GCERT:面向无地图轨迹预测的智能体运动与交互关系学习方法
Intra-Agent Motion and Inter-Agent Relation Learning for Map-Free Trajectory Prediction
AI 导读
一篇 arXiv 论文提出无高精地图依赖的自动驾驶轨迹预测框架,核心是目标条件专家路由 Transformer(GCERT)。该方法用移动平均将历史运动特征分解为趋势与细节残差,并通过边级关系专家和节点级状态专家实现双层路由,预测目标再更新节点表示以引导交互建模。模型输出多模态未来轨迹,联合轨迹回归、模式分类和目标预测三类目标优化。
正文 · 原文
Abstract:Trajectory prediction is essential for safe planning and decision-making in autonomous driving. Map-free prediction improves deployment flexibility by removing the dependence on high-definition maps, but it also loses explicit road-topology and lane-connectivity priors. Consequently, the model must recover stable motion cues from short histories while resolving prospective interaction relations without lane-level guidance. To address these challenges, this paper proposes a map-free trajectory prediction framework centered on a novel Goal-Conditioned Expert-Routed Transformer (GCERT). A lightweight intra-agent front-end first decomposes projected historical motion features into a smooth trend and a local detail residual through a centered moving average. Component-specific residual projections transform the two signals before a causal temporal Transformer summarizes their recombined evolution. GCERT employs dual-level expert routing: edge-level relation experts generate interaction-specific messages, while node-level state experts adapt the transformation after message aggregation. Predicted motion goals update the node representations and construct prospective relative-geometry and orientation edge features before the final interaction layer, thereby conditioning attention, relation-specific message generation, and state transformation. GCERT therefore determines not only which neighboring agents should be attended to, but also what relation-specific information should be transmitted and how the aggregated node state should be transformed. The resulting representations are decoded into multimodal future trajectories and jointly optimized with trajectory-regression, mode-classification, and goal-prediction objectives.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2512.02368 [cs.CV] |
| (or arXiv:2512.02368v3 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2512.02368 arXiv-issued DOI via DataCite |
Submission history
From: Wenyi Xiong [view email]
[v1]
Tue, 2 Dec 2025 03:20:07 UTC (1,331 KB)
[v2]
Fri, 23 Jan 2026 04:59:15 UTC (3,371 KB)
[v3]
Tue, 17 Nov 2026 05:11:44 UTC (4,278 KB)
来源:arXiv cs.AI · arxiv.org