cs.RO · 2026-10-17 · No. 146

Robotics, 2026-10-17.

10 new papers in cs.RO. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

10 entries
  1. 01

    LIBERO-PeRM: Benchmarking Personalized Robotic Manipulation

    Zhixu Li, Keqian Tang, Litian Gong, Jingyu Yao, Wenqian Zhang, Tianze Xu, Zehao Wang, Yuping Wang, Junge Zhang, Jiachen Li

    cs.RO · cs.AI · cs.LG

    Personalization is essential for general-purpose robots to transition into household environments and achieve true practicality. While general robotic manipulation has been extensively studied, personalized robotic manipulation (PeRM) lacks a controlled benchmark for separating task completion from preference satisfaction. We introduce LIBERO-PeRM, a benchmark for preference learning in embodied agents. LIBERO-PeRM studies five questions: 1)...

    arxiv.org/abs/2610.22372 · PDF

  2. 02

    T2-z: Test-Time Optimization of Environment Latents for Robotic World Models

    Chenyuan Zhou, Yining Hong, Huang Huang, Yunfan Jiang, Wenlong Huang, David Held, Vitor Campagnolo Guizilini, Yue...

    cs.RO · cs.AI · cs.CV

    Predicting how the world responds to an action requires more than what can be seen: robots must account for environmental factors that are neither directly observable nor explicitly specified, from physical properties such as friction and mass to human-defined environmental rules. We introduce T2-Z for test-time optimization of environment latents, which augments a robotic world model with a learnable environment latent to condition world...

    arxiv.org/abs/2610.22364 · PDF

  3. 03

    CoDA: Co-Evolution of Data Engines and Action Policies

    Tianjiao Yu, Zhilin Ou, Yifan Shen, Xinzhuo Li, Yuanzhe Liu, Onkar Kishor Susladkar, Fan Wang, Ismini Lourentzou

    cs.RO · cs.AI

    Generative simulation can automate robot environment construction, but physically valid environments are not necessarily useful for training. The challenge is to identify environments that address a policy's failures and supervision that helps it overcome them. We introduce CoDA, a framework in which a simulation data engine and an action policy co-evolve through a shared heterogeneous memory of environment construction, policy failures, and...

    arxiv.org/abs/2610.22362 · PDF

  4. 04

    Dexterity from Supervised Play

    Botao He, Yiming Dou, Yiannis Aloimonos, Jitendra Malik, Akash Sharma, Ruoshi Liu

    cs.RO · cs.AI

    How can robots autonomously collect the contact-rich experience needed to learn dexterous manipulation? We present DSP: Dexterity from supervised play, a framework in which a robot learns a play policy from minutes of human play through behavior cloning, then deploys it autonomously to collect hours of interaction data to train a world model. During inference, the same play policy then guides model-predictive control (MPC) by proposing...

    arxiv.org/abs/2610.22340 · PDF

  5. 05

    Asking Smarter Questions: Targeted Active Preference Learning for Underspecified Rewards

    Helena Merker, Nick Walker, Andreea Bobu

    cs.RO · cs.AI · cs.HC · cs.LG

    Reward learning typically assumes the human's input covers everything that matters for the task. In practice, humans can only attend to so much at once, so their teaching naturally captures some features---or aspects of the task---better than others. Prior work has shown how the robot can identify which features were poorly supervised directly from its teaching data. But the current solution is to ask the human to try again, putting the...

    arxiv.org/abs/2610.22285 · PDF

  6. 06

    Whole-Body Dexterity

    Conor Mc Gartoll, An Dang, Pranay Thangeda, Arjun Gupta, Carolina Higuera, Nima Fazeli, Mustafa Mukadam, Manikantan Nambi

    cs.RO · cs.AI · cs.LG · eess.SY

    Current humanoid dexterous manipulation remains largely confined to end-effectors and simple grasps, falling short of humans' ability to engage the entire body by bracing and sliding bulky objects against the arms and torso. We introduce Whole-Body Dexterity (WBD), a general framework that uses the robot's body and appendages as contact surfaces to grasp and manipulate objects. Our sim-to-real pipeline first generates a dataset of feasible...

    arxiv.org/abs/2610.22184 · PDF

  7. 07

    REKI: Registering Knowledge in VLAs

    Juliette Marrie, Paul Pacaud, Adrien Ramanana Rahary, Shizhe Chen, Moritz Böhle

    cs.RO · cs.CV · cs.LG

    We introduce REKI, a 2.4B vision-language-action model (VLA) pretrained exclusively on public data that sets a new Pareto frontier between performance and model size: on LIBERO-Plus, RoboTwin Clean2Rand and RoboCasa365, it is outperformed only by models about twice its size. REKI consists of a vision-language model (VLM) followed by a flow-matching action expert, and is pretrained on a curated mixture of public robot, egocentric human and...

    arxiv.org/abs/2610.22178 · PDF

  8. 08

    DemoStream: Batched Task-and-Motion-Plan Optimization for Automated Learning from Demonstration

    Caelan Garrett, Neel Jawale, Fabio Ramos

    cs.RO · cs.AI · cs.LG

    Learning from demonstration is an effective strategy for endowing robots with manipulation capabilities but requires training on datasets comprised of massive amounts of demonstrations. Existing demonstration collection approaches either require constant human involvement, for example, via teleoperation or are specialized for a single task. Task and Motion Planning (TAMP) systems are able to autonomously solve and therefore generate...

    arxiv.org/abs/2610.22020 · PDF

  9. 09

    Cross-Embodiment Causal Transfer from Human Videos to Robot Manipulation

    Xingyu Zhang, Yingchao Li, Peizheng Guo, Jie Hu, Changwen Zheng, Wenwen Qiang

    cs.RO · cs.AI

    Scaling robot manipulation models requires large amounts of interaction data, yet collecting diverse real-robot experience remains costly. Human manipulation videos, in contrast, provide abundant and diverse task experience that could potentially benefit robot learning. However, differences in morphology, action spaces, and control mechanisms make human motions unsuitable as direct supervision for robot actions, raising a scientific question:...

    arxiv.org/abs/2610.21798 · PDF

  10. 10

    AVALON: Zero-Shot Indoor Navigation with Human-Seeded Topological Memory

    Jing Xia, Changyan Li, Yuduo Wang, Guiyin Tian, Bo Wang, Yifan Liao, Mingjun Li, Shiyan Hu

    cs.RO · cs.AI

    Indoor service robots often enter unmapped buildings whose layouts and task constraints are already familiar to users. We address this human-familiar, robot-unseen setting with AVALON, a topological navigation framework organized around human-seeded layered spatial memory, node-verified topological execution, and task-triggered, evidence-gated human--robot memory co-updating. The robot has no prior on-site traversal or site-specific training....

    arxiv.org/abs/2610.21586 · PDF

This edition is part of The Daily Abstract — cs.RO archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.