Monocular inspection of spacecraft under illumination constraints and avoidance regions
This paper presents an adaptive control approach to information-based guidance and control of a spacecraft carrying out on-orbit inspection by actively computing optimal policies for the spacecraft to achieve the best possible representation of objects within its orbital environment. Due to the complexity of navigating the space environment, it may be impossible to carry out on-orbit servicing to maintain space systems like satellites using a spacecraft equipped with controllers that cannot adapt to changing conditions. In particular, the presence of constraints such as illumination, field-of-view (FOV), minimal fuel, the use of visual-inertial navigation for improved localization, and the need for real-time computation of control policies render the spacecraft motion planning problem challenging. The control framework developed in this paper addresses these challenges by formulating the inspection task as a constrained optimization problem where the goal is to maximize information gained from the cameras, while navigating to the next best view, subject to illumination and FOV constraints. The developed architecture is analyzed using a Lyapunov-based stability analysis and the effectiveness of the planning algorithm is verified in simulation.
Code (0)
등록된 구현이 없습니다.
Tasks
Motion PlanningSimilar Papers 제목 키워드 기반
Initialization of Monocular Visual Navigation for Autonomous Agents Using Modified Structure from Small Motion
We propose a standalone monocular visual Simultaneous Localization and Mapping (vSLAM) initialization pipeline for autonomous space robots. Our method, a state-of-the-art factor graph optimization pipeline, extends Struc…
Motion EstimationSimultaneous Localization and MappingVisual NavigationPrecision-Aware Illumination-Disentangled Vision Transformer for Spacecraft 6D Pose Estimation
Vision sensors provide a lightweight solution for spacecraft proximity operations, but monocular spacecraft 6D pose estimation remains difficult under illumination variation, specular reflection, shadowing, weak texture,…
6D Pose EstimationGAP-GDRNet: Geometry-aware monocular 6D pose estimation for spacecraft using synthetic geometric supervision
Monocular spacecraft 6D pose estimation remains difficult under weak texture, thin structures, illumination variation, and occlusion. This article presents GAP-GDRNet, a geometry-aware RGB framework built on GDR-Net for …
6D Pose EstimationPose Estimation for Non-Cooperative Spacecraft Rendezvous Using Convolutional Neural Networks
On-board estimation of the pose of an uncooperative target spacecraft is an essential task for future on-orbit servicing and close-proximity formation flying missions. However, two issues hinder reliable on-board monocul…
BenchmarkingImage GenerationPose EstimationRun Time Assured Reinforcement Learning for Six Degree-of-Freedom Spacecraft Inspection
The trial and error approach of reinforcement learning (RL) results in high performance across many complex tasks, but it can also lead to unsafe behavior. Run time assurance (RTA) approaches can be used to assure safety…
Reinforcement Learning (RL)