Robot Manipulation and Learning

Últimos artículos

• Toward a Fully Autonomous, AI-Native Particle Accelerator

  Chris Tennant · 20 de febrero de 2026

  This position paper presents a vision for self-driving particle accelerators that operate autonomously with minimal human intervention. We propose that future facilities be designed through artificial intelligence (AI) co-design, where AI jointly optimizes the accelerator lattice, diagnostics, and s…

• SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation

  Kushal Kedia, Tyler Ga Wei Lum, Jeannette Bohg, C. Karen Liu · 20 de febrero de 2026

  The ability to manipulate tools significantly expands the set of tasks a robot can perform. Yet, tool manipulation represents a challenging class of dexterity, requiring grasping thin objects, in-hand object rotations, and forceful interactions. Since collecting teleoperation data for these behavior…

• RoboGene: Boosting VLA Pre-training via Diversity-Driven Agentic Framework for Real-World Task Generation

  Yixue Zhang (Beijing Innovation Center of Humanoid Robotics, The School of Advanced Manufacturing and Robotics, Peking University), Kun Wu (Beijing Innovation Center of Humanoid Robotics), Zhi Gao (Beijing Institute of Technology), Zhen Zhao (Beijing Innovation Center of Humanoid Robotics), Pei Ren (Beijing Innovation Center of Humanoid Robotics), Zhiyuan Xu (Beijing Innovation Center of Humanoid Robotics), Fei Liao (Beijing Innovation Center of Humanoid Robotics), Xinhua Wang (Beijing Innovation Center of Humanoid Robotics), Shichao Fan (Beijing Innovation Center of Humanoid Robotics, The School of Mechanical Engineering and Automation, Beihang University), Di Wu (Beijing Innovation Center of Humanoid Robotics, State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University), Qiuxuan Feng (Beijing Innovation Center of Humanoid Robotics, State Key Laboratory of Multimedia Information Processing, School of Computer Science, Peking University), Meng Li (Beijing Innovation Center of Humanoid Robotics), Zhengping Che (Beijing Innovation Center of Humanoid Robotics), Chang Liu (The School of Advanced Manufacturing and Robotics, Peking University), Jian Tang (Beijing Innovation Center of Humanoid Robotics) · 19 de febrero de 2026

  The pursuit of general-purpose robotic manipulation is hindered by the scarcity of diverse, real-world interaction data. Unlike data collection from web in vision or language, robotic data collection is an active process incurring prohibitive physical costs. Consequently, automated task curation to …

• FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency

  Yifei Su, Ning Liu, Dong Chen, Zhen Zhao, Kun Wu, Meng Li, Zhiyuan Xu, Zhengping Che, Jian Tang · 19 de febrero de 2026

  Generative modeling-based visuomotor policies have been widely adopted in robotic manipulation, attributed to their ability to model multimodal action distributions. However, the high inference cost of multi-step sampling limits its applicability in real-time robotic systems. Existing approaches acc…

• MARVL: Multi-Stage Guidance for Robotic Manipulation via Vision-Language Models

  Xunlan Zhou, Xuanlin Chen, Shaowei Zhang, Xiangkun Li, ShengHua Wan, Xiaohai Hu, Yuan Lei, Le Gan, De-chuan Zhan · 19 de febrero de 2026

  Designing dense reward functions is pivotal for efficient robotic Reinforcement Learning (RL). However, most dense rewards rely on manual engineering, which fundamentally limits the scalability and automation of reinforcement learning. While Vision-Language Models (VLMs) offer a promising path to re…

• Articulated 3D Scene Graphs for Open-World Mobile Manipulation

  Martin B\"uchner, Adrian R\"ofer, Tim Engelbracht, Tim Welschehold, Zuria Bauer, Hermann Blum, Marc Pollefeys, Abhinav Valada · 19 de febrero de 2026

  Semantics has enabled 3D scene understanding and affordance-driven object interaction. However, robots operating in real-world environments face a critical limitation: they cannot anticipate how objects move. Long-horizon mobile manipulation requires closing the gap between semantics, geometry, and …

• Dex4D: Task-Agnostic Point Track Policy for Sim-to-Real Dexterous Manipulation

  Yuxuan Kuang, Sungjae Park, Katerina Fragkiadaki, Shubham Tulsiani · 18 de febrero de 2026

  Learning generalist policies capable of accomplishing a plethora of everyday tasks remains an open challenge in dexterous manipulation. In particular, collecting large-scale manipulation data via real-world teleoperation is expensive and difficult to scale. While learning in simulation provides a fe…

• MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction

  Qiang Zhang, Jiahao Ma, Peiran Liu, Shuai Shi, Zeran Su, Zifan Wang, Jingkai Sun, Wei Cui, Jialin Yu, Gang Han, Wen Zhao, Pihai Sun, Kangning Yin, Jiaxu Wang, Jiahang Cao, Lingfeng Zhang, Hao Cheng, Xiaoshuai Hao, Yiding Ji, Junwei Liang, Jian Tang, Renjing Xu, Yijie Guo · 18 de febrero de 2026

  Humanoid motion control has witnessed significant breakthroughs in recent years, with deep reinforcement learning (RL) emerging as a primary catalyst for achieving complex, human-like behaviors. However, the high dimensionality and intricate dynamics of humanoid robots make manual motion design impr…

• HybridFlow: A Two-Step Generative Policy for Robotic Manipulation

  Zhenchen Dong, Jinna Fu, Jiaming Wu, Shengyuan Yu, Fulin Chen, Yide Liu · 17 de febrero de 2026

  Limited by inference latency, existing robot manipulation policies lack sufficient real-time interaction capability with the environment. Although faster generation methods such as flow matching are gradually replacing diffusion methods, researchers are pursuing even faster generation suitable for i…

• TWISTED-RL: Hierarchical Skilled Agents for Knot-Tying without Human Demonstrations

  Guy Freund, Tom Jurgenson, Matan Sudry, Erez Karpas · 17 de febrero de 2026

  Robotic knot-tying represents a fundamental challenge in robotics due to the complex interactions between deformable objects and strict topological constraints. We present TWISTED-RL, a framework that improves upon the previous state-of-the-art in demonstration-free knot-tying (TWISTED), which smart…

• SemanticFeels: Semantic Labeling during In-Hand Manipulation

  Anas Al Shikh Khalil, Haozhi Qi, Roberto Calandra · 17 de febrero de 2026

  As robots become increasingly integrated into everyday tasks, their ability to perceive both the shape and properties of objects during in-hand manipulation becomes critical for adaptive and intelligent behavior. We present SemanticFeels, an extension of the NeuralFeels framework that integrates sem…

• Learning Part-Aware Dense 3D Feature Field for Generalizable Articulated Object Manipulation

  Yue Chen, Muqing Jiang, Kaifeng Zheng, Jiaqi Liang, Chenrui Tie, Haoran Lu, Ruihai Wu, Hao Dong · 17 de febrero de 2026

  Articulated object manipulation is essential for various real-world robotic tasks, yet generalizing across diverse objects remains a major challenge. A key to generalization lies in understanding functional parts (e.g., door handles and knobs), which indicate where and how to manipulate across diver…

• Grounding Bodily Awareness in Visual Representations for Efficient Policy Learning

  Junlin Wang, Zhiyun Lin · 17 de febrero de 2026

  Learning effective visual representations for robotic manipulation remains a fundamental challenge due to the complex body dynamics involved in action execution. In this paper, we study how visual representations that carry body-relevant cues can enable efficient policy learning for downstream robot…

• Hierarchical Audio-Visual-Proprioceptive Fusion for Precise Robotic Manipulation

  Siyuan Li, Jiani Lu, Yu Song, Xianren Li, Bo An, Peng Liu · 17 de febrero de 2026

  Existing robotic manipulation methods primarily rely on visual and proprioceptive observations, which may struggle to infer contact-related interaction states in partially observable real-world environments. Acoustic cues, by contrast, naturally encode rich interaction dynamics during contact, yet r…

• FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation

  Huajian Zeng, Lingyun Chen, Jiaqi Yang, Yuantai Zhang, Fan Shi, Peidong Liu, Xingxing Zuo · 17 de febrero de 2026

  Recent vision-language-action (VLA) models can generate plausible end-effector motions, yet they often fail in long-horizon, contact-rich tasks because the underlying hand-object interaction (HOI) structure is not explicitly represented. An embodiment-agnostic interaction representation that capture…

• AdaptManip: Learning Adaptive Whole-Body Object Lifting and Delivery with Online Recurrent State Estimation

  Morgan Byrd, Donghoon Baek, Kartik Garg, Hyunyoung Jung, Daesol Cho, Maks Sorokin, Robert Wright, Sehoon Ha · 17 de febrero de 2026

  This paper presents Adaptive Whole-body Loco-Manipulation, AdaptManip, a fully autonomous framework for humanoid robots to perform integrated navigation, object lifting, and delivery. Unlike prior imitation learning-based approaches that rely on human demonstrations and are often brittle to disturba…

• Imitating What Works: Simulation-Filtered Modular Policy Learning from Human Videos

  Albert J. Zhai, Kuo-Hao Zeng, Jiasen Lu, Ali Farhadi, Shenlong Wang, Wei-Chiu Ma · 16 de febrero de 2026

  The ability to learn manipulation skills by watching videos of humans has the potential to unlock a new source of highly scalable data for robot learning. Here, we tackle prehensile manipulation, in which tasks involve grasping an object before performing various post-grasp motions. Human videos off…

• Accelerating Robotic Reinforcement Learning with Agent Guidance

  Haojun Chen, Zili Zou, Chengdong Ma, Yaoxiang Pu, Haotong Zhang, Yuanpei Chen, Yaodong Yang · 13 de febrero de 2026

  Reinforcement Learning (RL) offers a powerful paradigm for autonomous robots to master generalist manipulation skills through trial-and-error. However, its real-world application is stifled by severe sample inefficiency. Recent Human-in-the-Loop (HIL) methods accelerate training by using human corre…

• MolmoSpaces: A Large-Scale Open Ecosystem for Robot Navigation and Manipulation

  Yejin Kim, Wilbert Pumacay, Omar Rayyan, Max Argus, Winson Han, Eli VanderBilt, Jordi Salvador, Abhay Deshpande, Rose Hendrix, Snehal Jauhri, Shuo Liu, Nur Muhammad Mahi Shafiullah, Maya Guru, Ainaz Eftekhar, Karen Farley, Donovan Clay, Jiafei Duan, Arjun Guru, Piper Wolters, Alvaro Herrasti, Ying-Chun Lee, Georgia Chalvatzaki, Yuchen Cui, Ali Farhadi, Dieter Fox, Ranjay Krishna · 13 de febrero de 2026

  Deploying robots at scale demands robustness to the long tail of everyday situations. The countless variations in scene layout, object geometry, and task specifications that characterize real environments are vast and underrepresented in existing robot benchmarks. Measuring this level of generalizat…

• Flow-Enabled Generalization to Human Demonstrations in Few-Shot Imitation Learning

  Runze Tang, Penny Sweetser · 12 de febrero de 2026

  Imitation Learning (IL) enables robots to learn complex skills from demonstrations without explicit task modeling, but it typically requires large amounts of demonstrations, creating significant collection costs. Prior work has investigated using flow as an intermediate representation to enable the …

• ContactGaussian-WM: Learning Physics-Grounded World Model from Videos

  Meizhong Wang, Wanxin Jin, Kun Cao, Lihua Xie, Yiguang Hong · 12 de febrero de 2026

  Developing world models that understand complex physical interactions is essential for advancing robotic planning and simulation.However, existing methods often struggle to accurately model the environment under conditions of data scarcity and complex contact-rich dynamic motion.To address these cha…

• Localized Graph-Based Neural Dynamics Models for Terrain Manipulation

  Chaoqi Liu, Yunzhu Li, Kris Hauser · 12 de febrero de 2026

  Predictive models can be particularly helpful for robots to effectively manipulate terrains in construction sites and extraterrestrial surfaces. However, terrain state representations become extremely high-dimensional especially to capture fine-resolution details and when depth is unknown or unbound…

• Self-Augmented Robot Trajectory: Efficient Imitation Learning via Safe Self-augmentation with Demonstrator-annotated Precision

  Hanbit Oh, Masaki Murooka, Tomohiro Motoda, Ryoichi Nakajo, Yukiyasu Domae · 12 de febrero de 2026

  Imitation learning is a promising paradigm for training robot agents; however, standard approaches typically require substantial data acquisition -- via numerous demonstrations or random exploration -- to ensure reliable performance. Although exploration reduces human effort, it lacks safety guarant…

• RoboSubtaskNet: Temporal Sub-task Segmentation for Human-to-Robot Skill Transfer in Real-World Environments

  Dharmendra Sharma, Archit Sharma, John Reberio, Vaibhav Kesharwani, Peeyush Thakur, Narendra Kumar Dhar, Laxmidhar Behera · 11 de febrero de 2026

  Temporally locating and classifying fine-grained sub-task segments in long, untrimmed videos is crucial to safe human-robot collaboration. Unlike generic activity recognition, collaborative manipulation requires sub-task labels that are directly robot-executable. We present RoboSubtaskNet, a multi-s…

• Sample-Efficient Real-World Dexterous Policy Fine-Tuning via Action-Chunked Critics and Normalizing Flows

  Chenyu Yang, Denis Tarasov, Davide Liconti, Hehui Zheng, Robert K. Katzschmann · 11 de febrero de 2026

  Real-world fine-tuning of dexterous manipulation policies remains challenging due to limited real-world interaction budgets and highly multimodal action distributions. Diffusion-based policies, while expressive, do not permit conservative likelihood-based updates during fine-tuning because action pr…