In recent years, III-V semiconductor nanowires have been widely investigated for infrared photodetector applications due to their direct and suitable bandgap, unique optical and electrical properties, flexibility in device design and to create heterostructures, and/or grow on a foreign substrate such as Si with more effective strain relaxation compared with planar structures. In particular, vertically aligned and ordered nanowire arrays have emerged as a promising photodetector platform, since their geometry-related light absorption and carrier transport properties can be tailored to achieve high photodetector performance and new functionalities. In this article, the state-of-the-art progress in the development of various types of infrared photodetectors based on III-V semiconductor nanowire arrays is reviewed. The nanowire synthesis/fabrication methods are introduced briefly at first, followed by discussions on the working principle and device performance of various types of nanowire array-based photodetectors and their emerging applications. Finally, we analyze the challenges and present the perspectives for the development of future low-cost, large-scale, high-performance nanowire array infrared photodetectors for practical applications.
Intelligent motion planning is one of the core components in automated vehicles, which has received extensive interests. Traditional motion planning methods suffer from several drawbacks in terms of optimality, efficiency and generalization capability. Sampling based methods cannot guarantee the optimality of the generated trajectories. Whereas the optimizationbased methods are not able to perform motion planning in real-time, and limited by the simplified formalization. In this work, we propose a learning-based approach to handle those shortcomings. Mixed Integer Quadratic Problem based optimization (MIQP) is used to generate the optimal lane-change trajectories which served as the training dataset for learningbased action generation algorithms. A hierarchical supervised learning model is devised to make the fast lane-change decision. Numerous experiments have been conducted to evaluate the optimality, efficiency, and generalization capability of the proposed approach. The experimental results indicate that the proposed model outperforms several commonly used motion planning baselines.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.