Robot Manipulation and Learning

Últimos artículos

• DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

  Haoyuan Deng, Jiebin Liu, Tengxiao Zhang, Langning Yan, Hongye Cao, Ziwei Wang · 1 de octubre de 2026

  Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physical execution. Semantic reasoning operates at a coarser timescale than physical interaction, while episode-level failures provide limited guidance on …

• Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models

  Mingyue Cui, Zheyuan Liu, Yihan Zhu, Zheyuan Zhang, Meng Jiang · 1 de octubre de 2026

  Vision-language-action (VLA) models generalize broadly across robotic manipulation tasks, but complex environments require balancing task success with unintended contact. Runtime shields can correct individual actions, but they leave the underlying policy unchanged, so repeated disagreements may cre…

• RoboCoach: World Models as Active Coaches for Compositional Robot Skills

  Jiajun Liu, Yifan Chen, Yichao Liu, Jiayi Zhang, Ruoqu Chen, Shaoxuan Xie, Guocai Yao, Mengdi Xu, Sen Cui, Changshui Zhang · 1 de octubre de 2026

  Long-horizon robot manipulation reuses skills across many task compositions, but improving these compositions with additional end-to-end demonstrations is costly. A practical self-improving system must decide both what to teach next and where to apply that supervision. We present ROBOCOACH, a world-…

• Text-to-3D Policy: Fine-Grained Language-Behavior Alignment for Unseen Specification Generalization

  Xinhao Yang, Wenhao Wu, Ning Lv, Yanshen Ding, Zhenhong Sun, Daoyi Dong, Chunlin Chen, Zhi Wang · 1 de octubre de 2026

  3D visuomotor policies provide a strong foundation for spatially precise manipulation, yet current text-to-3D policies struggle to follow unseen fine-grained behavioral specifications beyond those covered by demonstrations. We study this challenge as unseen specification generalization, where langua…

• HiWE: Hierarchical World Knowledge Model with Visual Keypoint Enhancement for Zero-Shot 3D Path Planning

  Guoqing Ma, Mingqi Yuan, Chen Gao, Jiayu Chen, Shan Yu · 1 de octubre de 2026

  Robot demonstration generation requires a system to identify where an interaction should occur, plan a feasible motion, and execute the required contact. HiWE connects these decisions through a point-based interface between visual grounding and language-based planning. PointVLM is instruction-tuned …

• Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools

  Shijia Ge, Alex Zhou, Jianshu Zeng, Yexing Wan, Di Wu, Zelin Zheng, Yazhe Wang, Zhiqi Jia, Xuan Shangguan, Jay Zhu, Yijun Liu, Lingyu He, Sihang Wu, Xiao He, Hongcheng Gao · 1 de octubre de 2026

  Frontier models can control robots, but reasoning through every reach, grasp, and retreat makes manipulation slow and token-intensive. We revisit code as policy with a different division of labor: models build executable tools, code handles multi-phase motions, and models decide what to do next. We …

• SimEX: Simulation-Integrated Robotics AutoResearch

  Jiaheng Hu, Roberto Martin-Martin, Peter Stone, Rocky Duan, Zhenyu Jiang, Guanya Shi · 1 de octubre de 2026

  Coding agents powered by large language models (LLMs) have shown remarkable abilities to autonomously reason about and achieve goals in the digital world. However, bringing this success to the physical world remains challenging. On the one hand, direct generation methods (e.g., Code as Policies) oft…

• Online Evolution Strategy for Flow-Matching VLA Policies via Self-Supervised Trajectory Distribution Optimization

  Gongxin Yao, Yongsheng Zhao, Jiayin Deng, Deng Liang, Han Gao, Lei Zhao, Baoping Cheng · 1 de octubre de 2026

  Vision-Language-Action (VLA) models based on generative frameworks, such as Flow Matching, have recently achieved impressive performance in robotic manipulation. Unlike deterministic policies, Flow Matching enables VLA models to learn conditional action trajectory distributions, where latent noise v…

• F4R: Failure-Driven Recognition, Reconstruction, Refinement, and Redeployment for Continual Robot Self-Improvement

  Zhuoyuan Yu, Jiacheng Wang, Tianle Liu, Yihua Ren, Peng Yu, Chen Bai, Ziheng Zhang, Yufei Jia, Jindou Jia, Yuhang Zhang, Xinrui Zhang, Shang Yujing, Yuxiang Chen, Chuhao Zhou, Tiancai Wang, Jianfei Yang · 30 de septiembre de 2026

  The real-world performance of current vision-language-action models is fundamentally constrained by the limited coverage of expert demonstrations and their insufficient understanding of physical interactions. A common remedy is to collect additional real-world demonstrations of newly encountered fai…

• Don't Throw Away the Tail: Action Upcycling for Policy Acceleration

  Taesung Kwon, Jangho Park, Sunwoo Park, Youngmin Kim, Seonghyun Jin, Youngjun Jun, Kyumin Choi, Jong Chul Ye · 30 de septiembre de 2026

  Modern robot policies predict a chunk of future actions from a single observation, execute only a prefix, and discard the rest before replanning. Choosing the length of this prefix, the execution horizon, poses a trade-off between reactivity and efficiency. A short horizon keeps the policy reactive …

• PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball

  Lizhi Yang, Junheng Li, Aaron D. Ames · 30 de septiembre de 2026

  We present PAC-MAN, a perception-aware CBF-RL framework that couples control-barrier safety with deployment-realistic onboard sensing for whole-body humanoid dodgeball. The deployed policy sees the ball only as segmentation-masked depth from a head-mounted camera, while training-time CBF guidance re…

• Explore, Execute, Evolve: A Skill Acquisition and Reuse Loop for Embodied Agents

  Sicheng Xie, Yitong Chen, Haidong Cao, Shunlin Lu, Zuxuan Wu, Yu-Gang Jiang · 30 de septiembre de 2026

  Vision-language-action and world-action models have demonstrated impressive capabilities in robotics, yet generalization to unseen tasks remains challenging. More recently, general-purpose multimodal agents have shown great potential for zero-shot robotic task solving. However, they often incur high…

• Encore: Few-Shot Agentic Discovery of Manipulation Strategies

  Yifan Kang, Zihan Wang, Zhiwen Fan, Bangya Liu · 30 de septiembre de 2026

  Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified by a sentence that leaves out how to grasp, in what order to make contact, and what the result should look like, and an agent given only the sentence must find these details by tr…

• EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation

  Jin Chen, Yiming Jiang, Chongyang Xu, Modi Shi, Shijia Peng, Li Chen, Tianyu Li, Mu Xu, Yilun Chen, Steven Hoi, Hongyang Li · 30 de septiembre de 2026

  Human demonstrations capture diverse scenes and rich whole-body skills without requiring robot teleoperation. Prior work on egocentric transfer has emphasized scene generalization in loco-manipulation under decoupled control, leaving direct transfer of coordinated whole-body skills less explored. We…

• FACT: Fidelity-Aware Construction of Articulated Twins

  Kuixiang Shao, Chuansen Nie, Yinuo Bai, Jiayuan Gu, Jingyi Yu · 30 de septiembre de 2026

  Visually plausible articulated assets may still fail during contact interactions or exhibit inaccurate motion. We present FACT (Fidelity-Aware Construction of Articulated Twins), an agentic framework that progressively constructs articulated twins to improve geometry, contact, and dynamic fidelity. …

• AeroManip-VLA: Scalable Vision-Language-Action Learning for Aerial Manipulation with RL-Generated Demonstrations

  Rui Huang, Yanlin Mu, Lidong Li, Yucong Wang, Zichen Yan, Lin Zhao · 30 de septiembre de 2026

  Aerial manipulators extend robotic manipulation into 3D workspaces that are difficult for ground-based robots to access, creating new opportunities for general-purpose manipulation. However, extending Vision-Language-Action (VLA) models to aerial robots introduces distinct challenges due to the tigh…

• Simple Agentic Memory for Generalist Robot Policies

  Yuyou Zhang, Yunbei Zhang, Miao Li, Janet Wang, Zijian Jin, Shilong Liu, Ding Zhao · 30 de septiembre de 2026

  Visual-memory systems commonly retain or compress past observations. Robot control additionally requires interaction-derived state that no individual frame may explicitly represent, such as persistent identity relations, accumulated progress, or ordered procedures. We introduce Simple Agentic Robot …

• LIBERO-MAX: Do Robot Policies Adapt When the World Changes?

  Yunbei Zhang, Zijian Jin, Yuanzhe Liu, Janet Wang, Xilun Zhang, Yuyou Zhang, Zhenyu Zhang, Daoan Zhang, Shuaicheng Niu, Gen Li, Jianfei Yang, Jihun Hamm, Ismini Lourentzou, Weirui Ye, Bo Liu, Peter Stone, Marco Pavone · 30 de septiembre de 2026

  Robots must often continue a task after a target moves, the viewpoint shifts, or an obstacle appears, even though their earlier observations and committed actions reflect the previous scene. Many simulation robustness benchmarks fix external conditions at reset, leaving this temporal challenge under…

• Staircase Policy: Streaming Inference for World-Action Models with Large Action Chunks

  Guoheng Sun, Chen Chen, Jin Wang, Ang Li, Teresa Lv · 30 de septiembre de 2026

  World-Action Models (WAMs) improve robotic manipulation by conditioning action generation on predicted future observations, but future prediction adds further inference overhead to already expensive iterative action generation. Action chunking can amortize this cost over multiple actions, yet perfor…

• FineART: Fine-grained Annotated Robotic Trajectory Dataset and Vision-Language-Action Model for Bimanual Manipulation

  Jade Choghari, Pepijn Kooijmans, Mansi Agarwal, Yusuf Umut Ciftci, Aseem Doriwala, Catherine Weaver, Mouli Sivapurapu, Kai Yang, Jackson Lee, Thomas Wolf, Pragna Mannam · 30 de septiembre de 2026

  Robots operating in real-world environments must execute complex, multi-step bimanual tasks over long horizons rather than single, isolated actions. Current manipulation datasets struggle to support this capability: although single-arm datasets reach hundreds of thousands of trajectories, they typic…

• Direct Experience World-Model Optimization: Learning the World Beyond Action Imitation

  Xiangcheng Zhan, Zirui Chen, Yicheng Zhao, Ziteng Gao, Shuo Yang · 30 de septiembre de 2026

  World-Action Models (WAMs) couple action generation with predictions of how physical interactions unfold. However, current post-deployment learning paradigms typically improve behavior without requiring better world predictions. Especially in dexterous manipulation, small execution errors can compou…

• WAM-OPD: Sharpening World Action Models via On-Policy Distillation

  Panjun Liu, Xiaohan Lei, Shiqi Zhang, Yikun Wang, Yongxin Zhang, Mingyi Hu, Shida Sun, Jiateng Shou, Wengang Zhou, Jiajun Deng, Zhiwei Xiong · 29 de septiembre de 2026

  Pretrained world action models (WAMs) provide generalist capabilities across diverse robotic manipulation tasks, yet improving target-task performance to an expert level without degrading pretrained skills remains challenging. We explore on-policy distillation (OPD) for WAMs and introduce WAM-OPD. W…

• Robot-GST: geometry-aware spatial-temporal robot policy representation and evaluation

  Sichao Liu, Zekun Wang, Lixuan Tang, Yiming Li, Xiaohan Wang, Hanzhi Zhang, Daqiang Guo, Peng Zhou, Lihui Wang · 29 de septiembre de 2026

  Robotic manipulation policies are advancing rapidly with increasing reliance on vision-language models for end-to-end decision making. However, reliable deployment remains challenging because many policies lack explicit mechanisms for predicting task outcomes and evaluating whether generated actions…

• Achieve What You Imagined: Learning to Align Actions with Visual Plans

  Yuheng Qiao, Ziran Wei, Xiaohan Wang, Daqiang Guo, Yichen Luo, Zhibo Pang, Peng Zhou, Sichao Liu · 29 de septiembre de 2026

  World-action models can jointly predict future visual observations and robot actions. However, discrepancies may exist between their visual predictions and the consequences implied by generated actions. We observe that WAMs can often generate visually plausible task-completion outcomes before produc…

• CodeActionBench: Evaluating Agentic Code-as-Policy for Embodied Manipulation

  Yiheng Lyu, Xueying Jiang, Wenhao Li, Shijian Lu, Gongjie Zhang · 29 de septiembre de 2026

  How well can general-purpose multimodal models turn visual understanding and reasoning into embodied manipulation via executable code? We introduce CodeActionBench, a benchmark of 25 manipulation tasks that evaluates this capability through agentic Code-as-Policy. Without task-specific fine-tuning, …