Perception is a vital part of driving. Every year, the loss in visibility due to snow, fog, and rain causes serious accidents worldwide. Therefore, it is important to be aware of the impact of weather conditions on perception performance while driving on highways and urban traffic in all weather conditions. The goal of this paper is to provide a survey of sensing technologies used to detect the surrounding environment and obstacles during driving maneuvers in different weather conditions. Firstly, some important historical milestones are presented. Secondly, the state-of-the-art automated driving applications (adaptive cruise control, pedestrian collision avoidance, etc.) are introduced with a focus on all-weather activity. Thirdly, the most involved sensor technologies (radar, lidar, ultrasonic, camera, and far-infrared) employed by automated driving applications are studied. Furthermore, the difference between the current and expected states of performance is determined by the use of spider charts. As a result, a fusion perspective is proposed that can fill gaps and increase the robustness of the perception system.

Three new lanthanide metal–organic frameworks IRHs-(1–3) supported by cyamelurate linkers have been synthesized and structurally characterized. The incorporation of numerous heteroatoms (N and O) into the pore walls and the relatively small microchannels of these porous solids enhance bonding force of the host–guest interactions, thus promoting the adsorption of carbon dioxide (CO2) over methane (CH4). The nonpolar covalent bonds in methane also favor the less uptake due to the hydrophilic walls of these frameworks. Grand canonical Monte Carlo simulations were performed to determine the origin of the adsorption. The density isocontour surfaces show that CO2 is mainly adsorbed on the walls composed of organic linkers and around the metal sites, whereas no specific adsorption site is observed for CH4, which indicates weak interactions between the framework and the adsorbed gas. As expected, the simulations show that CH4 is not observed around the metal center due to the presence of H2O molecules. The excellent selectivity of CO2/CH4 binary mixture was predicted by the ideal adsorbed solution theory (IAST) via correlating pure component adsorption isotherms with the Toth model. At 25 °C and 1 bar, the CO2 and CH4 uptakes for IRH-3 were 2.7 and 0.07 mol/kg, respectively, and the IAST predicated selectivity for CO2/CH4 (1:1) reached 27, which is among the best value for MOF materials.

No abstract

As an essential feature of autonomous road vehicles, obstacle detection must be executed on a real‐time onboard platform with high accuracy. Cameras are still the most commonly used sensors in autonomous driving. Most detections using cameras are based on convolutional neural networks. In this regard, a recent teacher–student approach, called transfer learning, has been used to improve the neural network training process. This approach has only been used with a neural network acting as a teacher to the best of our knowledge. This paper proposes a novel way of improving training data based on attention transfer by getting the attention map from a human. The proposed method allows the dataset size reduction by 50%, which leads to up to a 60% decline in the training time. The experimental results indicate that the proposed method can enhance the F1‐score of the network by up to 10% in winter conditions.

No abstract