传统机器人社会行为生成在灵活性和自主性上受限，依赖预定义动作或人类反馈。本文提出CRISP（Critique-and-Replan for Interactive Social Presence），一个自主框架，通过基于视觉语言模型的`人类-like社会批评者`评估并重新规划机器人自身行为。CRISP整合了从机器人描述文件中提取可移动关节和约束、基于情境生成分步行为计划、参考视觉信息生成低级关节控制代码、基于VLM评估社会适当性和自然性，包括定位错误步骤，以及通过奖励搜索迭代优化行为。该方法不依赖特定机器人API，仅使用机器人结构文件即可在不同平台上生成微妙不同的、人类般的动作。在涉及五种不同机器人类型和20种场景的用户研究中，包括移动机械臂和人形机器人，所提出的方法在偏好和情境适当性评分上显著高于先前方法。本研究提出了一种通用框架，最小化人类干预，同时扩展了机器人自主交互能力和跨平台适用性。
英文摘要：
Conventional robot social behavior generation has been limited in flexibility and autonomy, relying on predefined motions or human feedback. This study proposes CRISP (Critique-and-Replan for Interactive Social Presence), an autonomous framework where a robot critiques and replans its own actions by leveraging a Vision-Language Model (VLM) as a `human-like social critic.' CRISP integrates (1) extraction of movable joints and constraints by analyzing the robot's description file (e.g., MJCF), (2) generation of step-by-step behavior plans based on situational context, (3) generation of low-level joint control code by referencing visual information (joint range-of-motion visualizations), (4) VLM-based evaluation of social appropriateness and naturalness, including pinpointing erroneous steps, and (5) iterative refinement of behaviors through reward-based search. This approach is not tied to a specific robot API; it can generate subtly different, human-like motions on various platforms using only the robot's structure file. In a user study involving five different robot types and 20 scenarios, including mobile manipulators and humanoids, our proposed method achieved significantly higher preference and situational appropriateness ratings compared to previous methods. This research presents a general framework that minimizes human intervention while expanding the robot's autonomous interaction capabilities and cross-platform applicability.
Detailed result videos and supplementary information regarding this work are available at: https://limjiyu99.github.io/inner-critic/
AINav: Large Language Model-Based Adaptive Interactive Navigation
School of Advanced Manufacturing and Robotics, Peking University（北京大学先进制造与机器人学院）；AI Institute, School of Computer Science, Shanghai Jiao Tong University（上海交通大学计算机学院人工智能研究所）
VLM-SAFE: Vision-Language Model-Guided Safety-Aware Reinforcement Learning with World Models for Autonomous Driving
Lyles School of Civil and Construction Engineering, Purdue University（普渡大学莱尔斯土木与建筑工程学院）；Department of Civil and Environmental Engineering, University of Wisconsin-Madison（威斯康星大学麦迪逊分校土木与环境工程系）；Google（谷歌）
VLM-E2E: Enhancing End-to-End Autonomous Driving with Multimodal Driver Attention Fusion
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Li Auto Inc.（Li汽车公司）；the School of Aeronautics and Astronautics, Xiamen University（厦门大学航空航天学院）；The Hong Kong University of Science and Technology（香港科技大学）
GeoWorld-VLM: Geometry from World Models for Vision-Language Models
Harvard AI and Robotics Lab（哈佛人工智能与机器人实验室）；Kempner Institute for the Study of Natural and Artificial Intelligence（凯普纳自然与人工智能研究 institute）；Harvard University（哈佛大学）
LLM-Based Generalizable Hierarchical Task Planning and Execution for Heterogeneous Robot Teams with Event-Driven Replanning
Department of Mechanical Engineering, IIT Gandhinagar（印度加尔各直辖区理工学院机械工程系）；Sahyadri College of Engineering and Management（萨哈亚德里工程与管理学院）；Vishwakarma Institute of Information Technology（维什瓦克arma信息技术学院）
Self-Evolutionary Replanning for Failure-Aware Motion Planning
Department of Computer and Information Science, University of Macau（澳门大学计算机与信息科学系）；SIAT, Chinese Academy of Sciences（中国科学院上海技术物理研究所）；Department of Computer Science, University of Hong Kong（香港大学计算机科学系）；Academy for Engineering & Technology, Fudan University（复旦大学工程与技术学院）；Department of EEE, Southern University of Science and Technology（南方科技大学电子工程系）
How Do VLMs Behave When Blind or Misled? Behavioral Evaluation of VLMs on Scientific Figures
University of Aberdeen（阿伯丁大学）；International Institute of Information Technology Hyderabad（海德拉巴国际信息技术学院）；University of Technology Nuremberg（纽伦堡工业大学）；University of Southern California（南加利福尼亚大学）
RLSS: Real-time Multi-Robot Trajectory Replanning using Linear Spatial Separations
University of Southern California（南加州大学）；California Institute of Technology（加州理工学院）
轨迹重规划是多机器人团队在动态环境中导航的关键问题。本文提出了一种基于线性空间分离的重新规划算法RLSS（Replanning using Linear Spatial Separations）：一种实时的【形】轨迹重新规划算法，该算法利用线性空间分离来保证多机器人团队的安全性。我们的算法明确地处理机器人的动态限制，是完全分布式的，并且对环境变化，机器人故障和轨迹跟踪错误具有鲁棒性。它不需要机器人之间的通信，而是只依赖于本地的相对测量。我们证明了该算法在实时的【形】仿真和实验中使用物理机器人。我们比较我们的算法的一个国家的最先进的在线轨迹生成算法的基础上模型预测控制，并表明，我们的算法的结果显着减少碰撞在高度约束的环境中，并有效地避免了死锁。
VLCP: Vision Language Control Policy Closed-Loop Code Replanning for Robot Manipulation
University of Monastir（莫纳斯提尔大学）；St. Mildred’s-Lightbourn School（圣米尔德雷德-莱特本学校）；Cornell University（康奈尔大学）；Carnegie Mellon University（卡内基梅隆大学）；Silverstream AI（银流人工智能公司）；Mila -- Quebec AI Institute（米拉-魁北克人工智能研究所）
Critic in the Loop: A Tri-System VLA Framework for Robust Long-Horizon Manipulation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；the School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
Using VLM Reasoning to Constrain Task and Motion Planning
Department of Computer Science, Purdue University（普渡大学计算机科学系）；Department of Computer Science, Rice University（莱斯大学计算机科学系）；Ken Kennedy Institute, Rice University（莱斯大学肯尼迪研究所）
A Human-in-the-loop Approach to Robot Action Replanning through LLM Common-Sense Reasoning
Human-Robot Interfaces and Interaction (HRII) Laboratory, Istituto Italiano di Tecnologia（人机交互（HRII）实验室，意大利技术研究院）；Dept. of Informatics, Bioengineering, Robotics, and Systems Engineering, University of Genoa（信息学、生物工程、机器人学和系统工程系，热那亚大学）
AdaptPNP: Integrating Prehensile and Non-Prehensile Skills for Adaptive Robotic Manipulation
School of Computing, National University of Singapore（新加坡国立大学计算机学院）；RoboScience（机器人科学）；East China Normal University（华东师范大学）；Peking University（北京大学）；Nanjing University（南京大学）
