Sort:
Open Access Review Article Issue
Progress and Development Trend of Space Backlight Detection Imaging Technology
Space: Science & Technology 2025, 5: 0197
Published: 05 August 2025
Abstract PDF (23 MB) Collect
Downloads:14

Based on the high-resolution detection and imaging requirements for space targets under future backlighting conditions, this paper reviews the development and application trends of space backlighting detection and imaging technology. First, it examines the potential detection tasks involving space debris and decommissioned spacecraft that on-orbit vehicles may face, analyzing the necessity of backlight detection imaging. Second, the characteristics of backlight scenes and backlight target imaging are discussed in detail, followed by an overview of the development trends in backlight detection imaging technology. Subsequently, based on the solar radiation propagation path, the imaging technology for dim targets under strong light backgrounds is summarized and categorized into stages. Finally, the paper concludes with a summary and outlook on space backlight detection technology, analyzing its potential applications in future space detection tasks. Through this comprehensive review and analysis, the paper aims to provide valuable insights and references for advancing space backlighting detection technology.

Open Access Research Article Issue
Deep MARL-Based Resilient Motion Planning for Decentralized Space Manipulator
Space: Science & Technology 2024, 4: 0145
Published: 27 August 2024
Abstract PDF (7.2 MB) Collect
Downloads:0

Space manipulators play an important role in the on-orbit services and planetary surface operation. In the extreme environment of space, space manipulators are susceptible to a variety of unknown disturbances. How to have a resilient guarantee in failure or disturbance is the core capability of its future development. Compared with traditional motion planning, learning-based motion planning has gradually become a hot spot in current research. However, no matter what kind of research ideas, the single robotic manipulator is studied as an independent agent, making it unable to provide sufficient flexibility under conditions such as external force disturbance, observation noise, and mechanical failure. Therefore, this paper puts forward the idea of “discretization of the traditional single manipulator”. Different discretization forms are given through the analysis of the multi-degree-of-freedom single-manipulator joint relationship, and a single-manipulator representation composed of multiple new subagents is obtained. Simultaneously, to verify the ability of the new multiagent representation to deal with interference, we adopted a centralized multiagent reinforcement learning framework. The influence of the number of agents and communication distances on learning-based planning results is analyzed in detail. In addition, by imposing joint locking failures on the manipulator and introducing observation and action interference, it is verified that the “multiagent robotic manipulator” obtained after discretization has stronger antidisturbance resilient capability than the traditional single manipulator.

Total 2