W2W：基于语言模型与强化学习的轨迹预测
W2W: Language-Model-Based Trajectory Prediction with Reinforcement Learning
把行人轨迹与交互线索（同行/跟随/障碍）转成可解析文本提示，再用 T5-Small 两阶段训练（交叉熵监督微调 + 以 ADE 与越野惩罚为奖励的强化学习）做轨迹预测；对做视觉时序预测的人，这是一个可复用的「语言模型 + RL 奖励约束」范式，尤其适合把场景约束写进奖励函数而非损失函数。
原文依据 a reward function combining ADE error and off-road penalties strengthens scene constraints
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论行人轨迹预测对自动驾驶和社交机器人等应用至关重要。近期，基于语言模型（LM）的轨迹预测同时提供了预测精度与可解释性。然而，轨迹预测中常用的 L2 损失无法直接用于 LM 优化，导致预测性能下降。此外，当前基于 LM 的轨迹预测方法缺乏对社会交互的显式表达，其场景描述也过于简单，难以施加实际的场景约束。为解决这些问题，我们提出 Write-to-Walk（W2W）。首先，我们将观测到的轨迹与交互线索（同行/跟随/障碍）转换为可解析的文本提示，使交互语义在模型输入中得到更显式的表达。随后，以 T5-Small 为骨干网络进行两阶段训练：（1）使用交叉熵损失进行全参数监督微调以学习语言，实现格式化问答；（2）使用强化学习（RL）优化 W2W，其中结合 ADE 误差与越野惩罚的奖励函数强化了场景约束，产生与场景上下文一致的未来轨迹，并进一步提升预测精度。在基准数据集（ETH/UCY 与 SDD）上的实验表明，W2W 在 ADE/FDE 上与近期基于 LM 的预测方法及强轨迹预测基线保持竞争力。LM 的可解释性进一步支持 W2W 在自动驾驶等安全关键领域的部署。
英文原文摘要 1608 字符
Pedestrian trajectory prediction is crucial for applications such as autonomous driving and social robots. Recently, language model (LM)-based trajectory prediction has offered both prediction accuracy and interpretability. However, the L2 loss commonly used in trajectory prediction cannot be directly applied to LM optimization, resulting in degraded prediction performance. Moreover, current LM-based trajectory prediction methods lack explicit expressions of social interactions, and their scene descriptions are overly simplistic, making it challenging to impose practical scene constraints. To address these issues, we propose Write-to-Walk (W2W). First, we convert observed trajectories and interaction cues (companion/following/obstacle) into parsable textual prompts, so that interaction semantics are expressed more explicitly in the model input. Afterward, a T5-Small backbone is trained in a two-stage manner: (1) Full-parameter supervised fine-tuning with cross-entropy loss for language learning, enabling formatted question answering; (2) Reinforcement Learning (RL) to optimize W2W, where a reward function combining ADE error and off-road penalties strengthens scene constraints, producing future trajectories consistent with the scene context and further improving prediction accuracy. Experiments on benchmark datasets (ETH/UCY and SDD) demonstrate that W2W remains competitive with recent LM-based prediction methods and strong trajectory prediction baselines on ADE/FDE. The interpretability of LMs further supports W2W's deployment in safety-critical domains such as autonomous driving.