Robot Manipulation and Learning

Últimos artículos

• Learning Sim-Grounded Policies for Bimanual Rope Manipulation from Human Teleoperation Data

  Gina Wigginghaus, Tim Missal, Berk Guler, Simon Manschitz, Jan Peters · 18 de mayo de 2026

  Deformable Linear Objects (DLOs) such as ropes and cables are widely encountered in both household and industrial applications, yet remain challenging to manipulate due to their infinite-dimensional configuration space and frequent self-occlusion. Imitation learning from teleoperation offers a pract…

• SkiP: When to Skip and When to Refine for Efficient Robot Manipulation

  Mingtong Dai, Guanqi Peng, Yongjie Bai, Feng Yan, Chunjie Chen, Lingbo Liu, Liang Lin, Xinyu Wu · 18 de mayo de 2026

  Previous imitation learning policies predict future actions at every control step, whether in smooth motion phases or precise, contact-rich operation phases. This uniform treatment is wasteful: most steps in a manipulation trajectory traverse free space and carry little task-relevant information, wh…

• DecomPose: Disentangling Cross-Category Optimization Contention for Category-Level 6D Object Pose Estimation

  Yifan Gao, Lu Zou, Zhangjin Huang, Guoping Wang · 18 de mayo de 2026

  Category-level 6D object pose estimation is typically formulated as a multi-category joint learning problem with fully shared model parameters. However, pronounced geometric heterogeneity across categories entangles incompatible optimization signals in shared modules, resulting in gradient conflicts…

• Offline Semantic Guidance for Efficient Vision-Language-Action Policy Distillation

  Jin Shi, Brady Zhang, Yishun Lu · 18 de mayo de 2026

  Billion-parameter Vision-Language-Action (VLA) policies have recently shown impressive performance in robotic manipulation, yet their size and inference cost remain major obstacles for real-time closed-loop control. We introduce \textbf{VLA-AD}, a distillation framework that uses a Vision-Language M…

• GAP: Geometric Anchor Pre-training for Data-Efficient Visuomotor Learning of Manipulation Tasks

  Davide Buoso, Andrea Protopapa, Stefano Di Carlo, Francesca Pistilli, Giuseppe Averta · 18 de mayo de 2026

  Learning visuomotor policies from scarce expert demonstrations remains a core challenge in robotic manipulation. A primary hurdle lies in distilling high-dimensional RGB representations into control-relevant geometry without overfitting. While using frozen pre-trained Vision Foundation Models (VFMs)…

• Hand-in-the-Loop: Improving Dexterous VLA via Seamless Interventional Correction

  Zhuohang Li, Liqun Huang, Wei Xu, Zhengming Zhu, Nie Lin, Xiao Ma, Xinjun Sheng, Ruoshi Wen · 15 de mayo de 2026

  Vision-Language-Action (VLA) models are prone to compounding errors in dexterous manipulation, where high-dimensional action spaces and contact-rich dynamics amplify small policy deviations over long horizons. While Interactive Imitation Learning (IIL) can refine policies through human takeover data…

• WarmPrior: Straightening Flow-Matching Policies with Temporal Priors

  Sinjae Kang, Chanyoung Kim, Kaixin Wang, Li Zhao, Kimin Lee · 15 de mayo de 2026

  Generative policies based on diffusion and flow matching have become a dominant paradigm for visuomotor robotic control. We show that replacing the standard Gaussian source distribution with WarmPrior, a simple temporally grounded prior constructed from readily available recent action history, consi…

• Matrix-Space Reinforcement Learning for Reusing Local Transition Geometry

  Zuyuan Zhang, Carlee Joe-Wong, Tian Lan · 15 de mayo de 2026

  Compositional generalization in sequential decision-making requires identifying which parts of prior rollouts remain useful for new tasks. Existing methods reuse skills or predictive models, but often overlook rich local transition geometry and dynamics. We propose Matrix-Space Reinforcement Learnin…

• When Absolute State Fails: Evaluating Proprioceptive Encodings for Robust Manipulation

  Maxime Alvarez, Ryo Watanabe, Paul Crook, Afshin Zeinaddini Meymand, Suvin Kurian, Pablo Ferreiro, Genki Sano · 14 de mayo de 2026

  As end-to-end robotic policies are progressively deployed in the real world to solve real tasks, they face a gap between the training and inference conditions. Scaling the amount and diversity of the training data has shown some success in improving zero-shot generalization, yet robots still fail wh…

• CUBic: Coordinated Unified Bimanual Perception and Control Framework

  Xingyu Wang, Pengxiang Ding, Jingkai Xu, Donglin Wang, Zhaoxin Fan · 14 de mayo de 2026

  Recent advances in visuomotor policy learning have enabled robots to perform control directly from visual inputs. Yet, extending such end-to-end learning from single-arm to bimanual manipulation remains challenging due to the need for both independent perception and coordinated interaction between a…

• SECOND-Grasp: Semantic Contact-guided Dexterous Grasping

  Han Yi Shin, Heeju Ko, Jaewon Mun, Qixing Huang, Jaehyeok Lee, Sung June Kim, Honglak Lee, Sujin Jang, Sangpil Kim · 14 de mayo de 2026

  Achieving reliable robotic manipulation, such as dexterous grasping, requires a synergy between physically stable interactions and semantic task guidance, yet these objectives are often treated as separate, disjoint goals. In this paper, we investigate how to integrate dexterous grasping techniques,…

• UniJEPA: Enhancing Robot Policy via Unified Continuous and Discrete Representation Learning

  Jianke Zhang, Yucheng Hu, Yanjiang Guo, Xiaoyu Chen, Yichen Liu, Wenna Chen, Chaochao Lu, Jianyu Chen · 14 de mayo de 2026

  Building generalist robot policies that can handle diverse tasks in open-ended environments is a central challenge in robotics. To leverage knowledge from large-scale pretraining, prior work (VLA) has typically built generalist policies either on top of vision-language understanding models (VLMs) or…

• Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations

  Shivansh Patel, Shraddhaa Mohan, Hanlin Mai, Unnat Jain, Svetlana Lazebnik, Yunzhu Li · 14 de mayo de 2026

  This work introduces Robots Imitating Generated Videos (RIGVid), a system that enables robots to perform complex manipulation tasks--such as pouring, wiping, and mixing--purely by imitating AI-generated videos, without requiring any physical demonstrations or robot-specific training. Given a languag…

• AssemblyBench: Physics-Aware Assembly of Complex Industrial Objects

  Danrui Li, Jiahao Zhang, Bernhard Egger, Moitreya Chatterjee, Suhas Lohit, Tim K. Marks, Anoop Cherian · 14 de mayo de 2026

  Assembling objects from parts requires understanding multimodal instructions, linking them to 3D components, and predicting physically plausible 6-DoF motions for each assembly step. Existing datasets focus on simplified scenarios, overlooking shape complexities and assembly trajectories in industri…

• AttenA+: Rectifying Action Inequality in Robotic Foundation Models

  Daojie Peng, Fulong Ma, Jiahang Cao, Qiang Zhang, Xupeng Xie, Jian Guo, Ping Luo, Andrew F. Luo, Boyu Zhou, Jun Ma · 14 de mayo de 2026

  Existing robotic foundation models, while powerful, are predicated on an implicit assumption of temporal homogeneity: treating all actions as equally informative during optimization. This "flat" training paradigm, inherited from language modeling, remains indifferent to the underlying physical hiera…

• HeteroGenManip: Generalizable Manipulation For Heterogeneous Object Interactions

  Zhenhao Shen, Zeming Yang, Yue Chen, Yuran Wang, Shengqiang Xu, Mingleyang Li, Hao Dong, Ruihai Wu · 13 de mayo de 2026

  Generalizable manipulation involving cross-type object interactions is a critical yet challenging capability in robotics. To reliably accomplish such tasks, robots must address two fundamental challenges: "where to manipulate" (contact point localization) and "how to manipulate" (subsequent interact…

• ForceFlow: Learning to Feel and Act via Contact-Driven Flow Matching

  Shuoheng Zhang, Yifu Yuan, Hongyao Tang, Yan Zheng, Qiaojun Yu, Pengyi Li, Guowei Huang, Helong Huang, Xingyue Quan, Jianye Hao · 13 de mayo de 2026

  Existing imitation learning methods enable robots to interact autonomously with the physical environment. However, contact-rich manipulation tasks remain a significant challenge due to complex contact dynamics that demand high-precision force feedback and control. Although recent efforts have attemp…

• Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context

  Mohammad Shahverdikondori, Amir Mohammad Abouei, Alireza Rezaeimoghadam, Negar Kiyavash · 13 de mayo de 2026

  We introduce the problem of best arm identification (BAI) with post-action context, a new BAI problem in a stochastic multi-armed bandit environment and the fixed-confidence setting. The problem addresses the scenarios in which the learner receives a post-action context in addition to the reward aft…

• Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation

  Hao Wang, Joshua Bowden, Colton Crosby, Somil Bansal · 13 de mayo de 2026

  Policy evaluation is a fundamental component of the development and deployment pipeline for robotic policies. In modern manipulation systems, this problem is particularly challenging: rewards are often sparse, task progression of evaluation rollouts are often non-monotonic as the policies exhibit re…

• DreamAvoid: Critical-Phase Test-Time Dreaming to Avoid Failures in VLA Policies

  Xianzhe Fan, Yuxiang Lu, Shenyuan Gao, Xiaoyang Wu, Ruihua Han, Manling Li, Hengshuang Zhao · 13 de mayo de 2026

  Vision-Language-Action (VLA) models are often brittle in fine-grained manipulation, where minor action errors during the critical phases can rapidly escalate into irrecoverable failures. Since existing VLA models rely predominantly on successful demonstrations for training, they lack an explicit awa…

• SEVO: Semantic-Enhanced Virtual Observation for Robust VLA Manipulation via Active Illumination and Data-Centric Collection

  Tianchonghui Fang, Yuan Zhuang, Fei Miao · 13 de mayo de 2026

  Vision-Language-Action (VLA) and imitation-learning policies trained via community toolchains on low-cost hardware frequently fail when deployed outside the training environment. Existing evaluations, including the original ACT and SmolVLA benchmarks, demonstrate high success rates under controlled,…

• PhysHanDI: Physics-Based Reconstruction of Hand-Deformable Object Interactions

  Jihyun Lee, Changmin Lee, Donghwan Kim, Tae-Kyun Kim · 12 de mayo de 2026

  While existing methods for reconstructing hand-object interactions have made impressive progress, they either focus on rigid or part-wise rigid objects-limiting their ability to model real-world objects (e.g., cloth, stuffed animals) that exhibit highly non-rigid deformations-or model deformable obj…

• TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning

  Giacomo Spigler · 11 de mayo de 2026

  Active vision -- where a policy controls its own gaze during manipulation -- has emerged as a key capability for imitation learning, with multiple independent systems demonstrating its benefits in the past year. Yet there is no shared benchmark to compare approaches or quantify what active vision co…

• Rollback-Free Stable Brick Structures Generation

  Chenhui Xu, Ziyue Bai, Fuxun Yu, Heng Huang, Jinjun Xiong · 11 de mayo de 2026

  While autoregressive models have advanced 3D generation, creating physically stable brick structures remains a challenge due to the strict requirements of gravity and interconnectivity. Existing approaches rely on external physical simulators during inference to perform rejection sampling and brick-…

• DexSim2Real: Foundation Model-Guided Sim-to-Real Transfer for Generalizable Dexterous Manipulation

  Zijian Zeng, Fei Ding, Huiming Yang, Xianwei Li, Yuhao Liao · 8 de mayo de 2026

  Sim-to-real transfer remains a critical bottleneck for deploying dexterous manipulation policies learned in simulation to real-world robots. Existing approaches rely on manually designed domain randomization or task-specific adaptation, limiting their generalizability across diverse manipulation sce…