$Z$ nuclei above ${}^{100}$Sn were compared to shell model calculations. The calculated proton separation energies for ${}^{103}$Sb and ${}^{102}$Sb point to half-lives of the order of 10 ps and 1 ns, respectively.

The transportation system is moving towards higher levels of autonomy. Longitudinal speed control, or adaptive cruise control (ACC), is intended to provide driver assistance by controlling vehicle speed and maintaining a safe distance from the preceding vehicle. Artificial intelligence (AI) and machine learning (ML) paved the way for robust navigation and decision-making in complex environments. In this paper, we propose a comprehensive framework for speed control using a deep reinforcement learning algorithm for safety and comfort. We incorporate the deep deterministic policy gradient (DDPG) framework with an attention mechanism for this. Many works achieved smooth vehicle control output from the DDPG algorithm with different network structures, but we demonstrate that adding an attention mechanism improves the overall performance. The baseline DDPG framework is based on fully connected layers. However, when we bring the attention mechanism to the DDPG model, it helps to increase focus on the most important features and enhances the overall model effectiveness. We also designed a custom reward function as our priority is to improve overall safety and comfort. The efficacy of our model is evaluated in comparison to the baseline DDPG model, emphasizing the influence of the attention mechanism. We have performed an ablation study to determine the impact of the number of layers and neurons in the hidden layer. In addition, we tested this model on diverse datasets (simulated and real), including some unknown scenarios in the testing datasets. We demonstrate that our architecture has outperformed the state-of-the-art model, and is quite robust across different datasets.

Negative obstacles have long been a challenging aspect of autonomous navigation for ground vehicles. However, as terrestrial lidar sensors have become lighter and less costly, they have increasingly been deployed on small, low-flying UAV, affording an opportunity to use these sensors to aid in autonomous navigation. In this work, we develop an analytical model for predicting the ability of UAV or UGV mounted lidar sensors to detect negative obstacles. This analytical model improves upon past work in this area because it takes the sensor rotation rate and vehicle speed into account, as well as being valid for both large and small view angles. This analytical model is used to predict the influence of velocity on detection range for a negative obstacle and determine a limiting speed when accounting for vehicle stopping distance. Finally, the analytical model is validated with a physics-based simulator in realistic terrain. The results indicate that the analytical model is valid for altitudes above 10 m and show that there are drastic improvements in negative obstacle detection when using a UAV-mounted lidar. It is shown that negative obstacle detection ranges for various UAV-mounted lidar are 60–110 m, depending on the speed of the UAV and the type of lidar used. In contrast, detection ranges for UGV mounted lidar are found to be less than 10 m.

Machine-learning (ML) requires human-labeled “truth” data to train and test. Acquiring and labeling this data can often be the most time-consuming and expensive part of developing trained models of convolutional neural networks (CNN). In this work, we show that an automated workflow using automatically labeled synthetic data can be used to drastically reduce the time and effort required to train a machine learning algorithm for detecting buildings in aerial imagery acquired with low-flying unmanned aerial vehicles. The MSU Autonomous Vehicle Simulator (MAVS) was used in this work, and the process for integrating MAVS into an automated workflow is presented in this work, along with results for building detection with real and simulated images.