我们介绍了iMotion-LLM，一种集成了轨迹预测模块的大型语言模型（LLM），用于交互式运动生成。与传统方法不同，它基于文本指令生成可行且安全对齐的轨迹，使驾驶行为具有适应性和上下文感知能力。它结合了编码器-解码器多模态轨迹预测模型与通过LoRA微调的预训练LLM，将场景特征投影到LLM输入空间，并将特殊标记映射到轨迹解码器，以实现基于文本的交互和可解释的驾驶。为了支持这一框架，我们引入了两个数据集：1）InstructWaymo，是Waymo Open Motion Dataset的扩展，包含基于方向的运动指令；2）Open-Vocabulary InstructNuPlan，包含安全对齐的指令-描述词对及其对应的安全轨迹场景。我们的实验验证了指令条件化能够生成符合预期条件的轨迹。iMotion-LLM在上下文理解方面表现出色，方向可行性检测的平均准确率为84%，开放式词汇指令的安全评估平均准确率为96%。这项工作为自动驾驶中的文本引导运动生成奠定了基础，支持模拟数据生成、模型可解释性和轨迹生成模型的稳健安全对齐测试。我们的代码、预训练模型和数据集可在：https://vision-cair.github.io/iMotion-LLM/ 上获取。
英文摘要：
We introduce iMotion-LLM, a large language model (LLM) integrated with trajectory prediction modules for interactive motion generation. Unlike conventional approaches, it generates feasible, safety-aligned trajectories based on textual instructions, enabling adaptable and context-aware driving behavior. It combines an encoder-decoder multimodal trajectory prediction model with a pre-trained LLM fine-tuned using LoRA, projecting scene features into the LLM input space and mapping special tokens to a trajectory decoder for text-based interaction and interpretable driving. To support this framework, we introduce two datasets: 1) InstructWaymo, an extension of the Waymo Open Motion Dataset with direction-based motion instructions, and 2) Open-Vocabulary InstructNuPlan, which features safety-aligned instruction-caption pairs and corresponding safe trajectory scenarios. Our experiments validate that instruction conditioning enables trajectory generation that follows the intended condition. iMotion-LLM demonstrates strong contextual comprehension, achieving 84% average accuracy in direction feasibility detection and 96% average accuracy in safety evaluation of open-vocabulary instructions. This work lays the foundation for text-guided motion generation in autonomous driving, supporting simulated data generation, model interpretability, and robust safety alignment testing for trajectory generation models. Our code, pre-trained model, and datasets are available at: https://vision-cair.github.io/iMotion-LLM/.
Instruction-as-State: Environment-Guided and State-Conditioned Semantic Understanding for Embodied Navigation
National Key Laboratory of Human-Machine Hybrid Augmented Intelligence（人机混合增强智能国家重点实验室）；The Institute of Artificial Intelligence and Robotics（人工智能与机器人研究所）；School of Information Science and Technology（信息科学与技术学院）；Zhongguancun Academy（中关村学院）
Language-Conditioned World Modeling for Visual Navigation
University of Washington（华盛顿大学）；National University of Singapore（新加坡国立大学）；Clemson University（克莱姆森大学）；Drexel University（德雷塞尔大学）；Microsoft Research（微软研究院）
InstructSeq: Unifying Vision Tasks with Instruction-conditioned Multi-modal Sequence Generation
The Chinese University of Hong Kong（香港中文大学）；Fudan University（复旦大学）；Sensetime Research Institute（商汤研究院）；Tsinghua University（清华大学）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving
Laboratory for Intelligent & Safe Automobiles (LISA), University of California, San Diego（加州大学圣迭戈分校智能与安全汽车实验室（LISA））；Machine Intelligence, Interaction, and Imagination (Mi) Laboratory, University of California, Merced（加州大学默塞德分校机器智能、交互与想象实验室（Mi））
Action- and Language-Conditioned Video Assessment for Embodied Control
Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院）；School of Electrical Engineering, Korea Advanced Institute of Science and Technology (KAIST)（韩国科学技术院电气工程学院）
Before the Body Moves: Learning Anticipatory Joint Intent for Language-Conditioned Humanoid Control
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；LimX Dynamics Technology Co., Ltd.（LimX动态技术有限公司）；Shandong University（山东大学）；Data61/CSIRO；Griffith University（格里菲斯大学）；Institute of Deep Perception Technology, Jiangsu Industrial Technology Research Institute (JITRI)（深度感知技术研究院，江苏省工业技术研究院（JITRI））
Dynamic Cross-Modal Prompt Generation for Multimodal Continual Instruction Tuning
School of Artificial Intelligence, Nanjing University（南京大学人工智能学院）；State Key Laboratory for Novel Software Technology, Nanjing University（南京大学新型软件技术国家重点实验室）
