AutoTraces：基于多模态大语言模型的自回归轨迹预测
AutoTraces: Autoregressive Trajectory Forecasting via Multimodal Large Language Models
把连续物理坐标离散化为 token 接入 LLM 自回归解码，并用多模态 LLM 自动生成时空推理思维链，这套「坐标分词 + 自动 CoT」可迁移到人体轨迹预测、视觉导航等需要输出连续几何序列的视觉任务。
原文依据 a novel trajectory tokenization scheme, which represents physical waypoints as discrete tokens
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论本文提出 AutoTraces，一种面向人群环境中机器人轨迹预测的自回归视觉-语言-轨迹模型，利用大语言模型（LLM）固有的推理能力来建模复杂的人类行为。与以往仅依赖文本表示的工作不同，本文的核心创新在于一种新颖的轨迹分词方案，该方案将物理路点表示为离散 token，并通过轻量级编码器-解码器架构无缝集成到 LLM 的空间中。这一设计在保留 LLM 原生自回归生成机制的同时，将其扩展到物理坐标空间，便于对轨迹数据中的长期交互进行建模。本文进一步引入自动思维链（CoT）生成机制，利用多模态 LLM 从视觉观测和轨迹数据中推断时空关系，从而消除对手工标注的依赖。通过两阶段训练策略，AutoTraces 取得了当前最优的预测精度，尤其在长时程预测方面表现突出，同时展现出强大的跨场景泛化能力，并支持灵活长度的预测。
英文原文摘要 1203 字符
We present AutoTraces, an autoregressive vision-language-trajectory model for robot trajectory forecasting in humam-populated environments, which harnesses the inherent reasoning capabilities of large language models (LLMs) to model complex human behaviors. In contrast to prior works that rely solely on textual representations, our key innovation lies in a novel trajectory tokenization scheme, which represents physical waypoints as discrete tokens, seamlessly integrated into the LLM's space through a lightweight encoder-decoder architecture. This design preserves the LLM's native autoregressive generation mechanism while extending it to physical coordinate spaces, facilitates modeling of long-term interactions in trajectory data. We further introduce an automated chain-of-thought (CoT) generation mechanism that leverages a multimodal LLM to infer spatio-temporal relationships from visual observations and trajectory data, eliminating reliance on manual annotation. Through a two-stage training strategy, our AutoTraces achieves SOTA forecasting accuracy, particularly in long-horizon prediction, while exhibiting strong cross-scene generalization and supporting flexible-length forecasting.