About

I am a Ph.D. student in Computer Application Technology at the University of Chinese Academy of Sciences, advised by Prof. Xue Wan. My training unit is the Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences.

My research focuses on embodied agents, multimodal perception, and simulation-to-real robot validation.

Education

2023.09 - Present — Ph.D., Computer Application Technology, University of Chinese Academy of Sciences; expected graduation: December 2026.
2020.09 - 2023.06 — M.S., Computer Application Technology, University of Chinese Academy of Sciences.
2016.09 - 2020.06 — B.E., Department of Automatic Control, Nanjing University of Aeronautics and Astronautics.

Internship Experience

Morphi Robot

May 2026 - August 2026 · Embodied Intelligence Intern

Designed and implemented tool-calling, intent-understanding, and task-management modules for an embodied-agent system.
Evaluated the agent in the Isaac Sim Behavior 1K environment, achieving a 75.3% task completion rate.
Built a household service scenario in Isaac Sim with 45 atomic actions and 37 scene objects, supporting 20-minute long-horizon task validation.
Converted the Python implementation to an edge-side C++ version on the real robot and conducted deployment tests.

Honors and Awards

2025.11 1st Place, UCAS Graduate Forum, Aerospace Session.
2025.10 2nd Place + Innovation Solution Award, IROS 2025 RoboSense Challenge (team leader).
2024.03 1st Place, CVPR 2024 SPARK Spacecraft Pose Estimation Challenge (team member).
2024.03 4th Place, CVPR 2024 SPARK Spacecraft Part Segmentation Challenge (team leader).
2023 Authorized invention patent on intelligent in-orbit exposure and focus control for space cameras.
2016-2020 National Encouragement Scholarship; GPA 4.0/5.0; 2nd Prize in Jiangsu Undergraduate Electronic Design Contest; 1st Prize in NUAA Electronic Design Contest.

Selected Work

IAA-SPAICE 2025 / Acta (accepted, SCI Q1)

SpaceMind: A Modular and Self-Evolving Embodied VLM Agent for Autonomous On-orbit Servicing

Aodi Wu, Haodong Han, Xubo Luo, Ruisuo Wang, Shan He, Xue Wan.

Paper Code Project Page YouTube Bilibili

Modular VLM-agent framework that decomposes skills, MCP tools, and reasoning into three independently extensible dimensions.
Three switchable reasoning modes (Standard / ReAct / Prospective) with skill self-evolution that turns failed episodes into reusable skills.
192 closed-loop runs across 5 satellites, 3 task types, 2 environments; the identical codebase transfers from UE5 simulation to a physical robot lab with 100% rendezvous success.

IROS 2026 (accepted, June 2026)

Aodi Wu, Jianhong Zuo, Zeyuan Zhao, Xubo Luo, Ruisuo Wang, Xue Wan.

Paper Code Project Page Dataset YouTube Bilibili

136 satellite models with around 70 GB of time-synchronized RGB (1024x1024), depth, and 256-beam LiDAR data built in Unreal Engine 5.
Dense 7-class part-level semantic labels at both pixel and point level, plus accurate 6-DoF pose ground truth.
Supports six tasks: 2D / 3D detection, 2D / 3D segmentation, depth estimation, 6-DoF pose, multi-modal fusion. HuggingFace downloads 2700+.

IROS 2025 / 2nd Place + Innovation Award

Enhancing Vision-Language Models for Autonomous Driving through Dynamic Routing and Spatial Reasoning

Aodi Wu, Xubo Luo. IROS 2025 RoboSense Challenge Technical Report.

Code Report

Dynamic routing module that dispatches each question to a task-specific expert prompt, eliminating cross-task interference.
Explicit multi-view coordinate grounding plus Chain-of-Thought / Tree-of-Thought reasoning to fix BACK-camera and left-right confusion.
70.87% on Phase-1 clean data and 72.85% on Phase-2 corrupted data with Qwen2.5-VL-72B; 2nd place overall and Innovation Solution Award.

CVPR 2024 / Pose 1st + Seg 4th

CVPR 2024 SPARK Challenge — Non-cooperative Spacecraft Perception

Spacecraft pose estimation and part segmentation on synthetic and real satellite imagery.

Paper Challenge Page

Pose estimation track — 1st place (team member).
Part segmentation track — 4th place (team leader).
Integrated multiple segmentation algorithms with depth estimation, and fused absolute and relative localization on the SPARK 2024 dataset.

Master's Thesis / In-orbit Verified

Led camera exposure/focus control, visual perception, and monocular navigation, from algorithm research to software-hardware integration and launch support.

ICDIP 2025 Project ICoSR 2022 Paper Patent CN 2023102948012

Cross-domain spacecraft component segmentation with edge-consistency generative networks, robust to synthetic-to-real domain gap.
Intelligent on-orbit exposure and focus control for space cameras, granted as an authorized invention patent (2023).
Monocular relative navigation for non-cooperative spacecraft over 200 m to 10 m, 5.16% mean error at 10 FPS on NVIDIA TX2, deployed on-orbit.