cs.RO · 2026-07-21 · No. 60
Robotics, 2026-07-21.
8 new papers in cs.RO. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
8 entries-
01
Patch Policy: Efficient Embodied Control via Dense Visual Representations
Gaoyue Zhou, Zichen Jeff Cui, Ada Langford, Bowen Tan, Yann LeCun, Lerrel Pinto
cs.RO · cs.LG
Pretrained dense visual features from Vision Transformers (ViTs) are powerful yet have been underutilized in robot learning. Modern robot policies either compress each observation into a single global token, or rely on visual backbones trained from scratch, sacrificing both fine-grained spatial detail and the benefits of large-scale visual pre-training. While there exist policies that do operate on dense patch features like large...
-
02
Learning Adaptive Safety Margins for Visual Navigation
Junyi Hu, Shuaihang Yuan, Geeta Chandra Raju Bethala, Anthony Tzes, Yi Fang
cs.RO · cs.AI
Robots in cluttered indoor spaces often fail not because they cannot generate collision-free paths, but because a fixed safety margin is mis-calibrated: conservative margins cause detours and timeouts, while permissive margins lead to near-boundary shortcuts under perception bias. Diffusion-based planners propose diverse trajectory candidates from egocentric RGB-D, yet reliable selection remains the bottleneck. We propose a...
-
03
ConceptTree: Bringing Semantic Transparency to Black-Box Decision Making for Robotic Manipulation
Yongyan Wen, Feifan Liu, Jinyi Chen, Bo An, Peng Liu, Siyuan Li
cs.RO · cs.AI
Establishing interpretable decision-making processes in long-horizon robotic manipulation is critical for enabling reliable human oversight and intervention. However, existing approaches to robotic manipulation largely treat skill selection as opaque mappings from observations to actions, offering limited transparency into how decisions are formed. In this work, we propose ConceptTree, a framework that reframes high-level manipulation skill...
-
04
Reasoning as a Double-Edged Sword: Architecture and Cross-Stage Robustness in Vision-Language-Action Models
Tuan Duong Trinh, Naveed Akhtar, Basim Azam
cs.RO · cs.AI · cs.CR · cs.LG
Does adding a reasoning step make a Vision-Language-Action (VLA) model more robust to perturbation? Intuitively, a policy that reasons before acting should absorb a perturbed input better than one that maps observations directly to actions. We test this premise head-on across three models that span the reasoning spectrum (no reasoning, a text chain-of-thought, and a latent iterative loop), perturbing each at the vision, reasoning, and action...
-
05
Seg2Grasp: A Robust Modular Suction Grasping in Bin Picking
Hye-Jung Yoon, Juno Kim, Yesol Park, Jun-Ki Lee, Byoung-Tak Zhang
cs.RO · cs.AI
Current bin picking methods that rely heavily on end-to-end learning often falter when confronted with unfamiliar or complex objects in unstructured environments. To overcome these limitations, we introduce Seg2Grasp, a modular pipeline designed for robust suction grasping in dynamic and cluttered bin scenarios. Seg2Grasp is built on a three-step process: Segmentation, Grasping, and Classification. The Segmentation module employs a...
-
06
Lifelong Multi-Subsystem Pickup and Delivery with Buffer-Limited Handover Stations
Chuanlong Zang, Isabelle Barz, Anna Mannucci, Philipp Schillinger, Florian Lier, Wolfgang Hönig
cs.RO · cs.AI · cs.MA
Coordinating payload transfers between subsystems is a critical challenge in lifelong Multi-Agent Pickup and Delivery (MAPD). We study systems where agents are confined to separate regions and must exchange payloads through shared handover stations. These stations, equipped with single docks and finite buffers, are inherently vulnerable to blocking and starvation. We formalize this problem as Multi-Subsystem MAPD with Buffer-limited Handover...
-
07
Predictive Training with Latent Imagination for Visual Quadruped Navigation
Yancheng Zhu, Wanli Ma, Chen Han, Irvin Haozhe Zhan, Bingfeng Qin, Yixin Xu
cs.RO · cs.AI
Reinforcement-learning navigation policies for legged robots select actions reactively from current observations and short-term memory, with limited capacity to anticipate how moving obstacles will evolve in the near future. In dynamic environments, this reactivity causes the robot to respond too late because collision risk depends on short-horizon scene structure rather than on current obstacle positions alone. Lightweight predictive...
-
08
COLIP-2: Olfaction-Vision-Language Embeddings
Kordel Kade France
cs.RO · cs.AI · cs.ET · cs.LG
The Contrastive Olfaction-Language-Image Pre-training 2 (COLIP-2) model is a multimodal embeddings space that places olfaction as a first-class citizen among vision and language. Molecular structure, gas-sensor readings, odor-descriptor language, and images are all trained into a single shared representation space, so that a robot can localize a detected aroma to objects in a scene probabilistically. No ImageNet-scale datasets of paired...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.