Robot Manipulation and Learning

Últimos artículos

• A hierarchical spatial-aware algorithm with efficient reinforcement learning for human-robot task planning and allocation in production

  Jintao Xue, Xiao Li, Nianmin Zhang · 15 de abril de 2026

  In advanced manufacturing systems, humans and robots collaborate to conduct the production process. Effective task planning and allocation (TPA) is crucial for achieving high production efficiency, yet it remains challenging in complex and dynamic manufacturing environments. The dynamic nature of hu…

• Frequency-aware Decomposition Learning for Sensorless Wrench Forecasting on a Vibration-rich Hydraulic Manipulator

  Hyeonbeen Lee, Min-Jae Jung, Tae-Kyeong Yeu, Jong-Boo Han, Daegil Park, Jin-Gyun Kim · 15 de abril de 2026

  Force and torque (F/T) sensing is critical for robot-environment interaction, but physical F/T sensors impose constraints in size, cost, and fragility. To mitigate this, recent studies have estimated force/wrench sensorlessly from robot internal states. While existing methods generally target relati…

• FastGrasp: Learning-based Whole-body Control method for Fast Dexterous Grasping with Mobile Manipulators

  Heng Tao, Yiming Zhong, Zemin Yang, Yuexin Ma · 15 de abril de 2026

  Fast grasping is critical for mobile robots in logistics, manufacturing, and service applications. Existing methods face fundamental challenges in impact stabilization under high-speed motion, real-time whole-body coordination, and generalization across diverse objects and scenarios, limited by fixe…

• IMPACT: A Dataset for Multi-Granularity Human Procedural Action Understanding in Industrial Assembly

  Di Wen, Zeyun Zhong, David Schneider, Manuel Zaremski, Linus Kunzmann, Yitian Shi, Ruiping Liu, Yufan Chen, Junwei Zheng, Jiahang Li, Jonas Hemmerich, Qiyi Tong, Patric Grauberger, Arash Ajoudani, Danda Pani Paudel, Sven Matthiesen, Barbara Deml, J\"urgen Beyerer, Luc Van Gool, Rainer Stiefelhagen, Kunyu Peng · 14 de abril de 2026

  We introduce IMPACT, a synchronized five-view RGB-D dataset for deployment-oriented industrial procedural understanding, built around real assembly and disassembly of a commercial angle grinder with professional-grade tools. To our knowledge, IMPACT is the first real industrial assembly benchmark th…

• AffordSim: A Scalable Data Generator and Benchmark for Affordance-Aware Robotic Manipulation

  Mingyang Li, Haofan Xu, Haowen Sun, Xinzhe Chen, Sihua Ren, Liqi Huang, Xinyang Sui, Chenyang Miao, Qiongjie Cui, Zeyang Liu, Xingyu Chen, Xuguang Lan · 14 de abril de 2026

  Simulation-based data generation has become a dominant paradigm for training robotic manipulation policies, yet existing platforms do not incorporate object affordance information into trajectory generation. As a result, tasks requiring precise interaction with specific functional regions--grasping …

• Volumetric Ergodic Control

  Jueun Kwon, Max M. Sun, Todd Murphey · 14 de abril de 2026

  Ergodic control synthesizes optimal coverage behaviors over spatial distributions for nonlinear systems. However, existing formulations model the robot as a non-volumetric point, whereas in practice a robot interacts with the environment through its body and sensors with physical volume. In this wor…

• Multimodal Diffusion Forcing for Forceful Manipulation

  Zixuan Huang, Huaidian Hou, Dmitry Berenson · 14 de abril de 2026

  Given a dataset of expert trajectories, standard imitation learning approaches typically learn a direct mapping from observations (e.g., RGB images) to actions. However, such methods often overlook the rich interplay between different modalities, i.e., sensory inputs, actions, and rewards, which is …

• AffordGen: Generating Diverse Demonstrations for Generalizable Object Manipulation with Afford Correspondence

  Jiawei Zhang, Kaizhe Hu, Yingqian Huang, Yuanchen Ju, Zhengrong Xue, Huazhe Xu · 14 de abril de 2026

  Despite the recent success of modern imitation learning methods in robot manipulation, their performance is often constrained by geometric variations due to limited data diversity. Leveraging powerful 3D generative models and vision foundation models (VFMs), the proposed AffordGen framework overcome…

• SafeMind: A Risk-Aware Differentiable Control Framework for Adaptive and Safe Quadruped Locomotion

  Zukun Zhang, Kai Shu, Mingqiao Mo · 13 de abril de 2026

  Learning-based quadruped controllers achieve impressive agility but typically lack formal safety guarantees under model uncertainty, perception noise, and unstructured contact conditions. We introduce SafeMind, a differentiable stochastic safety-control framework that unifies probabilistic Control B…

• STAR: Learning Diverse Robot Skill Abstractions through Rotation-Augmented Vector Quantization

  Hao Li, Qi Lv, Rui Shao, Xiang Deng, Yinchuan Li, Jianye Hao, Liqiang Nie · 8 de abril de 2026

  Transforming complex actions into discrete skill abstractions has demonstrated strong potential for robotic manipulation. Existing approaches mainly leverage latent variable models, e.g., VQ-VAE, to learn skill abstractions through learned vectors (codebooks), while they suffer from codebook collaps…

• RoboPlayground: Democratizing Robotic Evaluation through Structured Physical Domains

  Yi Ru Wang, Carter Ung, Evan Gubarev, Christopher Tan, Siddhartha Srinivasa, Dieter Fox · 8 de abril de 2026

  Evaluation of robotic manipulation systems has largely relied on fixed benchmarks authored by a small number of experts, where task instances, constraints, and success criteria are predefined and difficult to extend. This paradigm limits who can shape evaluation and obscures how policies respond to …

• SnapFlow: One-Step Action Generation for Flow-Matching VLAs via Progressive Self-Distillation

  Wuyang Luan, Junhui Li, Weiguang Zhao, Wenjian Zhang, Tieru Wu, Rui Ma · 8 de abril de 2026

  Vision-Language-Action (VLA) models based on flow matching -- such as pi0, pi0.5, and SmolVLA -- achieve state-of-the-art generalist robotic manipulation, yet their iterative denoising, typically 10 ODE steps, introduces substantial latency: on a modern GPU, denoising alone accounts for 80% of end-t…

• Belief Dynamics for Detecting Behavioral Shifts in Safe Collaborative Manipulation

  Devashri Naik, Divake Kumar, Nastaran Darabi, Amit Ranjan Trivedi · 8 de abril de 2026

  Robots operating in shared workspaces must maintain safe coordination with other agents whose behavior may change during task execution. When a collaborating agent switches strategy mid-episode, continuing under outdated assumptions can lead to unsafe actions and increased collision risk. Reliable d…

• Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation

  Yifu Yuan, Haiqin Cui, Yaoting Huang, Yibin Chen, Fei Ni, Zibin Dong, Pengyi Li, Yan Zheng, Hongyao Tang, Jianye Hao · 7 de abril de 2026

  Generalization in embodied AI is hindered by the "seeing-to-doing gap," which stems from data scarcity and embodiment heterogeneity. To address this, we pioneer "pointing" as a unified, embodiment-agnostic intermediate representation, defining four core embodied pointing abilities that bridge high-l…

• SERNF: 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 · 7 de abril 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…

• CRAFT: Video Diffusion for Bimanual Robot Data Generation

  Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme, Daniel Seita · 7 de abril de 2026

  Bimanual robot learning from demonstrations is fundamentally limited by the cost and narrow visual diversity of real-world data, which constrains policy robustness across viewpoints, object configurations, and embodiments. We present Canny-guided Robot Data Generation using Video Diffusion Transform…

• From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation

  Yifu Yuan, Haiqin Cui, Yibin Chen, Zibin Dong, Fei Ni, Longxin Kou, Jinyi Liu, Pengyi Li, Yan Zheng, Jianye Hao · 7 de abril de 2026

  Achieving generalization in robotic manipulation remains a critical challenge, particularly for unseen scenarios and novel tasks. Current Vision-Language-Action (VLA) models, while building on top of general Vision-Language Models (VLMs), still fall short of achieving robust zero-shot performance du…

• HOIGS: Human-Object Interaction Gaussian Splatting

  Taewoo Kim, Suwoong Yeom, Jaehyun Pyun, Geonho Cha, Dongyoon Wee, Joonsik Nam, Yun-Seong Jeong, Kyeongbo Kong, Suk-Ju Kang · 7 de abril de 2026

  Reconstructing dynamic scenes with complex human-object interactions is a fundamental challenge in computer vision and graphics. Existing Gaussian Splatting methods either rely on human pose priors while neglecting dynamic objects, or approximate all motions within a single field, limiting their abi…

• Learning Dexterous Grasping from Sparse Taxonomy Guidance

  Juhan Park, Taerim Yoon, Seungmin Kim, Joonggil Kim, Wontae Ye, Jeongeun Park, Yoonbyung Chai, Geonwoo Cho, Geunwoo Cho, Dohyeong Kim, Kyungjae Lee, Yongjae Kim, Sungjoon Choi · 7 de abril de 2026

  Dexterous manipulation requires planning a grasp configuration suited to the object and task, which is then executed through coordinated multi-finger control. However, specifying grasp plans with dense pose or contact targets for every object and task is impractical. Meanwhile, end-to-end reinforcem…

• Pickalo: Leveraging 6D Pose Estimation for Low-Cost Industrial Bin Picking

  Alessandro Tarsi, Matteo Mastrogiuseppe, Saverio Taliani, Simone Cortinovis, Ugo Pattacini · 7 de abril de 2026

  Bin picking in real industrial environments remains challenging due to severe clutter, occlusions, and the high cost of traditional 3D sensing setups. We present Pickalo, a modular 6D pose-based bin-picking pipeline built entirely on low-cost hardware. A wrist-mounted RGB-D camera actively explores …

• ROPA: Synthetic Robot Pose Generation for RGB-D Bimanual Data Augmentation

  Jason Chen, I-Chun Arthur Liu, Gaurav Sukhatme, Daniel Seita · 6 de abril de 2026

  Training robust bimanual manipulation policies via imitation learning requires demonstration data with broad coverage over robot poses, contacts, and scene contexts. However, collecting diverse and precise real-world demonstrations is costly and time-consuming, which hinders scalability. Prior works…

• The Compression Gap: Why Discrete Tokenization Limits Vision-Language-Action Model Scaling

  Takuya Shiba · 6 de abril de 2026

  Scaling Vision-Language-Action (VLA) models by upgrading the vision encoder is expected to improve downstream manipulation performance--as it does in vision-language modeling. We show that this expectation fails when actions are represented as discrete tokens, and explain why through an information-…

• Cross-Modal Visuo-Tactile Object Perception

  Anirvan Dutta, Simone Tasciotti, Claudia Cusseddu, Ang Li, Panayiota Poirazi, Julijana Gjorgjieva, Etienne Burdet, Patrick van der Smagt, Mohsen Kaboli · 3 de abril de 2026

  Estimating physical properties is critical for safe and efficient autonomous robotic manipulation, particularly during contact-rich interactions. In such settings, vision and tactile sensing provide complementary information about object geometry, pose, inertia, stiffness, and contact dynamics, such…

• Multi-Camera View Scaling for Data-Efficient Robot Imitation Learning

  Yichen Xie, Yixiao Wang, Shuqi Zhao, Cheng-En Wu, Masayoshi Tomizuka, Jianwen Xie, Hao-Shu Fang · 2 de abril de 2026

  The generalization ability of imitation learning policies for robotic manipulation is fundamentally constrained by the diversity of expert demonstrations, while collecting demonstrations across varied environments is costly and difficult in practice. In this paper, we propose a practical framework t…

• House of Dextra: Cross-embodied Co-design for Dexterous Hands

  Kehlani Fay, Darin Anthony Djapri, Anya Zorin, James Clinton, Ali El Lahib, Hao Su, Michael T. Tolley, Sha Yi, Xiaolong Wang · 2 de abril de 2026

  Dexterous manipulation is limited by both control and design, without consensus as to what makes manipulators best for performing dexterous tasks. This raises a fundamental challenge: how should we design and control robot manipulators that are optimized for dexterity? We present a co-design framewo…