cs.RO · 2026-06-16 · No. 25
Robotics, 2026-06-16.
11 new papers in cs.RO. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
11 entries-
01
Geometric Action Model for Robot Policy Learning
Jisang Han, Seonghu Jeon, Jaewoo Jung, René Zurbrügg, Honggyu An, Tifanny Portela, Marco Hutter, Marc Pollefeys,...
cs.RO · cs.CV · cs.LG
Generalist robot policies must follow user instructions while reasoning about how objects, cameras, and robot actions interact in the 3D physical world. Recent vision-language-action models (VLAs) and video world-action models (WAMs) inherit strong semantic or temporal priors from large-scale foundation models, but they still operate primarily on 2D image frames or 2D-derived latent spaces, leaving implicit the 3D geometry required for...
-
02
Hierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode Outcomes
Tongyan Fang, Siyuan Huang, Naiyu Fang, Ganlong Zhao, Zhongjin Luo, Jianbo Liu, Xiaogang Wang, Ying Dong, Hongsheng Li
cs.RO · cs.LG
When pretrained VLA policies are fine-tuned through online RL, each rollout episode produces only a single binary outcome (success or failure), yet the actor update requires per-transition supervision. Existing approaches commonly reduce this sparse outcome to a single scalar reward or advantage signal, which conflates distinct forms of transition-level feedback and provides limited guidance once basic task success becomes achievable. First,...
-
03
ROVE: Unlocking Human Interventions for Humanoid Manipulation via Reinforcement Learning
Wei Xiao, Weiliang Tang, Yuying Ge, Hui Zhou, Yao Mu, Li Zhang, Yixiao Ge
cs.RO · cs.LG
Human interventions provide crucial corrective signals for post-training Vision-Language-Action (VLA) models. However, enabling seamless humanoid interventions is a formidable systems challenge due to complex whole-body kinematics and dexterous-hand control. Consequently, the collected intervention trajectories are often suboptimal, and methods that rely on human interventions as expert supervision can absorb hesitant, inefficient, or even...
-
04
Task-Error Residual Learning for Real-Robot Five-Ball Juggling
Kai Ploeger, Jan Peters
cs.RO · cs.LG · eess.SY
For residual learning that refines existing behavior, sample efficiency depends on two things: how much information each rollout returns, and how efficiently the learner uses that information. Reinforcement learning's standard scalar reward carries far less information than the directional task error that defines the task. Random exploration further discards whatever information each rollout returns. Through residual learning with directional...
-
05
CrossMaps: Confidence-Aware Open-Vocabulary Semantic Mapping for Rover Navigation
Jan-Niklas Klein, Sona Ghahremani, Christian Medeiros Adriano, Holger Giese
cs.RO · cs.AI · cs.LG
Rovers rely on perception to maintain spatial maps that encode both objects and sensor quality (e.g., range reliability, lighting artifacts, data density), guiding data fusion, embedding updates, and navigation under partial observability. To study these coupled perception-navigation processes, we present CrossMaps, a real-time confidence-aware open-vocabulary semantic mapping pipeline that constructs language-queryable maps from RGB-D data....
-
06
Binary Tracking for Spatial QA and Navigation with Open Vision-Language Models
Dongbin Na, Chanwoo Kim, Soonbin Rho, Giyun Choi, Gangbok Lee, Dooyoung Hong
cs.RO · cs.AI
This work addresses spatial question answering for service robots traversing long egocentric routes. Given a query such as "where can I find a dry cleaner on the way back home?", the system returns a metric coordinate that downstream navigation components can act on. Prior Spatial Question Answering approaches leverage retrieval-augmented agents built on closed-source models such as GPT-4o for path exploration. However, robots operating in...
-
07
ATOM-Bench: A Real-World Benchmark for Atomic Skills and Compositional Generalization in Manipulation Policies
Zenan Wu, Bingqing Wei, Lu Liu, Zheqi He, Xi Wang, Jiakang Liu, Zehui Li, Guocai Yao, Jing-Shu Zheng, Xi Yang, Yongtao Wang
cs.RO · cs.AI
Generalist manipulation policies are increasingly presented as foundation models for robotic control, but their real-world generalization remains difficult to diagnose. A policy may succeed on demonstrated tasks while still failing to execute fine-grained atomic skills or recombine learned skills in new task structures. We introduce \textbf{ATOM-Bench}, a real-world benchmark for evaluating both atomic skills and compositional generalization...
-
08
PATCH: Action-Chunk-Conditioned Latent Patch Innovation Monitoring for Robot Manipulation
Yanan Zhou, Ranpeng Qiu, Yincong Chen, Jiajie Cui, Weiming Zhi
cs.RO · cs.AI · cs.CV
Learning-based manipulation policies have made substantial progress in real-world robot manipulation, particularly for short-horizon action generation. However, deployment in open workspaces remains fragile under unexpected local scene dynamics, such as moving objects, transient occlusions, or disturbances near the intended motion. Existing runtime monitors often rely on global observation anomalies, policy uncertainty, or frame-level visual...
-
09
Elastic ODYN: Differentiable Optimization for Infeasible Control and Learning in Robotics
Aristotelis Papatheodorou, Jose Rojas, Ioannis Havoutis, Carlos Mastalli
cs.RO · cs.LG
Robotic systems routinely encounter conflicting objectives, modeling errors, and degenerate contact conditions that render quadratic programs (QPs) infeasible. Yet most optimization solvers and differentiable QP layers assume feasibility, leading to numerical failures, unstable gradients, or solver breakdown when constraints cannot be simultaneously satisfied. We present Elastic ODYN, a primal--dual non-interior-point QP solver that handles...
-
10
HOLO-MPPI: Multi-Scenario Motion Planning via Hierarchical Policy Optimization
Youngjae Min, Jovin D'sa, Faizan M. Tariq, David Isele, Navid Azizan, Sangjae Bae
cs.RO · cs.AI · eess.SY
Robots deployed in the real world must plan motions across diverse scenarios without per-scenario retuning. End-to-end reinforcement learning (RL) can generalize across scenarios but often becomes brittle under distribution shift, reward misspecification, and stochastic interactions. Model predictive path integral (MPPI) control enables strong real-time refinement without gradients, but its performance depends on a well-shaped sampling prior,...
-
11
Training and Evaluating Diffusion Policies with Long Context Lengths
Abhinav Agarwal, Adam Wei, Taylan Kargin, Michael Zeng, Cole Becker, Arif Kerem Dayi, Pablo Parrilo, Asuman...
cs.RO · cs.AI
Imitation learning has enabled highly-dexterous robotic manipulation from RGB observations. Policies trained with these methods, however, typically condition robot actions on only a short history of observations. These policies cannot solve tasks that require memory and can get stuck repeatedly executing the same failing motions. In this work, we first benchmark policy performance as context length is incrementally increased from short to...
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.