MEKAWIRE
Forschung

Studien

Neue Studien zu Robotik und Physical AI, jeweils mit ihrer Bedeutung für die Branche.

23 Studien
ThemaAlleManipulation 76VLA 60Navigation 35Robotik allgemein 32Roboterlernen 27Wahrnehmung 22Humanoide 20Simulation 15Fortbewegung 13Sicherheit 11World Action Models 4World-action model 3Aerial 2Aerial manipulation 2Dexterous manipulation 2Sim-to-Real Manipulation 2Social Navigation 2Vision-Language Navigation 23D Assembly 13DGS dataset 15G Simulation 1AMR Operations 1Active vision manipulation 1Adaptive MPC 1Adaptive action horizons 1Adaptive intervention 1Aerial Manipulation 1Aerial navigation 1Agricultural Robotics 1Articulation Estimation 1Autonomous Driving 1Autonomous Exploration 1Battery-aware RL 1Belief-space planning 1Benchmark for adding wrist force sensing to VLA manipulation policies 1Bimanual Manipulation 1Byzantine localization 1Canal inspection 1Co-speech Humanoid 1Compositional Manipulation 1Construction navigation 1Contact-Rich Manipulation 1Contact-rich Manipulation 1Continual reinforcement learning on top of robot foundation models 1Continuum sensing 1Controlled comparison of how to add world models to VLA robot policies 1Cross-embodiment transfer of humanoid whole-body controllers 1Curriculum RL 1Dexterous Manipulation 1Distributed Manipulation 1Distribution Shift 1Driving Simulation 1Efficient VIO 1Egocentric data 1Egocentric video 1Embodied Agents 1Embodied policy 1Empowerment MPC 1Endoscopic navigation 1Endovascular robotics 1Evaluating robot world models against real executions 1Event-camera VO 1Exoskeletons 1Failure recovery 1Faster on-device inference for flow-matching vision-language-action models 1Federated 3D Perception 1Fisheye detection 1Floorplan SLAM 1Geometry-aware manipulation 1Grasping 1Grounding 1Humanoid Control 1Humanoid RL 1Humanoid Tool Use 1Humanoid loco-manipulation 1Humanoid safety 1Humanoid whole-body control 1Humanoid whole-body training data from robot-specific video generation 1Imitation Learning 1JEPA World Models 1Lab automation 1Laboratory Manipulation 1Latent World Models 1Legged Manipulation 1LiDAR Security 1Lifelong RL 1MAPF 1MAV guidance 1Manipulation LfD 1Manipulation Safety 1Marine simulation 1Memory-centric VLA 1Miniature Locomotion 1Mining Perception 1Mobile manipulation 1Model-based RL 1Monocular SSC 1Motion Planning 1Multi-Agent RL 1Multi-Robot Exploration 1Multi-Robot Manipulation 1Multi-UAV Exploration 1Multi-UAV State Estimation 1Multi-agent RL 1Multi-agent motion planning 1Multi-camera odometry 1Multi-fidelity RL 1Multi-robot manipulation 1Multi-skill Manipulation 1Multi-view perception 1Multimodal simulation 1Navigation & Mapping 1Object Pose Estimation 1Object Search 1Panoramic 3D Detection 1Panoramic segmentation 1Pedestrian tracking 1PersonNav 1Planning 1Policy Optimization 1Preference Learning 1Quadruped locomotion 1Real-time VLA 1Real-to-sim 1Reinforcement learning for industrial assembly 1Representation alignment 1Robot-Use Agents 1Runtime Verification 1Safe Generative Planning 1Safe RL-MPC 1Safe VLA 1Safety monitoring 1Safety-critical control 1Sim-to-real Navigation 1Sim-to-real manipulation 1Simulation geometry 1Skill Discovery 1Social navigation 1Soft Pneumatic Actuators 1Soft manipulation 1Sonar SLAM 1Streaming 3D reconstruction 1Submovement decomposition 1Surgical 1Surgical robotics 1Tactile Exploration 1Tactile VLA 1Temporal manipulation 1Terrain traversability 1Text-to-3D Policy 1Tool Co-Design 1Trajectory Correction 1Traversability 1Turning phone-recorded human demonstrations into per-robot post-training data by retargeting object motion 1UAV Navigation 1UAV Swarms 1UAV traffic monitoring 1Underwater Robotics 1Underwater active mapping 1Underwater perception 1Unified world-action model 1VLA Conditioning 1VLA Defense 1VLA Robustness 1VLA evaluation 1VLA manipulation 1VLA robustness 1Video world models 1Vision-language-action models without wrist cameras (learned foveation) 1Visual Generalization 1Visual Grounding 1Visual Reward Models 1Visuomotor Fusion 1Visuotactile manipulation 1World Models 1World models 1World-Action Models 1
NiveauAlleEinstiegFortgeschrittenExperten
Noch nicht auf Deutsch verfügbar: Anzeige im englischen Original.
Gefiltert nach Technologie Weltmodelle, zurücksetzen
arXiv
Controlled comparison of how to add world models to VLA robot policiesExperten

Was bei Weltmodellen in Vision-Language-Action-Modellen wirklich zählt

Qisen Ma, Yixiang Chen, Yuan Xu, Peiyan Li, Jiabing Yang, Kai Wang, Jianhua Yang, Jianlou Si, Jun Huang, Jing Liu, Nianfeng Liu, Yan Huang, Liang WangInstitute of Automation, Chinese Academy of Sciences; University of Chinese Academy of Sciences; Alibaba Group; FiveAges

Ein Preprint der Chinesischen Akademie der Wissenschaften, von Alibaba und FiveAges vergleicht die gängigen Wege, Robotermodellen das Vorhersagen des nächsten Zustands beizubringen, auf identischer Basis. Vorhersage hilft fast immer, ein Universalrezept gibt es nicht; ein vom Hauptmodell getrenntes Vorhersagemodul passte am besten zu vortrainierten Robotermodellen und hob die Erfolgsquote am echten Roboter von 45 auf bis zu 73,8 Prozent.

VLAWeltmodelleRobotik-BasismodelleImitationslernen
Physical IntelligenceFranka Robotics
Vollständige Studie lesen (PDF)
arXiv
VLAExperten

Towards Agentic Robots: Model, Data, Environment, and Harness

Chonghan Qin, Dongming Wu, Kaituo Feng, Jiaxu Wang, Xinlei Yu, Peiwen Sun, Yijia Fan, Xilin He, Bingao Chen, Weitong Lian, Ryan Ji, Wenqi Ren, Xiaobin Hu, Dahua Lin, Yu-Gang Jiang, Xiangyu Yue

Foundation models are driving a paradigm shift in robotic intelligence, moving beyond low-level action prediction to goal-directed orchestration of data collection, model training, task planning, and real-world execution. We characterize this emerging paradigm as an agentic robots, in which agents reason over human instructions, interact with robotic environments, rectify execution errors autonomously, and dynamically adjust operational strategies.

VLAWeltmodelle
Foundation
Vollständige Studie lesen (PDF)
arXiv
VLAExperten

SafeDriveVLA: Navigation-Conditioned World Model Dreaming for Conflict-Aware End-to-End Autonomous Driving

Shaoyuan Xie, Zihan Zhang, Jingxuan Wang, Jiashu Qu, Xiaoqing Liang, Lingdong Kong, Junchi Lu, Henrik I. Christensen, Qi Alfred Chen

Vision-Language-Action (VLA) models are gaining attention in autonomous driving, inheriting commonsense priors from large language models (LLMs) and widening the navigation interface from a fixed command set to free-form natural-language instructions. However, this open-ended interface exposes a new vulnerability surface: an inattentive driver may issue instructions that are unsafe given the current scene, and a malicious user may issue dangerous ones on purpose.

VLAWeltmodelle
Vollständige Studie lesen (PDF)
arXiv
LearningExperten

DriveWLA: Unifying Future Dynamics and Scene Semantics through World-Language-Action Modeling for Autonomous Driving

Shuzheng Wang, Haoxuan Li, Shengzhen Li, Chenxi Wu, Yajing Sun, Lu Hou, Wenyu Liu, Xinggang Wang

Vision-Language Models (VLMs) and world models have demonstrated strong capabilities in semantic understanding and future scene evolution for autonomous driving. However, effectively integrating both capabilities for trajectory generation remains challenging.

WeltmodelleImitationslernenRL
Vollständige Studie lesen (PDF)
arXiv
ManipulationExperten

RoboFQE: Rollout-Free Evaluation of Visual Robot Policies from Offline Trajectories

Yunfu Deng, Sangwoo Shin, Brahma S. Pavse, Josiah P. Hanna

Evaluating robot policies before deployment typically requires producing new trajectories through real-world execution, simulators, or learned world models. These rollout-based approaches impose infrastructure requirements; simulator and world-model evaluators additionally face prediction errors that can compound over the evaluation horizon.

Weltmodelle
Foundation
Vollständige Studie lesen (PDF)
arXiv
VLAExperten

WoVR+: World Model as Reliable Simulator for Versatile VLA Policy Optimization with RL

Shangqing Zhou, Zhennan Jiang, Ning Ma, Xin Fu, Yupeng Zheng, Shuai Tian, Huangrui Li, Jiahao Liu, Chao Yu, Zhongpu Xia, Haoran Li, Dongbin Zhao

Action-conditioned world models can reduce costly real-robot interaction in reinforcement learning for Vision-Language-Action models (VLA-RL), but hallucinations can mislead policy optimization. Extending them to richer VLA interfaces and long-horizon tasks raises challenges in spatiotemporal and cross-modal consistency, exploration-reliability balance in RL, and compounding rollout errors.

VLAWeltmodelleRL
Vollständige Studie lesen (PDF)
arXiv
LearningExperten

OccWAM: Occupancy World-Action Models with Joint Scene-to-Ego Flow Matching

Qihang Huang, Wenhui Huang, Collister Chua, Shiyu Fang, Zhan Chen, Songyan Zhang, Zhidong Wang, Daiying Tian, Chen Lv

Occupancy world models provide a structured, metric representation of future driving scenes, making them a promising basis for end-to-end autonomous driving. However, existing occupancy-aware planners typically couple occupancy prediction and action generation through either hierarchical coupling or parallel multi-task learning.

Weltmodelle
Vollständige Studie lesen (PDF)
arXiv
NavigationExperten

SkipWorld: Latent Skip Planning with Distilled World Models for Efficient Visual Navigation

Yifei Yang, Zehua Fan, Zike Yan, Zhongyu Li, Yan Wang

World-model-based visual navigation enables action planning by predicting future states under candidate trajectories. However, long-horizon rollout remains challenging: models are often trained with ground-truth visual histories but deployed in closed-loop prediction, and evaluating many candidates with step-by-step rollout is computationally expensive.

Weltmodelle
Vollständige Studie lesen (PDF)
arXiv
ManipulationExperten

UniW(A)M: A Unified Mixture-of-Experts Framework for World and World-Action Models

Jingbo Xu, Jianjie Fang, Zhuohang Li, Zihao Song, Zhaolu Wang, Xvyuan Liu, Xin Zhang, Haisheng Su, Yinzhou Tang, Chen Gao, Wei Wu, Yong Li

World models (WMs) and world-action models (WAMs) focus on future world prediction and executable action generation, respectively. Although these models learn shared physical dynamics and interaction semantics from embodied trajectories, they are typically trained in isolation, which restricts knowledge reuse between prediction and control.

Weltmodelle
Vollständige Studie lesen (PDF)
arXiv
LearningExperten

Thinker-WM: A Unified World Model with Shared Multimodal Representations for Embodied Intelligence

Thinker Team, Peng Gao, Jichao Jiao, Chen Liao, Daqin Luo, Yiming Ma, Baiyu Pan, Hailin Shi, Jiyuan Wang, Xiangming Xu, Xiongwei Zhao

World models have emerged as a promising paradigm for embodied AI, yet existing systems often remain fragmented in the modalities they model and the functions they support. In particular, visual dynamics, geometric structure, and executable action are commonly coupled through separate interfaces or downstream modules rather than being jointly represented and evolved within a shared dynamics model.

Weltmodelle
Vollständige Studie lesen (PDF)
arXiv
Continual reinforcement learning on top of robot foundation modelsExperten

ACCRUE: Kontinuierliches Off-Policy-Verstärkungslernen für Robotik-Basismodelle

Changyeon Kim, Kimin Lee, Yashraj Narang, Yijie GuoNVIDIA; KAIST

Forscher von NVIDIA und dem KAIST beschreiben in einem Preprint, wie ein von einem Basismodell gesteuerter Roboter neue Montageaufgaben nacheinander lernt, ohne alte zu vergessen, indem er ein kleines Verstärkungslern-Modul von Aufgabe zu Aufgabe mitnimmt. Am realen Arm sank die Roboterzeit bis zur Beherrschung jeder neuen Fügeaufgabe um 31,0 bis 68,5 %, frühere Aufgaben gelangen weiterhin in durchschnittlich 19,4 von 20 Versuchen.

Robotik-BasismodelleRLVLAWeltmodelle
FoundationNVIDIAPhysical Intelligence
Vollständige Studie lesen (PDF)
arXiv
LearningExperten

Directional Pullback Regularization for Long-Horizon Rollout of Latent World Models in Autonomous Driving

Shatadal Mishra, Ahmadreza Moradipari, Nejib Ammar

Learned world models for autonomous driving operate in unconstrained latent spaces, yet the physical systems they represent are governed by strict non-holonomic constraints: ground vehicles cannot realize instantaneous pure lateral motion. We study long-horizon latent rollout modeling for autonomous driving and ask whether rollout quality can be improved by assigning a motion-aware geometry to latent transitions, rather than by redesigning the predictor architecture.

Weltmodelle
Vollständige Studie lesen (PDF)
arXiv
SimulationExperten

StreamingWAM: Streaming World Action Modeling via Chunk-Wise Staircase Flow Matching

Shaojie Ren, Jingwen Sun, Zezhi Liu, Hongjin Chen, Xin Jin, Wei Zou, Zhibo Chen

World Action Models (WAMs), often built upon pretrained video-generation world models, have emerged as a promising framework for general-purpose and open-ended robot control. However, their real-world deployment often suffers from discontinuous and jerky execution.

Weltmodelle
Vollständige Studie lesen (PDF)
arXiv
LearningExperten

LeHami: Symplectic Latent Dynamics for World Models

Romina Yalovetzky, Randall Balestriero, Yann LeCun

Joint-embedding predictive architectures (JEPAs) learn world models directly in latent space, but unconstrained autoregressive predictors may contract the latent distribution over long rollouts. We introduce Symplectic Hamiltonian JEPA (LeHami), which replaces the standard predictor with an action-conditioned Hamiltonian flow over a structured latent state (q, p) integrated using an exactly symplectic leapfrog step.

Weltmodelle
Vollständige Studie lesen (PDF)
arXiv
ManipulationExperten

Grounded-Dreamer: Robot Learning from World Model Synthetic Data with Physical Grounding

Feng Jiang, Shu Chen, Yuanfei Wang, Yuan Li, Zhenhao Shen, Jiaqi Liang, Yang Chen, Lei Wei, Chen Xie, Ruihai Wu

Scaling robot manipulation policies requires large amounts of diverse, action-labeled data, yet collecting such data in the real world remains expensive and difficult to scale. Existing methods either depend on human teleoperation, rely on simulation with limited visual realism, or use human videos that lack embodiment-specific annotations.

WeltmodelleTeleoperation
Vollständige Studie lesen (PDF)
arXiv
LearningExperten

Dream to Remember: Continual Steering of Generalist Robot Policies with World Models

Bahey Tharwat, Iman Nematollahi, Marvin Alles, Xingyuan Zhang, Akshay L Chandra, Abhinav Valada

Generalist robot policies are trained with imitation learning and are bounded by the quality and coverage of their demonstrations. Reinforcement learning can improve and extend them, either by fine-tuning the policy weights or by training a small module to steer the input noise of a frozen generative policy.

WeltmodelleImitationslernenRL
Vollständige Studie lesen (PDF)
arXiv
ManipulationExperten

Beyond Successful Robot Demonstrations: Learning from Human Interactions and Modeling Failure Dynamics

Peiyan Tu, Cong Wang, Hanxin Zhu, Xin Jin, Zhibo Chen

Action-conditioned world models offer a promising foundation for generalist robotic intelligence by predicting the consequences of actions. However, existing robotic datasets provide limited coverage of the diverse interaction dynamics required for generalizable world modeling.

Weltmodelle
Foundation
Vollständige Studie lesen (PDF)
arXiv
World-action modelExperten

Welche Bildmerkmale World-Action-Modelle brauchen: Systematischer Vergleich von Galbot und der Chinesischen Akademie der Wissenschaften

Kai Liu, Jiangran Lyu, Tingyu Deng, Yixin Zheng, Jingtian Wan, Wenbo Cui, Mi Yan, Yizhou Zhou, Haoran Li, Dongbin Zhao, Zhizheng Zhang, He WangInstitute of Automation, Chinese Academy of Sciences; Galbot; Peking University; University of Science and Technology of China

Ein Preprint des chinesischen Humanoid-Herstellers Galbot und der Chinesischen Akademie der Wissenschaften prüft, welche fertigen Bildencoder videobasierte Robotersteuerungen zuverlässiger machen, und kommt zu dem Schluss, dass ein einzelner starker Universal-Encoder den Großteil des Gewinns liefert. Das daraus abgeleitete Rezept erzielt im Humanoid-Benchmark RoboCasa GR1 einen Bestwert von 84,7 Prozent und hebt die Erfolgsquote bei drei Aufgaben auf einem realen Galbot-Roboter um jeweils 10 Punkte.

WeltmodelleVLARobotik-BasismodelleImitationslernen
GalbotNVIDIAPhysical Intelligence
Vollständige Studie lesen (PDF)
arXiv
JEPA World ModelsExperten

AVL-JEPA verhindert Informationskollaps kausaler Dynamik in JEPA-Weltmodellen

Yikang Qiao, Ling Zhang, Ziying Song, Duan Huang

Der Preprint stellt mit AVL-JEPA einen Ansatz vor, der verhindert, dass JEPA-Weltmodelle handlungsbedingte physikalische Dynamik zugunsten visueller Information ausblenden. In Simulationen auf vier Roboteraufgaben verbessert AVL die Erfolgsraten unter visuellen Störungen deutlich, etwa auf PushT unter Gaussian Noise von 15,3 auf 81,5 Prozent, und erhält gleichzeitig die Leistung ohne Störungen. Der Preprint liefert damit Belege, dass der Erhalt kausal relevanter Dynamikinformation die Planungsrobustheit von Weltmodellen steigert.

Weltmodelle
Vollständige Studie lesen (PDF)

Themenseiten

Manipulation 6VLA 4World Action Models 5World-action model 3Aerial manipulation 3Dexterous manipulation 3Sim-to-Real Manipulation 3Social Navigation 3

Die Studien stammen aus den Robotik-Feeds von arXiv. Solange unsere Zusammenfassung fehlt, erscheinen die ersten Zeilen des Abstracts.