Mixing Data-driven and Geometric Models for Satellite Docking Port State Estimation using an RGB or Event Camera

TL;DR

This work presents a pipeline for automated satellite docking port detection and state estimation using monocular vision data from standard RGB sensing or an event camera, and presents a lightweight and data-efficient pipeline that can be used independently with either RGB or event cameras.

Abstract

In-orbit automated servicing is a promising path towards lowering the cost of satellite operations and reducing the amount of orbital debris. For this purpose, we present a pipeline for automated satellite docking port detection and state estimation using monocular vision data from standard RGB sensing or an event camera. Rather than taking snapshots of the environment, an event camera has independent pixels that asynchronously respond to light changes, offering advantages such as high dynamic range, low power consumption and latency, etc. This work focuses on satellite-agnostic operations (only a geometric knowledge of the actual port is required) using the recently released Lockheed Martin Mission Augmentation Port (LM-MAP) as the target. By leveraging shallow data-driven techniques to preprocess the incoming data to highlight the LM-MAP's reflective navigational aids and then using basic geometric models for state estimation, we present a lightweight and data-efficient pipeline that can be used independently with either RGB or event cameras. We demonstrate the soundness of the pipeline and perform a quantitative comparison of the two modalities based on data collected with a photometrically accurate test bench that includes a robotic arm to simulate the target satellite's uncontrolled motion.

Figures (8)

• Figure 1: The proposed method performs the detection and state estimation of the Lockheed Martin Mission Augmentation Port (LM-MAP) ((a) and (b)) using standard RGB images (c) or event-based data (d).
• Figure 2: Diagram overview of the proposed pipeline for satellite docking port detection and state estimation. The blue blocks are built upon data-driven techniques while the red block correspond to geometry-based algorithms.
• Figure 3: Illustration of the ring and reflector CNN-based filters. (a) shows a ring filtering example with event-based input ($N$ = 35k). (b) shows the reflector filtering with RGB data.
• Figure 4: Photometrically accurate low earth orbit bench for satellite docking.
• Figure 5: Example of images from the data collected with our satellite docking test bench and the Davis 346 RGB/event camera. (a) and (b) are from the augmented texture training set. (c) is from the realistic training set.