OnSite Decision-Making and Planning
Overview
Replay testing is a method based on naturalistic driving data. It reconstructs trajectories of surrounding road users, recreates real-world scenarios in a simulation environment, and tests an autonomous-driving decision, planning, and control algorithm in that replay environment. The purpose is to test autonomous-vehicle safety inextracted real-world scenarios. In this service, surrounding vehicles do not interact with the ego vehicle and follow predefined trajectories exactly. The configuration is relatively simple but the simulated scenarios retain high realism.
Leaderboard
| Contributor | Model | Safety | Efficiency | Comfort | Coordination | Comliance | Overall Score | Submission Time |
|---|---|---|---|---|---|---|---|---|
| 2350296_Liao Ziyang+2353031_Wu Guocheng | AdvancedPlanner | 10 | 99.545 | 10 | 10 | 9.85 | 99.6191 | 2026/6/10 16:45 |
| 2351940_Dong Xinwei+2352071_Wang Zihao | RLHybrid2 | 9.9978 | 99.2232 | 9.2133 | 10 | 9.9 | 97.1567 | 2026/6/10 10:18 |
| 2354338_Liu Chang | LearningHybrid | 9.973 | 93.0433 | 8.3861 | 10 | 9.95 | 91.4338 | 2026/6/11 19:24 |
| 2354295_Huang Weihang+2351222_Xu Yueyue | IFPT | 9.9467 | 90.8794 | 8.5248 | 10 | 9.9 | 90.2436 | 2026/6/4 11:37 |
| 2350296_Liao Ziyang+2353031_Wu Guocheng | AdvancedPlanner | 10 | 82.556 | 9.7636 | 10 | 9.85 | 89.9463 | 2026/6/10 5:34 |
| 2352661_Yu Jiewen | ActionReplay | 9.5849 | 83.2023 | 7.6482 | 10 | 9.9 | 81.9056 | 2026/6/14 21:37 |
| Wen Junlin | Myplanner | 9.356 | 85.3936 | 7.0731 | 10 | 9.9 | 81.1585 | 2026/5/22 21:11 |
| 2352666_Lu Xiangyu+2353035_Chen Shunyao | Lattice_pro | 9.5611 | 81.2037 | 8.0323 | 10 | 9.9 | 80.6327 | 2026/6/12 12:42 |
| 2354338_Liu Chang | LearningHybridPlanner | 9.8686 | 77.5089 | 8.2017 | 9.9 | 8.175 | 79.7932 | 2026/5/18 9:21 |
| 2254042_Wang Yejia | lattice | 9.0997 | 80.4946 | 7.4592 | 9.9029 | 8.1553 | 77.0717 | 2026/6/3 19:03 |
| 2351786_Hu Jiahe | HBPF-RP | 9.5758 | 71.2073 | 8.524 | 10 | 8.75 | 76.3018 | |
| 2350291_Xie Jiabin+2350878_Qin Zhilun | StructuredRoutePlanner | 8.8809 | 74.0554 | 7.2063 | 9.8 | 9.7 | 74.0009 | 2026/6/11 21:15 |
| 2351940_Dong Xinwei+2352071_Wang Zihao | RLHybrid | 8.079 | 74.4552 | 6.7524 | 8.1 | 8.05 | 73.2801 | 2026/6/4 1:49 |
| 2354295_Huang Weihang+2351222_Xu Yueyue | IFPT | 7.3803 | 66.9264 | 7.841 | 9.1 | 8.25 | 66.6762 | 2026/5/14 11:29 |
| Ding Shijian | SafetyIDM-v5 | 8.6651 | 58.6431 | 8.5595 | 9.6 | 9.5 | 65.2188 | 2026/5/31 23:27 |
| 2351180_Yu Zhenhua | rl_planner | 7.6699 | 59.5998 | 8.8348 | 10 | 9.9 | 65.2053 | 2026/6/4 21:46 |
| 2350291_Xie Jiabin+2350878_Qin Zhilun | StructuredRoutePlanner | 8.6748 | 59.7063 | 7.2638 | 9.3 | 9.2 | 64.5701 | 2026/6/4 10:15 |
| 2350282_Wei Deyi+2350597_Yang Zhaolong | MPC | 9.3698 | 46.3772 | 9.7259 | 10 | 8.725 | 62.9941 | 2026/6/11 23:22 |
| 2354217Jiang Zhihang | IDM | 6.5806 | 57.2926 | 7.7847 | 8.8 | 7.7 | 58.7826 | 2026/6/11 22:54 |
| 2354007_Zhang Shuo | IDM | 7.2635 | 46.6248 | 9.7704 | 10 | 9.9 | 58.6744 | 2026-06-18 02:03 |
| 2351938_Che Shuai | frenet_mpc | 6.4894 | 50.3392 | 9.9995 | 10 | 8.875 | 57.9958 | 2026/6/7 22:52 |
| Baseline Model | IDM | 7.1892 | 46.6371 | 9.7704 | 10 | 8.775 | 57.7899 | |
| 2354338_Liu Chang | LearningHybrid | 7.4815 | 52.5775 | 6.3696 | 7.5 | 6.55 | 56.7106 | 2026/5/12 17:44 |
| 2354344_Yang Yinuo+2354215_Zhang Lingkai | IDM | 7.224 | 47.1395 | 7.4634 | 8.9 | 8.275 | 53.5613 | 2026/6/11 23:36 |
| 2250509Tang Zhitong | 6.8701 | 47.3025 | 6.4874 | 7.9 | 7.025 | 50.6501 | 2026/06/16 04:08 | |
| Baseline Model | LATTIC | 6.1281 | 46.2896 | 7.2812 | 9.6 | 8.6 | 49.3529 |