NANYANG TECHNOLOGICAL UNIVERSITY · SINGAPORE南洋理工大学 · 新加坡
Liu Xu刘旭
M.Sc. student in Smart Manufacturing智能制造 · 硕士研究生
My research and engineering work includes SLAM localization integration, 3DGS-based scene reconstruction and object search, WAM-based mobile manipulation, and UAV hardware integration and flight testing.我的研究与工程工作涵盖 SLAM 定位联调、基于 3DGS 的场景重建与物体搜索、基于 WAM 的移动操作，以及无人机硬件集成与实飞验证。
Online 3DGS for object and contextual-anchor search在线 3DGS 中的物体与上下文锚点搜索
Research work研究工作
Online 3DGS and a past photo condition an eight-channel Restoration Field for object and anchor readout. Nav2 and Contact-GraspNet connect this spatial information to search, grasping and placement.在线 3DGS 与旧照片共同生成八通道恢复场，提供物体和原始锚点的空间信息；通过 Nav2 与 Contact-GraspNet 接入搜索、抓取和放置。
Design evidence设计依据
The original location is empty, so object appearance alone cannot identify it. Removing anchor affinity reduces simulated ordered localization from 34.8% to 8.4%.原位置已空置，物体外观不足以定位它；移除锚点关联后，仿真顺序定位成功率从 34.8% 降至 8.4%。
Evaluation验证范围
Simulated ordered localization: 34.8%, without grasping or placement. Real restoration: 5/10, requiring stable placement on the correct support with horizontal error <0.25 m; orientation is not evaluated.仿真顺序定位 34.8%（不含抓放）；实机复原 5/10：正确支撑面上稳定放置，水平误差 <0.25 m，朝向不作评估。
Simulation: ordered object-and-anchor localization, without grasping or placement, at source 8×. Real: grasping and anchor-return excerpts from independent trials, at source 4×. The panels show different stages and outcomes.仿真：物体与锚点的顺序定位，不含抓放，原片 8 倍速。实机：多个独立试验的抓取与返回锚点片段，原片 4 倍速；各画格阶段与结果不同。
Iterative World Action Model for precise scene restoration用于精细场景恢复的迭代世界动作模型
Research work研究工作
Current point clouds guide docking, then the visual goal conditions WAM. Two refinement rounds precede arm actions; the first 24 actions are executed before observing and replanning.先根据当前点云选择停靠位置，再以视觉目标驱动 WAM；两轮预测细化后生成机械臂动作，执行前 24 步并重新观测规划。
Design evidence设计依据
A reachable pose may be poor for restoration, so frozen-WAM outcomes supervise docking utility. Removing utility reduces mean simulation success across three training seeds from 71.1% to 47.3%.可达位姿未必有利于恢复，故以冻结 WAM 的恢复结果监督停靠效用；移除效用后，三训练种子的仿真平均成功率由 71.1% 降至 47.3%。
Evaluation验证范围
Real success: 19/30 at ≤30 mm. Final position error: 30.7 ± 12.7 mm, mean ± sample SD across all 30 trials, including failures.实机 19/30（≤30 mm）；全部 30 次含失败的位置误差 30.7 ± 12.7 mm（均值 ± 样本标准差）。
Simulation video wall: 4K, 60 fps, source 4×. Real bottle grasp through release: 0.5× the source footage, with motion smoothing for display; the source is labelled 2×. These are independent trials.仿真九宫格视频墙：4K、60 fps，原片 4 倍速。实机连续展示瓶子抓取至释放，经过运动平滑，以 0.5 倍原片速度播放；原片标注 2X。两段为独立试验。
Contributed to LIO/FAST-LIO debugging: scan-to-map matching, initial pose alignment and odometry anomaly investigation. Contributed to initial scan alignment using Manhattan-world features and IMU gravity to address initial alignment error and height drift, and to relocalization in the official coordinate frame.负责部分 LIO/FAST-LIO 定位调试：scan-to-map 匹配、初始位姿对齐与 odom 异常排查；参与结合 Manhattan 世界特征与 IMU 重力估计进行初始扫描对齐，以处理初始对齐误差和高度漂移，并参与官方坐标系中的重定位联调。
10 Hz → 100 HzContributed to increasing the LIO update frequency through debugging and integration.参与调试与集成，提升 LIO 更新频率。
ONBOARD INTEGRATION机载系统集成
UAV integration无人机硬件集成
Participated in selection and integration of Livox Mid-360 LiDAR, monocular cameras, Jetson Orin NX, flight controllers and airframes. Handled part of the mounting, wiring, power connections, interface configuration and troubleshooting for three UAVs.参与 Livox Mid-360、单目相机、Jetson Orin NX、飞控及机架的选型和集成，负责部分安装固定、接线与供电连接、接口配置、联调及故障排查，支持 3 架无人机飞行验证。
The integration spans sensor inputs, localization output, planner trajectories and the flight-controller interface. Simulation used ROS2 and Unity HiFi Simulator. The three-UAV deployment from December 2025 to May 2026 used ROS1 on Ubuntu 20.04; I contributed to localization debugging and onboard integration.集成涉及传感器输入、定位输出、规划轨迹与飞控接口。仿真阶段使用 ROS2 与 Unity HiFi Simulator；2025.12—2026.05 的三机实飞阶段使用 ROS1／Ubuntu 20.04，我参与定位联调和机载系统集成。
Team validation团队验证
<10 cmLocalization error in module tests模块测试定位误差
<10 cm @ 3 m/sTrajectory tracking error动态轨迹跟踪误差
3/3 · 72 sDemo Day · UAVs completedDemo Day · 完成无人机数
Basic Sequence / Alternate Sequence / Demo Day: 50 / 60 / 72 s, each with 3/3 UAVs completing the task. Overall real-world completion-speed rank: 2nd of 8 teams.Basic Sequence / Alternate Sequence / Demo Day 分别为 50 / 60 / 72 s，每项均为 3/3 架完成；实机验收整体完成速度排名 2/8。
Simulation contribution仿真阶段分工
From July to November 2025, I led EGO-Planner adaptation for local planning, obstacle avoidance and replanning in the ten-UAV simulation. I adjusted safety margins, velocity constraints, takeoff order and task flow for narrow gates, corners and inter-agent path conflicts, and integrated ROS2 interfaces for mission initialization, odometry, cameras, trajectories and results. The team completed 10/10 UAVs in 166 s, ranking 1st of 8 teams by completion speed.2025.07—2025.11，我负责十机仿真中的 EGO-Planner 局部规划、避障与重规划适配，针对窄门、转角和多机路径冲突调整安全距离、速度约束、起飞顺序与任务流程，并接入 ROS2 的任务初始化、里程计、相机、轨迹和结果接口。团队仿真验收 10/10 架完成，用时 166 s，完成速度排名 1/8。
03
What the experiments show实验说明了什么
In Spot the Difference's ten real trials, the main observed failure stage is locating the original position. For Copy-Paste, a third refinement adds only 0.2 percentage points of mean simulation success and increases planning-round latency on RTX 6000 Ada from 0.654 to 0.838 s.Spot the Difference 的十次实机试验中，主要失败环节是原始位置搜索。Copy-Paste 增加第三轮预测细化后，仿真平均成功率只提高 0.2 个百分点，而 RTX 6000 Ada 上的规划轮时延从 0.654 s 增至 0.838 s。
04
Background教育与经历
Education教育背景
2025.08 — Present至今
Nanyang Technological University南洋理工大学
M.Sc. in Smart Manufacturing · Singapore智能制造 · 硕士研究生 · 新加坡
Supported line maintenance and fault analysis; used Python and Excel to structure, classify and analyze maintenance records.参与航线维修及故障排查，使用 Python 与 Excel 结构化维修记录，分析异常类别和重复性故障。
2023.07 — 2023.08
Bofeike (Tianjin) Technology博菲克（天津）科技有限公司
Mechanical Engineer · R&D Department机械工程师 · 研发部
Worked on automotive fluid-pipeline component design, UGNX modeling and assembly checks, and ANSYS structural analysis.参与汽车流体管道部件设计，使用 UGNX 建模与装配检查，并基于 ANSYS 开展结构分析。
OTHER MANUSCRIPT / THIRD AUTHOR其他研究稿件 / 第三作者
Uncertainty-Aware Dynamics Learning via Offline Generative Prior Extraction and Online Bayesian Posterior Refinement
IEEE Transactions on Industrial Informatics · Regular Paper · Under review · April 2026Regular Paper · 审稿中 · 2026 年 4 月
