cs.RO · 2026-06-30 · No. 39
Robotics, 2026-06-30.
9 new papers in cs.RO. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
9 entries-
01
VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes
Yen-Jen Wang, Jiaman Li, Sirui Chen, Takara E. Truong, Pei Xu, Pieter Abbeel, Rocky Duan, Koushil Sreenath, Angjoo...
cs.RO · cs.AI · cs.GR · eess.SY
Perception-based humanoid loco-manipulation requires connecting egocentric observations and task instructions to whole-body motion. Learning this mapping requires synchronized egocentric images, language commands, and robot-compatible kinematic trajectories, yet no existing data source provides this complete tuple at scale. We address this bottleneck by generating vision-language-kinematics (VLK) supervision synthetically in reconstructed...
-
02
GROW$^2$: Grounding Which and Where for Robot Tool Use
Yuhong Deng, Yuyao Liu, David Hsu
cs.RO · cs.AI · cs.CV
Can the robot use a plate to cut a cake if no knife is available? Tool use greatly expands robot capabilities, but to use tools creatively beyond their intended functions, the robot faces the challenge of $\textit{open-world affordance grounding}$: select an open-category object to act as a tool and localize its specific region of action. To this end, we introduce GROW$^2$ (GROunding Which and Where), which leverages object parts as a natural...
-
03
Learning from Mistakes: Rollout-Retrieval Lifelong Policy Learning for Autonomous Driving
Cheng Gong, Haoyang Wang, Chao Lu, Zirui Li, Jianwei Gong
cs.RO · cs.AI · cs.CV · cs.LG
Autonomous driving policies should be able to improve continually as deployment exposes them to increasingly diverse and long-tail traffic situations. However, most learning-based policies are trained or fine-tuned on expert demonstrations and then rely largely on generalization to handle challenging closed-loop scenarios, lacking an explicit mechanism to correct and retain the mistakes exposed in these scenarios. This paper studies...
-
04
ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control
Xiao Chen, Weishuai Zeng, Xiaojie Niu, Zirui Wang, Jianan Li, Huayi Wang, Furui Xu, Jiahe Chen, Weixiang Zhong, Lihe...
cs.RO · cs.AI · cs.CV
While current Behavior Foundation Models (BFMs) provide robust control priors for humanoids, they only execute pre-defined reference motions. As a result, they are vulnerable to environmental shifts and incapable of reactive whole-body coordination. Naively cascading them with generative motion planners fails to achieve true reactivity, as inevitable tracking discrepancies induce fatal cumulative exposure bias. To bridge this gap, we propose...
-
05
SA-VLA: State-aware tokenizer for improving Vision-Language-Action Models' performance
Tengyue Jiang, Chunpu Xu, Jiayue Kang, Yao Mu
cs.RO · cs.AI
Discrete action tokenization provides a compact interface for autoregressive VLA policies, but accurately recovering continuous robot actions from discrete codes remains challenging. Existing tokenizers typically map each discrete code to a fixed continuous action prototype, ignoring the robot's current proprioceptive state. This limitation is particularly pronounced in manipulation, where the same action token may require different...
-
06
Automating the Design of Embodied AgentArchitectures
Jian Zhou, Sihao Lin, Jin Li, Shuai Fu, Gengze Zhou, Qi Wu
cs.RO · cs.AI · cs.LG
Embodied agents are typically built as hand-designed compositions of perception, memory, planning, and action modules. This modularity exposes a large architectural design space, but current systems still rely on researcher intuition to choose where information is stored, how observations are processed, and how model calls are connected. Agent Architecture Search (AAS) automates such design for text-domain agents, but has not been...
-
07
Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigation
Hong Chen, Daqi Liu, Zehan Zhang, Haiguang Wang, Tianhao Lu, Longfei Yan, Haiyang Sun, Fangzhen Li, Hongwei Xie,...
cs.RO · cs.AI
Existing world model-based planners for visual navigation typically follow a verification-centric paradigm, decoupling goal intent from trajectory synthesis. This approach suffers from candidate dependence, heavy computational overhead, and inconsistencies between sampled actions and predicted visuals. To address these issues, we propose SWAM (Spatial-perceiving World Action Model), a task-centric joint observation-action generation...
-
08
Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies
Haoxu Huang, Tongsam Zheng, Yifan Chen, Jiacheng You, Yang Gao
cs.RO · cs.AI
Real-world evaluation is the gold standard for robot policies because it tests them against the physical conditions and deployment challenges they are ultimately designed to handle. However, real-world evaluation is also the bottleneck for iterating on robot policies: it is costly, difficult to reproduce, and often too sparse to reliably compare nearby model variants. A straightforward proxy for performance is validation loss on expert...
-
09
Trust Your Instincts: Confidence-Driven Test-Time RL for Vision-Language-Action Models
Siyao Chen, Jiakang Yuan, Jiaxin Wang, Tao Chen
cs.RO · cs.AI
Reinforcement learning (RL) has become indispensable for pushing Vision-Language-Action Models (VLAs) beyond static imitation learning. However, existing RL methods typically require external environmental feedback, relying on predefined success signals to guide policy updates. In this work, we show that VLA models possess useful internal evaluative capabilities: in discrete-action VLAs, trajectories with higher generation confidence are...
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.