Lower extremity robotic exoskeletons (LEEX) can not only improve the ability of the human body but also provide healing treatment for people with lower extremity dysfunction. There are a wide range of application needs and development prospects in the military, industry, medical treatment, consumption and other fields, which has aroused widespread concern in society. This paper attempts to review LEEX technical development. First, the history of LEEX is briefly traced. Second, based on existing research, LEEX is classified according to auxiliary body parts, structural forms, functions and fields, and typical LEEX prototypes and products are introduced. Then, the latest key technologies are analyzed and summarized, and the research contents, such as bionic structure and driving characteristics, human–robot interaction (HRI) and intent-awareness, intelligent control strategy, and evaluation method of power-assisted walking efficiency, are described in detail. Finally, existing LEEX problems and challenges are analyzed, a future development trend is proposed, and a multidisciplinary development direction of the key technology is provided.

Stairs are common vertical traffic structures in buildings, and stair detection tasks are important in environmental perception for autonomous mobile robots. Most existing algorithms have difficulty combining the visual information from binocular sensors effectively and ensuring reliable detection at night and in the case of extremely fuzzy visual clues. To solve these problems, we propose a stair detection network with red-green-blue (RGB) and depth inputs. Specifically, we design a selective module, which can make the network learn the complementary relationship between the RGB feature maps and the depth feature maps and fuse the features effectively in different scenes. In addition, we propose several postprocessing algorithms, including a stair line clustering algorithm and a coordinate transformation algorithm, to obtain the stair geometric parameters. Experiments show that our method has better performance than existing the state-of-the-art deep learning method, and the accuracy, recall, and runtime are improved by 5.64%, 7.97%, and 3.81 ms, respectively. The improved indexes show the effectiveness of the multimodal inputs and the selective module. The estimation values of stair geometric parameters have root mean square errors within 15 mm when ascending stairs and 25 mm when descending stairs. Our method also has extremely fast detection speed, which can meet the requirements of most real-time applications.

No abstract