Robot Manipulation and Learning

Últimos artículos

• SkillMemo: Expert-guided Skill Memory Framework for Compositional Embodied Manipulation

  Changyuan Wang, Chubin Zhang, Zhenyu Wu, Runhao Li, Angyuan Ma, Ke Chao, Yinan Liang, Xiuwei Xu, Ziwei Wang, Yansong Tang, Jiwen Lu · 7 de agosto de 2026

  Embodied visuomotor models, including Diffusion Policy (DP) and Vision-Language-Action (VLA) models, have demonstrated promising performance on robotic manipulation benchmarks. However, their potential remains fundamentally constrained by the scarcity of large-scale embodied trajectory datasets, lea…

• Robot Learning from Human Demonstrations: Handwritten Alphabet Trajectories and Human-Likeness Evaluation

  Alperen Kenan, Paul Bremner, Manuel Giuliani · 7 de agosto de 2026

  Learning from demonstration (LfD) provides a developmental framework through which robots can develop motor skills by observing and imitating human dynamics, reducing reliance on explicit programming to teach a skill to a robot. The resulting human-like robot motion is recognised as a key factor in …

• Arnold: A multi-task, multi-embodiment muscle transformer policy

  Boshi An, Alberto Silvio Chiappa, Merkourios Simos, Chengkun Li, Alexander Mathis · 6 de agosto de 2026

  Controlling high-dimensional and nonlinear musculoskeletal models of the human body is a foundational scientific challenge. Recent machine learning breakthroughs have heralded in-silico policies that master individual skills like reaching, object manipulation and locomotion in musculoskeletal system…

• SiMDex: Mining Similar Egocentric Videos for Cross-Embodiment Dexterous Manipulation

  Nie Lin, Takehiko Ohkawa, Sijin Chen, Ruoshi Wen, Zhuohang Li, Liqun Huang, Zhengming Zhu, Yiming Bao, Yunfei Li, Minjie Cai, Xiao Ma, Wei Xu, Yoichi Sato · 6 de agosto de 2026

  Recent years have witnessed an explosive trend of scaling ego-centric human videos for robot manipulation, yet it remains unclear which data actually benefits dexterous manipulation. We present SiMDex, a similarity-based data mining framework that casts human data selection for VLA post-training in …

• Continue or Replan? Bernoulli-Continuation Policy Learning for Adaptive Horizon Execution

  Weichen Xu, Zhenhua Liu, Lin Luo, Yaobo Liang, Chengtang Yao, Qingyu Mei, Jian Cao, Xixin Cao, Xing Zhang, Jiaolong Yang, Baining Guo · 5 de agosto de 2026

  Existing chunk-based Vision-Language-Action (VLA) models execute a fixed number of actions (i.e., execution horizon) before replanning, turning replanning into a task-agnostic periodic schedule that is independent of task progress. As a result, when no replanning boundary falls before a critical man…

• DynamicManip: Enabling Dynamic Manipulation from a Single Static Demonstration

  Haoran Liao, Pengyue Wang, Shuoyu Chen, Kehan Cheng, Xuhang Chen, Yuhao Lin, Mu Lin, Zhizhao Liang, Xiaoyi Fan, Chengyi Xing, Dan Niu, Yi-Lin Wei, Wei-Shi Zheng · 4 de agosto de 2026

  Dynamic manipulation is a critical capability for robots operating in complex and dynamic environments, where robots must interact with objects that are moving or require rapid adjustments. However, learning models for dynamic manipulation tasks face two major challenges: (1) the combinatorial compl…

• Demystifying When and Why VLAs Fail in Contact-Rich Tasks and How to Fix Them

  Carlota Par\'es-Morlans, Nils Kuhn, Isabel Liu, Alberta Longhini, Jeannette Bohg · 4 de agosto de 2026

  We address the problem of understanding when and why Vision-Language-Action models struggle with contact-rich manipulation tasks that require precise physical interaction. Prior work has primarily focused on addressing contact failures through force-augmented architectures and training-time regulari…

• DexMani: Human-Derived Manipulability Guidance for Dexterous Rotation

  Xiaoyang Chen, Shengcheng Luo, Haoran Guo, Jiaming Jiang, Wanlin Li, Ziyuan Jiao, Chenxi Xiao · 4 de agosto de 2026

  Dexterous object rotation is a sequential contact problem: each support, release, and re-contact decision must both produce the desired object motion, and prepare the hand configuration for continued rotation. Existing reinforcement learning methods discover such movement patterns through trial and …

• MANGO-Grasp: Mahalanobis Fields over Geometry-Oriented 3D Gaussians for Cross-Embodiment Dexterous Grasping

  Heng Zhang, Kevin Yuchen Ma, Mike Zheng Shou, Weisi Lin, Yan Wu · 4 de agosto de 2026

  Cross-embodiment dexterous grasping aims to synthesize stable grasps across heterogeneous multi-fingered hands with little or no embodiment-specific tuning. Existing interaction-centric methods achieve promising results, but their object representations often underrepresent local surface geometry, w…

• Grounded Vision-Language Interpreter for Long-Horizon Bimanual Task and Motion Planning

  Jeremy Siburian, Keisuke Shirai, Cristian C. Beltran-Hernandez, Masashi Hamaya, Michael G\"orner, Atsushi Hashimoto · 4 de agosto de 2026

  While recent advances in vision-language models have accelerated language-guided robot planning, their black-box nature lacks the safety guarantees and interpretability crucial for real-world deployment. Conversely, classical symbolic planners offer rigorous safety verification but require significa…

• GraRe: Grasp Candidate Re-Ranking for Frozen 6-DoF Grasp Detectors

  Jibao Yuan, Yuhui Zhao, Yinzhen Lv, Chao Xu, Shun Li, Chenxi Deng, Shaofei Chen · 4 de agosto de 2026

  Existing 6-DoF grasp detectors typically rank grasp candidates by detector confidence. However, our analysis on GraspNet-1Billion shows that detector confidence is often poorly aligned with grasp quality, causing successful grasp candidates to be ranked too low during execution. Motivated by this ob…

• Towards General Language-Conditioned Latent Safety Filters

  Ihab Tabbara, Yuxuan Yang, Hussein Sibai · 4 de agosto de 2026

  Robot policies are becoming increasingly general, with vision-language-action (VLA) models enabling a single policy to execute diverse tasks specified in natural language. Safe deployment, however, requires adapting not only to new tasks but also to varying safety requirements across users, environm…

• Corrigible Assistance in One Round: Pragmatic-Pedagogic Best Response

  Elle Lazarski, Jaime Fern\'andez Fisac · 4 de agosto de 2026

  Assistance games formalize human-robot collaboration under asymmetric information: the human knows the goal, while the robot must infer it from observation and interaction in order to assist effectively. In general, computing optimal assistance game strategies online is intractable, since exact solu…

• Weights or Skills? A Survey of Robot-Learning Techniques: from Action-Predicting Weights to Robots that Write their Own Skills

  Gaytri Jena, Kapil Wanaskar, Vinija Jain, Aman Chadha, Vasu Sharma, Amitava Das · 4 de agosto de 2026

  Robot learning is splitting into two bets: policies that bake competence into frozen weights (vision-language-action, or VLA, models), and agents that write and refine their own executable skills as code. This survey organises the field around that axis of weights versus skills. Its central analytic…

• CoWAM: Coordination Contracts for Selective Policy Intervention with WAMs

  Shuaijun Liu, Qifu Wen, Shuyang Hao, Qi Luo, Chenglong Zhang, Feiyang You, Chengyu Wu, Ningxin Su · 4 de agosto de 2026

  World Action Models (WAMs) augment robot policies with action-conditioned predicted futures, but a plausible future alone does not justify changing the action that a bimanual policy would execute. We present CoWAM, a selective intervention layer that expresses synchronization, role compatibility, an…

• FBFM: A Training-Free Asynchronous Feedback Mechanism for Flow-Matching in World-Action Models Execution

  Peize Li, Ruimeng Zhang, Ru Zhang, Cong Huang, Kai Chen, Shanghang Zhang · 3 de agosto de 2026

  Although world-action models (WAMs) enhance long-horizon robot control by predicting visual evolution before acting, long-horizon reliability demands repeated re-grounding in real observations--not recursive rollout. Existing WAMs address this by refreshing history or KV cache with ground-truth data…

• Lightweight Neural Networks for Affordance Segmentation: Enhancement of the Decoder Module

  Simone Lugani, Edoardo Ragusa, Rodolfo Zunino, Paolo Gastaldo · 3 de agosto de 2026

  The deployment of deep neural networks for visual affordance segmentation on wearable robots poses may prove critical, due to some conflicting aspects of the problem. On one hand, affordance segmentation requires high-level abstraction capabilities, that typically involve large-size models. On the o…

• ActFovea: Runtime Safeguarding for VLA Policies via Spatiotemporal Visual-Action Consistency

  Wenda Yu, Tianshi Wang, Fengling Li, Xin Li, Jingjing Li, Lei Zhu · 3 de agosto de 2026

  Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the temporal alignment among visual observations, robot states, and executed actions. We introduce ActFovea, a plug-and-play safeguarding framework that d…

• LabEvolver: Training-Free Experience Evolution for Safe and Grounded Wet-Lab Agents

  Jingya Wang, Yuyang Gao, Liuzhenghao Lv, Yonghong Tian, Yuyang Liu · 3 de agosto de 2026

  We introduce LabEvolver, a training-free framework that equips safe and grounded wet-lab agents with episodic memory from execution experience. LabEvolver couples a state-grounded inner trial loop for adaptive perception, online planning, and safety validation with an outer evolution loop that disti…

• CLIFT: Turning Gemini Robotics On-Device into Humanoid Specialists via Non-Invasive Closed-Loop Iterative Fine-Tuning

  Yuxin Chen, Hari Srikanth, Nathan Jew, Menglin Wu, Pengcheng Wang, Junli Ren, Masayoshi Tomizuka, Peng Xu, Jinyu Xie, Thomas Tian · 3 de agosto de 2026

  While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-source, limiting downstream users' ability to adapt them to new tasks, embodiments, and deployment settings. Following the LLM community, an emerging acces…

• From Passive Video to Editable Experience: Physically Grounded Experience Synthesis for Embodied Intelligence

  Jia Luo · 30 de julio de 2026

  The key bottleneck in embodied AI is not model architecture but data. Although billions of human manipulation videos exist online, robots cannot directly learn from them due to the embodiment gap between human morphology and robot hardware. We introduce Pegasus, a low-resource framework that bridges…

• GBPP: Grasp-Aware Base Placement Prediction for Robots via Two-Stage Learning

  Jizhuo Chen, Diwen Liu, Jiaming Wang, Harold Soh · 30 de julio de 2026

  GBPP is a fast learning based scorer that selects a robot base pose for grasping from a single RGB-D snapshot. The method uses a two stage curriculum: (1) a simple distance-visibility rule auto-labels a large dataset at low cost; and (2) a smaller set of high fidelity simulation trials refines the m…

• SymmGrid: Super-Scaling On-Robot Learning with Parallelized Symmetries and Egocentric-Exocentric Visual Perception

  Gabe Everett, Brice Gunter, Ryan Vander Stelt, Cleiver Ruiz-Martinez, Blake Hull, Juan Rojas · 30 de julio de 2026

  Deep reinforcement policy learning directly in physical robots (on-robot learning) remains bottlenecked by slow wall-clock training times. We present SymmGrid, a trajectory level augmentation framework inspired by parallelized symmetries that super-scales group transformations to significantly accel…

• $\pi\mathbf{R}^2$: Reactive Real-time Flow Policies

  Sungjae Park, Shubham Tulsiani · 29 de julio de 2026

  Generalist manipulation policies increasingly take the form of action-chunking flow policies built on large pretrained backbones. Such chunks run open-loop, so the policy cannot react to sensory input arriving mid-execution, sacrificing \emph{reactivity}. Replanning more often would restore it, but …

• A context-adaptive policy framework for robust and reactive robotic manipulation via uncertainty-aware imitation learning

  Tim R. Winter, Leonard Kl\"upfel, Ashok M. Sundaram, Werner Friedl, Maximo A. Roa, Freek Stulp, Jo\~ao Silv\'erio · 29 de julio de 2026

  Generating robust and reactive manipulation strategies that can adapt to changing context information is a challenging task in robotics. Over the years, Learning from Demonstration (LfD) has emerged as an intuitive and effective solution for generating reactive policies, particularly by following dy…