The burgeoning fields of robot learning and embodied AI have triggered an increasing demand for large quantities of data. However, collecting sufficient unbiased data from the target domain remains a challenge due to costly data collection processes and stringent safety requirements. Consequently, researchers often resort to data from easily accessible source domains, such as simulation and laboratory environments, for cost-effective data acquisition and rapid model iteration. Nevertheless, the environments and embodiments of these source domains can be quite different from their target domain counterparts, underscoring the need for effective cross-domain policy transfer approaches. In this paper, we conduct a systematic review of existing cross-domain policy transfer methods. Through a nuanced categorization of domain gaps, we encapsulate the overarching insights and design considerations of each problem setting. We also provide a high-level discussion about the key methodologies used in cross-domain policy transfer problems. Lastly, we summarize the open challenges that lie beyond the capabilities of current paradigms and discuss potential future directions in this field.
Do Vision-Language-Action Models Mean What They Say? On the Role of Faithfulness in Embodied Reasoning
Stanford University（斯坦福大学）；Politecnico di Milano（米兰理工大学）；KTH Royal Institute of Technology（皇家理工学院）；Italian Institute of Artificial Intelligence (AI4I)（意大利人工智能研究所）；NVIDIA Research（英伟达研究院）
Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Sun Yat-sen University（中山大学）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东大数据分析与处理重点实验室）；Peng Cheng Laboratory（鹏城实验室）；Institute of Digital Media, Peking University（北京大学数字媒体研究院）
PMTRM: Pseudo-Memory Temporal Re-encoding Module for Embodied Policy Learning
Zhejiang University（浙江大学）；The Hong Kong University of Science and Technology（香港科技大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；vivo Robotics Lab（vivo机器人实验室）；South China Normal University（华南师范大学）
University of Padova（帕多瓦大学）；Fondazione Bruno Kessler (FBK)（布鲁诺·凯斯勒基金会（FBK））；Simon Fraser University（西蒙弗雷泽大学）
Learning how to navigate among humans in an occluded and spatially constrained indoor environment, is a key ability required to embodied agent to be integrated into our society. In this paper, we propose an end-to-end architecture that exploits Proximity-Aware Tasks (referred as to Risk and Proximity Compass) to inject into a reinforcement learning navigation policy the ability to infer common-sense social behaviors. To this end, our tasks exploit the notion of immediate and future dangers of collision. Furthermore, we propose an evaluation protocol specifically designed for the Social Navigat…
EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems
School of Software, Harbin Institute of Technology（哈尔滨工业大学软件学院）；School of Computer Science and Technology, Harbin Institute of Technology（哈尔滨工业大学计算机科学与技术学院）；School of Mathematical and Computer Sciences, Heriot-Watt University, Malaysia Campus（赫瑞-瓦特大学马来西亚校区数学与计算机科学学院）；School of Future Science and Engineering, Soochow University（苏州大学未来科学与工程学院）
Bridging VLMs and Embodied Intelligence with Deliberate Practice Policy Optimization
X-Humanoid；Imperial College London（帝国理工学院）；Peking University（北京大学）；University of Manchester（曼彻斯特大学）；Westlake University（西湖大学）；Fudan University（复旦大学）；Waseda University（早稻田大学）；Nvidia；Queen Mary University of London（伦敦大学玛丽女王学院）；Celonis AI；Meta AI
Renmin University of China（中国人民大学）；Samsung Research China Beijing（三星中国研究院（北京））
People always desire an embodied agent that can perform a task by understanding language instruction. Moreover, they also want to monitor and expect agents to understand commands the way they expected. But, how to build such an embodied agent is still unclear. Recently, people can explore this problem with the Vision-and-Language Interaction benchmark ALFRED, which requires an agent to perform complicated daily household tasks following natural language instructions in unseen scenes. In this paper, we propose LEBP -- Language Expectation and Binding Policy Module to tackle the ALFRED. The LEBP…
Embodied AI: Emerging Risks and Opportunities for Policy Action
Centre for the Governance of AI（治理人工智能中心）；French Center for AI Safety (CeSIA)（法国人工智能安全中心）；Carnegie Mellon University（卡内基梅隆大学）；University of Oxford（牛津大学）；University of Bologna（博洛尼亚大学）；Tony Blair Institute for Global Change（托尼·布莱尔全球变革研究所）；Yale University（耶鲁大学）；Yale Digital Ethics Center（耶鲁数字伦理中心）
MIT（麻省理工学院）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）
Self-supervised representation learning has achieved remarkable success in recent years. By subverting the need for supervised labels, such approaches are able to utilize the numerous unlabeled images that exist on the Internet and in photographic datasets. Yet to build truly intelligent agents, we must construct representation learning algorithms that can learn not only from datasets but also learn from environments. An agent in a natural environment will not typically be fed curated data. Instead, it must explore its environment to acquire the data it will learn from. We propose a framework,…
Towards Deploying VLA without Fine-Tuning: Plug-and-Play Inference-Time VLA Policy Steering via Embodied Evolutionary Diffusion
Collaborative and Versatile Robots (CLOVER) Laboratory, T-Stone Robotics Institute, The Chinese University of Hong Kong, Hong Kong（协作与多功能机器人实验室，T-Stone机器人研究所，香港中文大学，香港）；Φ \Phi -Institute for Physical Human Intelligence（物理人机智能研究所）；Center for Embodied Artificial Intelligence and Computer Vision, Shenzhen Loop Area Institute, Shenzhen, China（具身人工智能与计算机视觉中心，深圳环园研究院，深圳，中国）；Department of Advanced Robotics, Istituto Italiano di Tecnologia, Genoa, Italy（先进机器人系，意大利理工学院，热那亚，意大利）
GenRL: Multimodal-foundation world models for generalization in embodied agents
IDLab, Ghent University（IDLab，根特大学）；VERSES AI Research Lab（VERSES AI研究实验室）；Mila, University of Montreal（米拉研究所，蒙特利尔大学）；ServiceNow Research（ServiceNow研究院）
EmbodiedSkills: World Action Model-augmented Cascaded Skills for Vision-Language-Action Agent
College of Computer Science and Technology, Zhejiang University（浙江大学计算机科学与技术学院）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Cornell University（康奈尔大学）；Universal Ubiquitous AI Co., Ltd.（Universal Ubiquitous AI有限公司）；Hangzhou DEEP Robotics Technology Co., Ltd.（杭州深度机器人科技有限公司）；National University of Singapore（新加坡国立大学）
Safe Embodied AI for Long-horizon Tasks: A Cross-layer Analysis of Robotic Manipulation
UNIST InnoCORE AI-Space Solar Initiative（UNIST创新核心人工智能空间太阳能计划）；Ulsan National Institute of Science and Technology (UNIST)（乌山国立科学技术研究院）；Automation and Systems Research Institute（自动化与系统研究所）；Department of Electrical and Computer Engineering（电气与计算机工程系）；Interdisciplinary Program in Artificial Intelligence（人工智能跨学科项目）；LG Electronics（LG电子）
Empowering Embodied Visual Tracking with Visual Foundation Models and Offline RL
Peking University（北京大学）；National University of Singapore（新加坡国立大学）；City University of Macau（澳门城市大学）；State Key Laboratory of General Artificial Intelligence（通用人工智能国家重点实验室）；BIGAI（北京智源人工智能研究院）；Beihang University（北京航空航天大学）
Wow, wo, val! A Comprehensive Embodied World Model Evaluation Turing Test
State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机学院，北京大学）；Beijing Innovation Center of Humanoid Robotics（人形机器人创新中心）；The Hong Kong University of Science and Technology（香港科技大学）
The EmbodiedQA is a task of training an embodied agent by intelligently navigating in a simulated environment and gathering visual information to answer questions. Existing approaches fail to explicitly model the mental imagery function of the agent, while the mental imagery is crucial to embodied cognition, and has a close relation to many high-level meta-skills such as generalization and interpretation. In this paper, we propose a novel Mental Imagery eNhanceD (MIND) module for the embodied agent, as well as a relevant deep reinforcement framework for training. The MIND module can not only m…
PACT: Self-Evolving Physical Safety Alignment for Diffusion Policies in Embodied Manipulation
Dept. of Comp. Sci. and Tech., Institute for AI, Tsinghua-Bosch Joint ML Center, THBI Lab, BNRist Center, Tsinghua University, Beijing, 100084, China（计算机科学与技术系，人工智能研究院，清华-博世联合机器学习中心，THBI实验室，BNRist中心，清华大学，北京，100084，中国）；Peng Cheng Laboratory, 518108, China（鹏城实验室，518108，中国）
LAPT-Scale: Scaling Embodied Policies with Latent Action Pre-Training on Human Videos
Joy Future Academy, JD（京东探索研究院）；School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen（哈尔滨工业大学（深圳）计算机科学与技术学院）；Tsinghua SIGS, Tsinghua University（清华大学深圳国际研究生院）；Artificial Intelligence, The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州）人工智能学院）
Max Planck Institute for Mathematics in the Sciences（马克斯·普朗克数学科学研究所）；Faculty of Mathematics and Computer Science, Leipzig University（莱比锡大学数学与计算机科学学院）；Santa Fe Institute（圣塔菲研究所）
Reinforcement learning for embodied agents is a challenging problem. The accumulated reward to be optimized is often a very rugged function, and gradient methods are impaired by many local optimizers. We demonstrate, in an experimental setting, that incorporating an intrinsic reward can smoothen the optimization landscape while preserving the global optimizers of interest. We show that policy gradient optimization for locomotion in a complex morphology is significantly improved when supplementing the extrinsic reward by an intrinsic reward defined in terms of the mutual information of time con…
Nanyang Technological University（南洋理工大学）；Singapore University of Technology and Design（新加坡科技设计大学）；Institute for Infocomm Research, A*STAR（新加坡科技研究局资讯通信研究院）
There has been an emerging paradigm shift from the era of "internet AI" to "embodied AI", where AI algorithms and agents no longer learn from datasets of images, videos or text curated primarily from the internet. Instead, they learn through interactions with their environments from an egocentric perception similar to humans. Consequently, there has been substantial growth in the demand for embodied AI simulators to support various embodied AI research tasks. This growing interest in embodied AI is beneficial to the greater pursuit of Artificial General Intelligence (AGI), but there has not be…
FluxVLA Engine: A One-Stop VLA Engineering Platform for Embodied Intelligence
LimX Dynamics；Nankai University（南开大学）；The University of Hong Kong（香港大学）；University of Electronic Science and Technology of China（电子科技大学）；Beijing Institute of Technology（北京理工大学）；Xidian University（西安电子科技大学）；Zhejiang University（浙江大学）；Xi’an Jiaotong University（西安交通大学）
Sorbonne Université（索邦大学）；CNRS（法国国家科学研究中心）；Vrije Universiteit（阿姆斯特丹自由大学）；Universidade da Coruna（拉科鲁尼亚大学）
This paper provides an overview of evolutionary robotics techniques applied to on-line distributed evolution for robot collectives -- namely, embodied evolution. It provides a definition of embodied evolution as well as a thorough description of the underlying concepts and mechanisms. The paper also presents a comprehensive summary of research published in the field since its inception (1999-2017), providing various perspectives to identify the major trends. In particular, we identify a shift from considering embodied evolution as a parallel search method within small robot collectives (fewer …
Co-policy: Responsive Human-Robot Co-Creation for Musical Performances
School of Computer Science, Wuhan University（武汉大学计算机学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；School of Automation, Wuhan University of Technology（武汉理工大学自动化学院）；School of Geodesy and Geomatics, Wuhan University（武汉大学测绘学院）；School of Robotics, Wuhan University（武汉大学机器人学院）
University of California, Los Angeles（加利福尼亚大学洛杉矶分校）；Amazon Alexa AI（亚马逊 Alexa AI）；University of California, San Diego（加利福尼亚大学圣迭戈分校）；University of Southern California（南加利福尼亚大学）
Learning-based methods for training embodied agents typically require a large number of high-quality scenes that contain realistic layouts and support meaningful interactions. However, current simulators for Embodied AI (EAI) challenges only provide simulated indoor scenes with a limited number of layouts. This paper presents Luminous, the first research framework that employs state-of-the-art indoor scene synthesis algorithms to generate large-scale simulated scenes for Embodied AI challenges. Further, we automatically and quantitatively evaluate the quality of generated indoor scenes via the…
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；Allen Institute for AI（艾伦人工智能研究所）
While deep reinforcement learning (RL) promises freedom from hand-labeled data, great successes, especially for Embodied AI, require significant work to create supervision via carefully shaped rewards. Indeed, without shaped rewards, i.e., with only terminal rewards, present-day Embodied AI results degrade significantly across Embodied AI problems from single-agent Habitat-based PointGoal Navigation (SPL drops from 55 to 0) and two-agent AI2-THOR-based Furniture Moving (success drops from 58% to 1%) to three-agent Google Football-based 3 vs. 1 with Keeper (game score drops from 0.6 to 0.1). As…
