cs.RO · 2026-06-29 · No. 38

Robotics, 2026-06-29.

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

01 — The papers

7 entries
  1. 01

    DexCompose: Reusing Dexterous Policies for Multi-Task Manipulation with a Single Hand

    Dihong Huang, Zhenyu Wei, Zhuxiu Xu, Yunchao Yao, Sikai Li, Mingyu Ding

    cs.RO · cs.AI · cs.CV · cs.LG

    Dexterous manipulation policies can solve individual skills, but composing them to perform multiple tasks with a single hand remains challenging. Adding a new task on top of an existing manipulation skill often imposes conflicting demands on overlapping fingers and contact modes, causing destructive interference between preserving an existing manipulation outcome and executing a new one. We propose DexCompose, a role-aware residual...

    arxiv.org/abs/2606.28323 · PDF

  2. 02

    S$^2$-VLA: State-Space Guided Vision-Language-Action Models for Long-Horizon Manipulation

    Zhipeng Xie, Zongyi Han, Xiangyi Wei, Shiliang Sun, Yang Li, Jing Zhao

    cs.RO · cs.AI

    Vision-Language-Action (VLA) models have demonstrated strong capabilities in robotic manipulation, but their performance degrades significantly in long-horizon tasks due to cumulative error propagation. This limitation largely arises from static feature fusion mechanisms that rely on fixed weights to combine visual, language, and action representations, preventing the model from adapting to different phases of task execution. To address this...

    arxiv.org/abs/2606.27872 · PDF

  3. 03

    Drop-Then-Recovery: How Redundant Are Vision-Language-Action Models?

    Guoheng Sun, Kaixi Feng, Shwai He, Xiaochuan Gong, Yexiao He, Ziyao Wang, Zheyu Shen, Wanghao Ye, Ramana Rao...

    cs.RO · cs.AI

    Vision-Language-Action (VLA) models enable instruction-driven robotic manipulation, but they inherit oversized language backbones from pretrained VLMs whose capacity far exceeds what is needed for short robotic instructions. This raises a basic question: how much of a VLA model is actually necessary for closed-loop control? In this work, we study architectural redundancy in VLA models by using transformer block removal as a controlled...

    arxiv.org/abs/2606.27755 · PDF

  4. 04

    P-ARC: Exploiting Subproblem Independence for Parallel Multi-Robot Motion Planning

    James D. Motes, Marco Morales, Nancy M. Amato

    cs.RO · cs.DC

    This paper presents Parallel ARC (P-ARC), a parallel variant of the Adaptive Robot Coordination (ARC) approach to multi-robot motion planning (MRMP). P-ARC proposes a parallel variant for each of the three main stages in ARC: initial individual solutions, conflict detection, and conflict resolution, exploiting the independence created by ARC's decomposition of the MRMP problem. Additionally, we employ an OR-parallel multi-start strategy to...

    arxiv.org/abs/2606.27625 · PDF

  5. 05

    Physics-Guided Robotic Radiation Source Localization along Arbitrary Measurement Paths in Unstructured Environments

    Hojoon Son, Kai Tan, Fan Zhang

    cs.RO · cs.LG

    Using robots to estimate the location of the radiation source is an effective way to improve efficiency and safety. Existing methods focus on planning the robot's path to achieve precise estimation, typically approaching the source. However, approaching the source increases the risk of radiation damage to a robot. In addition, a path-planning algorithm designed solely for radiation source localization (RSL) limits the flexibility of missions...

    arxiv.org/abs/2606.27624 · PDF

  6. 06

    SceneBot: Contact-Prompted General Humanoid Whole Body Tracking with Scene-Interaction

    Sirui Chen, Shibo Zhao, Zhen Wu, Jiaman Li, Guanya Shi, C. Karen Liu

    cs.RO · cs.AI

    Current humanoid reinforcement-learning policies excel at free-space motions but struggle with contact-rich tasks, as pure kinematic tracking cannot resolve the physical ambiguities of interacting with objects and uneven terrain. To address this, we introduce SceneBot, a unified motion-tracking framework capable of handling freespace locomotion, terrain traversal, and whole-body manipulation. SceneBot conditions a single policy on both...

    arxiv.org/abs/2606.27581 · PDF

  7. 07

    Support-Constrained RL Enables Real-World Policy Improvement without Real-World Experience

    Raymond Yu, William Huey, Mustafa Mukadam, Anusha Nagabandi, Abhishek Gupta

    cs.RO · cs.LG

    Robots trained on real world data tend to be imprecise, slow, and brittle to perturbations. Improving these policies with reinforcement learning (RL) is an appealing alternative, but this process often requires expensive training in the real world. Performing policy improvement in simulation instead provides a far cheaper alternative, but unconstrained RL in simulation can exploit contact and dynamics mismatches, resulting in unsafe behaviors...

    arxiv.org/abs/2606.27475 · 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.