research-article Open AccessThe Survey of Image Generation from EEG Signals based on Deep Learning Share on Authors: Delong Yang Shenzhen Institute of Advanced Technology Chinese Academy of Sciences? Shenzhen, China, China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences? Shenzhen, China, ChinaSearch about this author , Dongnan Su Shenzhen Institute of Advanced Technology Chinese Academy of Sciences? Shenzhen, China, China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences? Shenzhen, China, ChinaSearch about this author , Zhaohui Luo Shenzhen Institute of Advanced Technology Chinese Academy of Sciences? Shenzhen, China, China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences? Shenzhen, China, ChinaSearch about this author , Peng Shang Shenzhen Institute of Advanced Technology Chinese Academy of Sciences? Shenzhen, China, China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences? Shenzhen, China, ChinaSearch about this author , Zhigang Hu Henan University of Science and Technology, Luoyang, China, China Henan University of Science and Technology, Luoyang, China, ChinaSearch about this author Authors Info & Claims BECB 2021: 2021 International Symposium on Biomedical Engineering and Computational BiologyAugust 2021 Article No.: 7Pages 1–5https://doi.org/10.1145/3502060.3502151Online:14 February 2022Publication History 0citation0DownloadsMetricsTotal Citations0Total Downloads0Last 12 Months0Last 6 weeks0 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteView all FormatsPDF
In this paper, a novel policy network update approach based on Proximal Policy Optimization (PPO), Advantageous Update Policy Proximal Policy Optimization (AUP-PPO), is proposed to alleviate the problem of over-fitting caused by the use of shared layers for policy and value functions. Extended from the previous sample-efficient reinforcement learning method PPO that uses separate networks to learn policy and value functions to make them decouple optimization, AUP-PPO uses the value function to calculate the advantage and updates the policy with the loss between the current and target advantage function as a penalty term instead of the value function. Evaluated by multiple benchmark control tasks in Open-AI gym, AUP-PPO exhibits better generalization to the environment and achieves faster convergence and better robustness compared with the original PPO.
Autonomous following is one of the critical issues in assistance walking robotics. In particular, it is a promising solution to help elders in everyday life. In this paper, we propose a method that combines large-scale piezoresistive films, wireless communication techniques, intelligent assistance walking robots and pressure image recognition to identify, track and follow the target person in dynamic environments. First, pressure image data acquisition devices are developed to obtain the object pressure distribution by measuring the voltage changes caused by the applied pressure on the piezoresistive films. Subsequently, host computer is developed to receive the pressure distribution image data from the designed signal acquisition devices through the serial port, and a statistical-based pressure distribution image recognition method is proposed to distinguish between robot and target person and to obtain the positions of robot and target person. Eventually, the host computer sends a command to assistance the walking robotics control system by wireless communication devices to achieve dynamic track and follow the target person. To validate the performance of the proposed method, a series of person following experiments are carried out. The experimental results show that the proposed algorithm effectively follows the target person.
Assistance robots are popular implemented in many industrial automatic manufactures. In particular, instead of carrying heavy object by hand, workers utilize industrial assistance robots to deal with non-easy handling stuff. Robots can also assist in completing tasks well when the goods need to be sent to a production workshop. Usually robots need to follow people to reach the destination. In this process, a robust adaptive following is necessarily used. Many previous researches were focused on vision-tracking following approaches or line tracking method for designing autonomous following. However, vision-tracking following is limited by light environment and line tracking method is only used in specific route. This paper proposed a novel following method combined UWB Sensors (Ultra-Wideband Sensors) and high-precision gyroscope to track and follow the target. When sensitivity of UWB Sensors declines because of the complex dynamic environment, high-precision gyroscope helps robot to identify the target and continue to follow it. The experimental results show that the combination of a variety of sensors and advanced algorithms could effectively deal with the problem caused by few sensors following method and achieve robust adaptive following in dynamic environment.
Stroke is a significant cause of disability worldwide, and stroke survivors often experience severe motor impairments. Lower limb rehabilitation exoskeleton robots provide support and balance for stroke survivors and assist them in performing rehabilitation training tasks, which can effectively improve their quality of life during the later stages of stroke recovery. Lower limb rehabilitation exoskeleton robots have become a hot topic in rehabilitation therapy research. This review introduces traditional rehabilitation assessment methods, explores the possibility of lower limb exoskeleton robots combining sensors and electrophysiological signals to assess stroke survivors' rehabilitation objectively, summarizes standard human-robot coupling models of lower limb rehabilitation exoskeleton robots in recent years, and critically introduces adaptive control models based on motion intent recognition for lower limb exoskeleton robots. This provides new design ideas for the future combination of lower limb rehabilitation exoskeleton robots with rehabilitation assessment, motion assistance, rehabilitation treatment, and adaptive control, making the rehabilitation assessment process more objective and addressing the shortage of rehabilitation therapists to some extent. Finally, the article discusses the current limitations of adaptive control of lower limb rehabilitation exoskeleton robots for stroke survivors and proposes new research directions.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
