Recent technological progress is opening up practical applications for quadruped robots. In this context, comprehensive performance demands, including speed, payload, robustness, terrain adaptability, endurance, and techno-economics, are increasing. However, design conflicts inevitably exist among these performance indicators, highlighting design challenges, especially for a heavy-duty, electrically actuated quadruped robots, which are strongly constrained by motor torque density and battery energy density. Starting from task-specific holistic system thinking, in this paper, we present a novel task-oriented approach to the design of such kind of robots, incorporating hierarchical optimization and a control-in-the-loop design, while following a structured design path that effectively exploits the strengths of both heuristic and computational designs. Guided by these philosophies, we utilize heuristic design to obtain the approximate initial form of the prototype and propose a key task-oriented actuator joint configuration, utilizing commercially available components. Subsequently, we build a step-wise analytical models considering trajectory optimization and motor heat constraints for optimization of leg length and joint match parameters to achieve a compact performance requirement envelope and minimize redundancy in the construction of task-specific components. Furthermore, we construct a holistic simulation platform with a module control algorithm for typical scenarios to evaluate subsystem results and adjust design parameters iteratively, balancing conflicts and eventually achieving a reliable design specification for detailed subsystem design. Based on these strategies, we develop a heavy-duty electric prototype achieving a maximum speed of 2 m/s in trotting gait with a load weighting over 160 kg and enduring a period of 2 h. The experiment upon the prototype verifies the efficiency of the proposed approach.
Remote sensing is an indispensable technical way for monitoring earth resources and environmental changes. However, optical remote sensing images often contain a large number of cloud, especially in tropical rain forest areas, make it difficult to obtain completely cloud-free remote sensing images. Therefore, accurate cloud detection is of great research value for optical remote sensing applications. In this paper, we propose a saliency model-oriented convolution neural network for cloud detection in remote sensing images. Firstly, we adopt Kernel Principal Component Analysis (KCPA) to unsupervised pre-training the network. Secondly, small labeled samples are used to fine-tune the network structure. And, remote sensing images are performed with super-pixel approach before cloud detection to eliminate the irrelevant backgrounds and non-clouds object. Thirdly, the image blocks are input into the trained convolutional neural network (CNN) for cloud detection. Meanwhile, the segmented image will be recovered. Fourth, we fuse the detected result with the saliency map of raw image to further improve the accuracy of detection result. Experiments show that the proposed method can accurately detect cloud. Compared to other state-of-the-art cloud detection method, the new method has better robustness.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.