[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-93147":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":9,"language":9,"languages":9,"totalLinesOfCode":9,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":13,"subscribersCount":13,"size":13,"stars1d":13,"stars7d":13,"stars30d":14,"stars90d":13,"forks30d":13,"starsTrendScore":13,"compositeScore":15,"rankGlobal":9,"rankLanguage":9,"license":9,"archived":16,"fork":16,"defaultBranch":17,"hasWiki":16,"hasPages":16,"topics":18,"createdAt":9,"pushedAt":9,"updatedAt":19,"readmeContent":20,"aiSummary":21,"trendingCount":13,"starSnapshotCount":13,"syncStatus":22,"lastSyncTime":23,"discoverSource":24},93147,"WheelRoute","Fuu1718121\u002FWheelRoute","Fuu1718121","Route-constrained robust localization for wheeled robots in GNSS-degraded environments.",null,155,12,7,0,13,41.64,false,"main",[],"2026-07-22 04:02:08","\u003Cdiv align=\"center\">\n\n# 🛰️ When GNSS Fails, WheelRoute Keeps Robots on Track\n\n### **WheelRoute: Route-Constrained Robust Localization for Wheeled Robots in GNSS-Degraded Environments**\n\n#### Official paper: Route-Constrained Robust Fusion Estimation for MEMS\u002FGNSS Integrated Navigation of Unmanned Ground Vehicles in GNSS-Degraded Environments\n\nJingzhi Cui\u003Csup>1\u003C\u002Fsup> · Chao Zhang\u003Csup>2\u003C\u002Fsup> · Yuliang Mao\u003Csup>2\u003C\u002Fsup> · Shaolin Lü\u003Csup>1\u003C\u002Fsup> · Dongmei Li\u003Csup>1\u003C\u002Fsup> · Huan Che\u003Csup>2\u003C\u002Fsup> · Rong Zhang\u003Csup>1\u003C\u002Fsup>\n\n\u003Csup>1\u003C\u002Fsup>Tsinghua University    \u003Csup>2\u003C\u002Fsup>Xiaomi Inc.\n\n\u003Cbr>\n\n[![arXiv](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FarXiv-2606.19687-b31b1b.svg)](https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.19687)\n[![ICRA](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FICRA-Robot%20Meets%20GNSS%20and%20Ranging%20for%20Seamless%20Autonomy-success.svg)](https:\u002F\u002Frobotmeetsranging.tech)\n[![Code](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FCode-release%20in%20progress-lightgrey.svg)](#release-roadmap)\n[![Localization](https:\u002F\u002Fimg.shields.io\u002Fbadge\u002FTask-Wheeled%20Robot%20Localization-purple.svg)](#-tldr)\n\n\u003Cbr>\n\n\u003Cimg src=\"assets\u002Fteaser.jpg\" width=\"92%\" alt=\"WheelRoute deviation comparison in GNSS-degraded tunnel scenarios\">\n\n\u003Cp>\u003Ci>GNSS drops in the tunnel. Dead reckoning drifts away. WheelRoute pulls the robot back to the route.\u003C\u002Fi>\u003C\u002Fp>\n\n\u003C\u002Fdiv>\n\n---\n\n## 📢 News\n\n- **[2026-06-19]** 🚀 Paper is now available on arXiv: [arXiv:2606.19687](https:\u002F\u002Farxiv.org\u002Fabs\u002F2606.19687).\n- **[2026-06-18]** 🛰️ arXiv submission completed.\n- **[2026-06-05]** 🎉 Paper accepted to the **1st Workshop on Robot Meets GNSS and Ranging for Seamless Autonomy**, IEEE ICRA 2026.\n- **[2026-06]** 🛠️ Code release is being cleaned for public use. See the roadmap below.\n\n---\n\n## 🌐 Community & Coverage\n\nWe appreciate independent discussions and community attention around this work. The links below are third-party materials and are not official implementations unless explicitly stated.\n\n- 🔁 **Independent reproduction** — a WeChat article reproduced and discussed the main WheelRoute pipeline and results. [Read here](https:\u002F\u002Fmp.weixin.qq.com\u002Fs\u002FZ5IOx1a6JCr1FFxWsePxVw)\n- 📝 **Technical review** — Moonlight published an AI-generated summary and review of the arXiv paper. [Read here](https:\u002F\u002Fwww.themoonlight.io\u002Fzh\u002Freview\u002Froute-constrained-robust-fusion-estimation-for-memsgnss-integrated-navigation-of-unmanned-ground-vehicles-in-gnss-degraded-environments)\n- 💬 **Social mention** — LinkedIn community post about the paper. [View post](https:\u002F\u002Fwww.linkedin.com\u002Fposts\u002Friawe_fwxroute-constrained-robust-fusion-estimation-activity-7474843923308478464-N8bC)\n\n---\n\n## 🎯 TL;DR\n\nA wheeled robot enters a tunnel, GNSS disappears, and MEMS\u002Fodometry dead reckoning starts drifting. **WheelRoute** keeps the robot localized by matching the recent dead-reckoning trajectory to route-level map geometry, turning the route into a pseudo-position measurement inside an EKF fusion framework.\n\nIt is designed for practical UGV navigation systems: **MEMS\u002FGNSS\u002Fodometry in, route-constrained robust localization out**.\n\n---\n\n## ✨ Highlights\n\n- 🛞 **Wheeled-robot degraded localization** — targets UGV localization under GNSS interruption, blockage, and degraded reception.\n- 🗺️ **Route-level map prior** — uses mission-route geometry as a lightweight constraint for drift suppression.\n- 🧭 **Trajectory-to-route matching** — aligns recent dead-reckoning history with local route segments through 2D rigid registration.\n- 🧩 **Map-as-measurement fusion** — converts route matching into EKF-compatible pseudo-position observations.\n- 🛡️ **Robust engineering design** — trigger control, matching validation, route offset compensation, and correction limiting.\n- 🚇 **Real-world tunnel validation** — long-tunnel, multi-segment tunnel, and curved-tunnel scenarios.\n\n---\n\n## 📅 Release Roadmap\n\n> Public release status. More details will be added as each component is ready.\n\n- [x] ICRA 2026 workshop acceptance\n- [x] arXiv submission completed\n- [x] arXiv identifier available\n- [ ] Project page and video demo\n- [ ] Reproducible code package\n- [ ] Dataset access instructions\n\n---\n\n## 🧭 Method\n\nThe pipeline turns route geometry into a usable localization measurement.\n\n\u003Cdiv align=\"center\">\n\u003Cimg src=\"assets\u002Fframework.jpg\" width=\"92%\" alt=\"WheelRoute route-constrained fusion framework\">\n\u003C\u002Fdiv>\n\n1. **Dead reckoning (DR)** — MEMS IMU and odometry propagate a short-term trajectory when GNSS is degraded.\n2. **Route registration** — the recent DR trajectory is aligned to local mission-route segments.\n3. **Pseudo-position observation** — the matched route-referenced position becomes a measurement.\n4. **Robust EKF fusion** — pseudo-position observations suppress accumulated drift while preserving continuity.\n\n\u003Cdiv align=\"center\">\n\u003Cimg src=\"assets\u002Fpipeline.jpg\" width=\"92%\" alt=\"Pseudo-position construction through trajectory-path matching\">\n\u003C\u002Fdiv>\n\n---\n\n## 📊 Results\n\nEvaluated on three real-vehicle tunnel scenarios under GNSS-degraded conditions. Position metrics are route-relative deviations in meters; heading metrics are in degrees.\n\n| Scenario | Method | Max Pos. Dev. | Mean Pos. Dev. | Pos. RMSE | Mean Heading Dev. | Heading RMSE |\n|---|---:|---:|---:|---:|---:|---:|\n| Long tunnel | Baseline | 386.3 | 142.909 | 186.821 | 2.073 | 3.524 |\n| Long tunnel | WheelRoute | **22.7** | **0.745** | **1.672** | **0.048** | **1.257** |\n| Curved tunnel | Baseline | 32.6 | 7.908 | 10.376 | -0.216 | **0.793** |\n| Curved tunnel | WheelRoute | **27.5** | **1.431** | **1.889** | **-0.179** | 0.946 |\n| Multi-segment tunnel | Baseline | 23.3 | 3.576 | 6.502 | **0.011** | 1.839 |\n| Multi-segment tunnel | WheelRoute | **8.5** | **1.755** | **2.351** | 0.018 | **1.332** |\n\n\u003Cdiv align=\"center\">\n\u003Cimg src=\"assets\u002Flong_tunnel_result.jpg\" width=\"56%\" alt=\"Long-tunnel trajectory comparison\">\n\u003C\u002Fdiv>\n\n---\n\n## 🚀 Getting Started\n\n> Code release in progress. The internal implementation has reproduced the tunnel experiments reported in the paper; the public interface and documentation are being cleaned.\n\n```bash\ngit clone https:\u002F\u002Fgithub.com\u002FFuu1718121\u002FWheelRoute.git\ncd WheelRoute\n```\n\nThe first public code release will include an example sequence interface, configuration files, and plotting scripts for reproducing the reported localization metrics.\n\n---\n\n## 📦 Dataset\n\nThe experiments cover three real-vehicle GNSS-degraded tunnel scenarios:\n\n- 🚇 Long tunnel\n- 🧱 Multi-segment tunnel\n- 🌀 Curved tunnel\n\nDataset release or access instructions will be added after cleanup.\n\n---\n\n## 📝 Citation\n\nIf you find this work useful, please consider citing:\n\n```bibtex\n@inproceedings{cui2026wheelroute,\n  title     = {Route-Constrained Robust Fusion Estimation for MEMS\u002FGNSS Integrated Navigation of Unmanned Ground Vehicles in GNSS-Degraded Environments},\n  author    = {Cui, Jingzhi and Zhang, Chao and Mao, Yuliang and L{\\\"u}, Shaolin and Li, Dongmei and Che, Huan and Zhang, Rong},\n  booktitle = {1st Workshop on Robot Meets GNSS and Ranging for Seamless Autonomy, IEEE ICRA},\n  address   = {Vienna, Austria},\n  date      = {2026-06-05},\n  year      = {2026},\n  eprint    = {2606.19687},\n  archivePrefix = {arXiv},\n  primaryClass  = {cs.RO}\n}\n```\n\n---\n\n## 🙏 Acknowledgements\n\nThis work was conducted by Tsinghua University and Xiaomi Inc. We thank the Robot Meets GNSS and Ranging workshop organizers for hosting the accepted paper at IEEE ICRA 2026.\n\n\u003Cdiv align=\"center\">\n\u003Csub>State Key Laboratory of Precision Space-time Information Sensing Technology, Tsinghua University\u003C\u002Fsub>\n\u003C\u002Fdiv>\n","WheelRoute 是一个面向轮式机器人在GNSS信号退化环境（如隧道、城市峡谷）中实现鲁棒定位的开源算法框架。其核心是将预定义行驶路线作为几何约束，融合MEMS惯性测量、轮式里程计与残余GNSS观测，在扩展卡尔曼滤波（EKF）框架内实现路由约束下的状态估计，显著抑制纯推算导致的漂移。项目强调工程实用性，适配低成本传感器组合，适用于无人地面车辆（UGV）、物流机器人、园区巡检机器人等依赖高精度路径跟踪的自主导航场景。",2,"2026-07-12 02:30:02","CREATED_QUERY"]