cs.RO · 2026-09-22 · No. 121

Robotics, 2026-09-22.

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

01 — The papers

14 entries
  1. 01

    DexTacWAM: A Visuo-Tactile World-Action Model for Dexterous Manipulation

    Haoran Yuan, Zekai Wang, Boning Shao, Haoran Lu, Trevor Darrell, Ismini Lourentzou, Wei Zhan

    cs.RO · cs.AI · cs.CV

    Dexterous manipulation depends on contact dynamics that are often only partially observable from vision. Recent World-Action Models (WAMs) couple predictive video world modeling with action generation, but remain largely vision-centric and therefore cannot directly model these contact dynamics. We present DexTacWAM, a visuo-tactile WAM that encodes each fingertip independently, aggregates the resulting features through a finger- and...

    arxiv.org/abs/2609.24976 · PDF

  2. 02

    Visuomotor Robotic Pruning in Planar Orchards Using Hybrid Reinforcement Learning

    Abhinav Jain, Cindy Grimm, Stefan Lee

    cs.RO · cs.AI

    Dormant tree pruning is labor-intensive yet essential for maintaining modern high-productivity fruit orchards. In this work, we focus on pruning of modern planar tree training systems - V-Trellis apples and UFO cherries - where trunks and primary branches are trained into approximately planar walls. We introduce an end-to-end pipeline to learn a closed-loop visuomotor controller for robotic pruning. This controller is trained entirely using...

    arxiv.org/abs/2609.24906 · PDF

  3. 03

    SE(3) Neural Potential Fields for 6-DoF Trajectory Planning Directly from Images Without Explicit 3D Reconstruction

    Jeffrey Eiyike, Masoud Ataei, Elvis Gyaase, Vikas Dhiman

    cs.RO · cs.AI

    Reaching a 6-DoF grasp pose in clutter requires a collision-free trajectory, conventionally obtained by reconstructing the scene in 3D and planning inside that reconstruction, at the cost of its accuracy and compute. Potential fields learned directly from images remove that dependency but inherit the classical weakness of artificial potential fields: where attractive and repulsive gradients cancel, the descent grazes the obstacle instead of...

    arxiv.org/abs/2609.24864 · PDF

  4. 04

    PredActor: Predictive Action Diffusion for Steerable Onboard Humanoid Control

    Lei Ye, Haibo Gao, Yitang Li, Peng Xu, Zetong Jing, Junhan Sun, Fanrong Dong, Ziqi Han, Xue Wang, Jianhua Sun, Cewu...

    cs.RO · cs.LG

    Diffusion models offer flexible motion generation, but translating this flexibility into feedback-responsive humanoid control remains challenging. Hierarchical systems steer motion through references that may exceed a separate tracker's capabilities, leaving recovery and physical execution largely to the tracker. Action-only diffusion generates actions directly but lacks an explicit future-state trajectory for test-time motion objectives....

    arxiv.org/abs/2609.24840 · PDF

  5. 05

    Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI

    Wenkang Qin, Yukun Zhou, Noah Shen, Jisong Cai, Dongxiao Mao, Baicheng Li, Yue Zhang, Wei Sui

    cs.RO · cs.AI

    Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional simulators require labor-intensive construction. We present Uranus, a data-driven robot simulator built around a joint-trajectory-conditioned autoregressive diffusion model. Uranus offers three key capabilities: (1) streaming, open-ended rollout, which receives future joint-position...

    arxiv.org/abs/2609.24815 · PDF

  6. 06

    D-JEPA: A Decision-Aligned Latent World Model

    Shuaijun Liu, Chengyu Wu, Qifu Wen, Feiyang You, Chenglong Zhang, Shuyang Hao, Xi Lin, Ningxin Su

    cs.RO · cs.LG

    Latent world models predict the consequences of actions, but accurate prediction does not guarantee that latent distance reflects which candidate will execute successfully. We identify a decision-local prediction gap: among the few futures competing for execution, a candidate predicted closer to the goal can produce a worse realized outcome than an available alternative. We introduce D-JEPA, a decision-aligned latent world model that learns...

    arxiv.org/abs/2609.24749 · PDF

  7. 07

    LLM-based Conversational AI Knowledge Assistant for MyBuddy Humanoid Robot

    Hanxiao Chen

    cs.RO · cs.AI

    Humanoid robots are increasingly being popular and developed for human-centered applications, yet their ability to provide intelligent conversations and natural interactive knowledge assistance remains constrained by traditional rule-based dialogue systems, pre-defined responses and limited knowledge repositories. Large language models (LLMs) have emerged as a powerful foundation for enabling natural, adaptive, and context-aware Human-Robot...

    arxiv.org/abs/2609.24742 · PDF

  8. 08

    Touch2Robot: Robot Touch in the Human Demonstration Loop

    Shengcheng Luo, Xiaoyang Cheng, Hong Ying, Xiaoying Zhou, Jiaming Jiang, Haoran Guo, Wanlin Li, Ziyuan Jiao, Chenxi Xiao

    cs.RO · cs.AI

    Human demonstrations offer a scalable way to collect manipulation data, but their contacts may be unstable or infeasible when transferred to a robot hand. Collecting demonstrations directly on the target robot avoids this mismatch, but substantially increases the cost of data collection. To address this trade-off, we present \textbf{Touch2Robot}, a framework that lets humans collect demonstrations while seeing how the target robot hand would...

    arxiv.org/abs/2609.24660 · PDF

  9. 09

    From Semantic Decisions to Feasible Trajectories: Self-Evolving LLM-Guided Optimal Control for Narrow-Space Parking

    Zhengbao Yao, Yuanfu Luo, Kehan Xue

    cs.RO · cs.AI

    Autonomous parking in nonconvex and narrow environments remains challenging. Although optimal-control methods can explicitly enforce vehicle dynamics and collision constraints, nonconvexity compromises solver robustness and can cause failures. Large language models (LLMs) exhibit strong semantic reasoning capabilities, but directly generating dense trajectories makes it difficult to guarantee physical feasibility. We introduce SE-LLM-OCP, a...

    arxiv.org/abs/2609.24631 · PDF

  10. 10

    Learning tactile perception from high-bandwidth single-point sensing

    Joseph Rigal, Emmanuel Virot, Caroline Pascal

    cs.RO · cs.LG

    Tactile sensing is increasingly being incorporated into learning-based robotic manipulation, yet many existing approaches rely on spatially distributed sensors. Here we introduce SpectRobot, a framework that transforms single-point tactile signals into compact time-frequency spectrograms. These spectrograms encode high-bandwidth tactile histories as fixed-size image-like representations. They can be processed by standard vision encoders and...

    arxiv.org/abs/2609.24621 · PDF

  11. 11

    FoldQuantVLA: Native Low-Bit Quantization of Vision-Language-Action Models via Consistent Folding

    Hung T. Ho, Khanh D. Nguyen, Quang D. Nguyen, Thanh Q. Duong, Ngan Le, Meng Guo, Vien A. Ngo, An T. Le

    cs.RO · cs.AI · eess.SY

    Low-bit vision-language-action inference must reduce observation-to-action latency while preserving robot behavior. We present FoldQuantVLA, a post-training quantization framework that carries a consistent activation representation through calibration, weight rounding, and native integer execution. It combines channel scaling and block Hadamard transforms with dynamic per-token quantization, without policy retraining. Custom TensorRT plugins...

    arxiv.org/abs/2609.24433 · PDF

  12. 12

    Tactile-JEPA: Topology-Aware Self-Supervised Representation Learning for Distributed Tactile Sensors

    Elizaveta Kovtun, Matvey Konovalov, Andrey Sakhovskiy, Semen Budennyy

    cs.RO · cs.AI

    Tactile sensing is an essential modality for robots performing contact-rich, dexterous manipulation, particularly under visual occlusion. While pre-trained image encoders are standard in robot learning pipelines, tactile encoders are still commonly trained from scratch from raw, noisy signals, which might limit their expressivity. Existing self-supervised learning (SSL) approaches focus predominantly on vision-based tactile sensors, leaving...

    arxiv.org/abs/2609.24385 · PDF

  13. 13

    vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation

    Khanh D. Nguyen, Hoang M. Truong, An T. Le

    cs.RO · cs.AI · eess.SY

    Deploying language-conditioned manipulation without a dedicated GPU requires efficient inference and action chunks that cover the delay between policy queries. We present vla.simd, a CPU inference engine that combines shared SIMD micro-kernels, reusable computation, and target-specific optimization. We relate query latency and execution horizon to action availability under lagged and time-aligned execution, distinguishing action supply from...

    arxiv.org/abs/2609.24274 · PDF

  14. 14

    ActiveArena: Benchmarking and Understanding Active Perception in Robotic Manipulation

    Yibo Li, Enshen Zhou, Rui Chen, Yanjun Ding, Mengzhen Liu, Yi Han, Jiabo Zhan, Lipeng Wang, Shanghang Zhang, Lu Sheng

    cs.RO · cs.AI

    Active perception and manipulation are crucial for robots to interact with complex scenes. Existing benchmarks struggle to evaluate how robots effectively acquire and maintain information in memory in an active manner. To this end, we introduce ActiveArena-Sim, an active-perception simulator with controllable viewpoints and large-scale workspaces as the foundation. Built on this, we propose ActiveArena-Bench, which comprises 35 tasks across 5...

    arxiv.org/abs/2609.24124 · 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.