SHIRT v1

Abstract

This repository contains the Satellite Hardware-In-the-loop Rendezvous Trajectory (SHIRT) dataset which consists of two rendezvous trajectory scenarios (ROE1 and ROE2) in Low Earth Orbit (LEO) created from two different image sources. One is the OpenGL-based computer graphics renderer to create the synthetic images, and the other is the TRON facility at the Space Rendezvous Laboratory (SLAB) of Stanford University which illuminates a satellite mockup model with the Earth albedo light boxes to create the lightbox images. In ROE1, the servicer maintains the along-track separation typical of a standard v-bar hold point while the target spins about one principal axis, whereas in ROE2, the servicer slowly approaches the target tumbling about two principal axes. The sequential images of the SHIRT dataset can be used to evaluate the robustness of machine learning models and vision-based navigation filters over time across domain gap.

---

주요 개념

Servicer	카메라 달린 내 위성
Target	추적 대상 위성
Pose	위치(x,y,z) + 자세(quaternion)
Trajectory	시간에 따라 변하는 pose

---

domain

synthetic	깨끗한 렌더링
lightbox	실제 촬영 (노이즈 있음)

---

roe2.json

{
  "filename": "...",
  "q_vbs2tango_true": [...],
  "r_Vo2To_vbs_true": [...]
}

q_vbs2tango_true	target 자세 (quaternion)
r_Vo2To_vbs_true	target 위치 (x,y,z)

---

quaternion
[qw, qx, qy, qz]

---

matadata.json

pSim

cam_step	프레임 간 시간 간격 = 5
num_images	전체 프레임 수 = 2371

pMdl (servicer 기준)

카메라 위치	r_pri2cam_pri	위성 중심 → 카메라 위치
카메라 방향	q_pri2cam	위성 기준 → 카메라 방향

[1,0,0,0] → 회전 없음 (같은 방향)

---

좌표계

spri / vps	내 위성 중심 기준
cam	카메라 기준
tpri	target 기준

*SHIRTv1은 spri -> target이므로, cam -> target으로 변환 필요.

---

metadata.md

q_A2B refers to a quaternion representing a rotation aligning the frame A with the frame B.

• q_spri2tpri = spri → tpri
• q_pri2cam = pri → cam

r_A2B_C refers to a position vector from point A to B expressed in reference frame C.

• rv_scom2tcom_spri[:3] = servicer com → target com, expressed in spri
• r_pri2cam_pri = servicer com → camera origin, expressed in pri