MEKAWIRE
Forschung

Studien

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

27 Studien
ThemaAlleManipulation 27VLA 22Perception 12Robotics 11Navigation 10Humanoid 9Learning 8Safety 5World Action Models 4Simulation 3Aerial manipulation 2Dexterous manipulation 2Sim-to-Real Manipulation 2Social Navigation 2Vision-Language Navigation 2World models 2World-action model 23D Assembly 13DGS dataset 15G Simulation 1AMR Operations 1Active vision manipulation 1Adaptive MPC 1Adaptive action horizons 1Adaptive intervention 1Aerial 1Aerial Manipulation 1Aerial navigation 1Agricultural Robotics 1Articulation Estimation 1Autonomous Driving 1Autonomous Exploration 1Battery-aware RL 1Belief-space planning 1Bimanual Manipulation 1Byzantine localization 1Canal inspection 1Co-speech Humanoid 1Compositional Manipulation 1Construction navigation 1Contact-Rich Manipulation 1Contact-rich Manipulation 1Continuum sensing 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 1Event-camera VO 1Exoskeletons 1Failure recovery 1Federated 3D Perception 1Fisheye detection 1Floorplan SLAM 1Geometry-aware manipulation 1Grasping 1Grounding 1Humanoid Control 1Humanoid RL 1Humanoid Tool Use 1Humanoid control 1Humanoid loco-manipulation 1Humanoid safety 1Imitation Learning 1JEPA World Models 1Lab automation 1Laboratory Manipulation 1Latent World Models 1Legged Manipulation 1LiDAR Security 1Lifelong RL 1Locomotion 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 1Policy Optimization 1Preference Learning 1Quadruped locomotion 1Real-time VLA 1Real-to-sim 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 robotics 1Tactile 1Tactile Exploration 1Tactile VLA 1Temporal manipulation 1Terrain traversability 1Text-to-3D Policy 1Tool Co-Design 1Trajectory Correction 1Traversability 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 1Visual Generalization 1Visual Grounding 1Visual Reward Models 1Visuomotor Fusion 1Visuotactile manipulation 1World Models 1World-Action Models 1
Noch nicht auf Deutsch verfügbar: Anzeige im englischen Original.
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.

arXiv
ManipulationExperten

AutoBio+: Benchmarking Dexterous Manipulation with Dynamic Experimental Phenomena in Realistic Laboratories

Xuanye Wu, Yue Shi, Yongcan Yang, Yiqun Wang, Zhaoqi Wan, Dayu Xia, Jiezhang Cao, Xiangfei Li, Yao Mu, Guangtao Zhai

Automating biological laboratories requires robots to perform dexterous tool interactions under realistic visual conditions while handling dynamic experimental phenomena, presenting significant challenges for robotic manipulation. To enable systematic evaluation under these conditions, we introduce AutoBio+, a simulation benchmark and framework for dexterous manipulation in realistic biological laboratory environments.

arXiv
ManipulationExperten

Evo-RL: Iterative Robot Reinforcement Learning from Selective Experience

Kai Ye, Yifan Jin, Qianhang Luo, Hongru Zhang, Jiedong Zhang, Shuyuan Hu, Song-Yuan Wu, Jihai Xu, Jie Zhao, Bo Zhao

Existing real-world reinforcement learning methods improve robot policies by combining human corrections with autonomous rollouts. However, accumulated experience varies in its value for policy improvement, and even successful trajectories can contain inefficient or redundant behavior, motivating more selective experience reuse.

arXiv
ManipulationExperten

Cooperative Aerial Transportation of a Payload with a Sliding Cable Attachment

Sebastian Tilaguy Lezama, Diego S D'Antonio

This paper presents a dual-quadrotor hook- suspended transport system for cooperative aerial manipulation of a payload that is not rigidly attached to a fixed point along the cable. Two quadrotors are connected by a single inextensible cable that passes through a frictionless hook mounted on the payload, allowing the cable to slide between its two segments.

arXiv
ManipulationExperten

AlphaNIST: Emergent Assembly Skills from Binary Task Rewards

Octi Zhang, Iretiayo Akinola, Rosario Scalise, Mateo Guaman Castro, Patrick Yin, Tobias Widmer, Miles Macklin, Chris Amevor, Dylan Turpin, Dirk Van Gelder, Jan Carius, Ankur Handa, Gavriel State, Yunrong Guo, Yashraj Narang

The NIST Assembly Task Board #1 remains a challenging benchmark for learning-based methods in robotic manipulation. Over short horizons, it demands precise, contact-rich control of small, tight-fitting parts.

arXiv
ManipulationExperten

ReAT: Residual Action Tokenization for Autoregressive Robot Policies

Dijia Zhan, Zhuo Li, Xuemiao Xu, Sun Zheng, Jinyi Li, Wenjun Wang, Jie Tang

Autoregressive robot policies rely on action tokenizers to convert continuous action chunks into compact sequences of discrete prediction targets. Existing tokenizers can reconstruct action chunks from discrete codes, but often leave implicit what each individual token contributes to the reconstructed action.

arXiv
ManipulationExperten

Human2Dex: Dexterous Robot Learning from Wrist-Centric Human Demonstrations

Jiachen Zhang, Yuanyuan Li, Shaqi Luo

Collecting dexterous manipulation demonstrations for each robot hand requires repeated task-specific data acquisition. We ask whether one shared corpus of natural human demonstrations can instead serve as a reusable data interface for different dexterous hands, without collecting task demonstrations on each target robot.

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.

arXiv
ManipulationExperten

What Visual Representations Do World Action Models Need?

Kai Liu, Jiangran Lyu, Tingyu Deng, Yixin Zheng, Jingtian Wan, Wenbo Cui, Mi Yan, Yizhou Zhou, Haoran Li, Dongbin Zhao, Zhizheng Zhang, He Wang

World Action Models (WAMs) inherit powerful priors from pretrained video generation models, but their variational autoencoder (VAE) representations are optimized for visual reconstruction rather than manipulation. External visual representations can improve manipulation, but existing methods couple representation choices with different integration mechanisms, obscuring their individual effects.

arXiv
ManipulationFortgeschritten

Bridging Frontier Reasoning and Robot Execution: From Autonomous Demonstration Generation to Dense Language Supervision

Bosung Kim, Alexander Trevithick, Ruiyi Wang, Prithviraj Ammanabrolu

Preprint. The authors present two ways to connect slow frontier reasoning models to fast local robot policies: autonomous generation of corrective demonstrations for training, and dense language supervision at multiple granularities. They report that autonomous demonstration generation becomes more reliable and cheaper as successful examples accumulate, and that a deployment harness lets the frontier model guide the local policy. This matters because it could enable powerful but high-latency models to drive real-time robot manipulation.

arXiv
ManipulationFortgeschritten

AdaTempo lernt gemeinsames relatives Tempo aus Demonstrationen für schnellere Roboter-Manipulation

Jiale Cao, Yike Niu, Zhengrong Xue, Huazhe Xu

AdaTempo ist ein selbstüberwachtes Verfahren, das aus Teleoperationsdemonstrationen phasenabhängige Geschwindigkeitsprofile ableitet und die Trainingsdaten offline neu abtastet, um Standardpolitiken wie ACT oder Diffusion Policy zu beschleunigen. In Simulation und Praxis erreicht es bis zu 3,57-fache Beschleunigung bei einer höheren Erfolgsrate als die Baselines, darunter DemoSpeedup und SAIL. Das Preprint zeigt, dass gemeinsames relatives Timing in Demonstrationen als direktes Signal für schnellere Manipulationspolitiken dienen kann, ohne Laufzeitmodule oder Online-Retiming.

arXiv
ManipulationFortgeschritten

PAM: Proprioceptive Sketches als Langzeit-Intent für generative Aktionspolitiken

Fangyuan Wang, Songhao Huang, Haoxiang Sun, Shipeng Lyu, Chengyang He, Anqing Duan, Peng Zhou, David Navarro-Alarcon

In diesem Preprint stellen die Autoren Proprioceptive Action Models (PAM) vor, die in einem einzigen Transformer-Denoiser eine kompakte, timingfreie Skizze des verbleibenden Roboterpfads und einen kurzen Aktionsblock gemeinsam erzeugen. PAM verbessert die Erfolgsrate bei vier realen bimanuellen Aufgaben von 47,5 % auf 75,0 % und übertrifft Diffusion Policy sowie B-spline Policy. Der Ansatz zeigt, dass eine explizite, geometrische Langzeit-Repräsentation ohne Zeitbezug die Aktionsvorhersage robuster macht.

arXiv
ManipulationExperten

Keep the Effect, Drop the Actor: Programmable Effect-to-Execution World-Action Models

Junyi Hu, Zhewen He, Zhenhua Li, Yi Fang

PEWAM is a preprint describing a 71.5M-parameter world-action model that compiles robot demonstrations into editable “effect programs”—3D object keypoint trajectories, grasp contact points, and final scene configuration—rather than actor-specific motions. On held-out LIBERO-Goal tasks, one program from a single demonstration completes 40 of 90 episodes, while the same backbone under goal-image or language conditioning and prior demonstration-conditioned methods complete at most 19. This matters because turning demonstrations into coordinate-based programs enables editing and cross-robot-arm reuse, a potential route to more flexible robot programming.

arXiv
ManipulationExperten

DynaHarness: Dynamischer physischer Harness für selbst evolvierende Roboteragenten

Haoyuan Deng, Jiebin Liu, Tengxiao Zhang, Langning Yan, Hongye Cao, Ziwei Wang

Das Paper stellt DynaHarness vor, einen Preprint, der einen dynamischen physischen Harness beschreibt, der semantische Planung eines Qwen3-VL-4B-Slow-Brain mit physischer Governance durch einen gemeinsamen Ausführungskontrakt verbindet. Auf LIBERO-Pro erreicht das eingefrorene System 75,2 % auf 800 neu gesampelten Startzuständen, die eingefrorene VLA-Politik 17,5 %. Der Ansatz zeigt, wie Ausführungsevidenz gezielte, validierte Revisionen wiederverwendbarer Fähigkeiten ermöglicht.

arXiv
ManipulationExperten

Dream4ACT: Gemeinsame visuelle Aktionsschnittstelle für verkörperungsübergreifende Video-Aktions-Modellierung

Xiangyu Zhu, Jin Xu, Yue Guo, Xin Wu, Yifan Sun, Xiancong Ren, Jianxin Sun, Yong Dai, Xiaozhu Ju

Das Preprint stellt Dream4ACT vor, ein Video-Aktions-Weltmodell, das Ziel-Gelenkkonfigurationen als feste Multiview-Aktionsbilder (Action Views) repräsentiert und damit mehrere Roboterembodiments über eine gemeinsame Schnittstelle trainiert. In Simulation erreicht das Modell durchschnittlich 88,98 % Erfolg auf RoboTwin 2.0 und einen TriWorldBench-Score von 65,66; auf vier realen Plattformen liegt der mittlere Erfolg bei gemeinsamen Aufgaben zwischen 85,0 % und 90,0 %. Die trainierungsfreie Rückgewinnung ausführbarer Gelenkziele über URDF-Optimierung macht die Aktionsdarstellung direkt für Steuerung nutzbar, ohne gelernte roboterspezifische Decoder.

arXiv
ManipulationFortgeschritten

RoboCoach: Weltmodelle als aktive Coaches für kompositionale Roboterfähigkeiten

Jiajun Liu, Yifan Chen, Yichao Liu, Jiayi Zhang, Ruoqu Chen, Shaoxuan Xie, Guocai Yao, Mengdi Xu, Sen Cui, Changshui Zhang

RoboCoach ist ein Preprint und beschreibt ein Framework, das mit dem aktionskonditionierten Weltmodell CoachWorld imaginierte Fehlschläge in langfristigen Manipulationsaufgaben lokalisiert und daraus gezielte Demonstrationsanfragen sowie LoRA-Updates für die zuständigen Skill-Experten ableitet. In Simulation und auf zwei echten Roboterplattformen steigt die Erfolgsrate mit 150 zusätzlichen Teilaufgaben-Demonstrationen von 13,3 % auf 75,0 % beim Franka und von 40,0 % auf 83,8 % beim AgileX, während eine gleichmäßige Datenerfassung mit gemeinsamem Adapter nur 30,0 % bzw. 47,5 % erreicht. Die Arbeit zeigt, dass Weltmodelle nicht nur simulieren, sondern als aktive Coaches entscheiden können, welche wiederverwendbare Fähigkeit als Nächstes gelernt werden soll.

arXiv
ManipulationExperten

MVG-WAM: Multiple View Geometry-Aware World-Action Modeling for Robotic Manipulation

Wenbo Chen, Tianfu Li, Haoxuan Xu, Zhihao Cao, Zhenghan Chen, Zhengming Zhu, Zizhou Luo, Guosheng Yang, Yuan Liu, Lujia Wang, Wen Chen, Haoang Li

World-Action Models (WAMs) couple visual dynamics with action prediction, bringing the rich priors of pretrained video models to robotic manipulation. However, their multi-view interfaces typically tile images or concatenate tokens, leaving the geometric relationships among synchronized cameras implicit.

arXiv
ManipulationExperten

BlenDAgger: Blended Shared Control for Interactive Imitation Learning

Cailyn Smith, Geoffrey Sun, Henny Admoni, Zackory Erickson

Robot policies are frequently trained from human corrections, yet teleoperating a robot to provide corrections is burdensome, and human demonstrators are not always optimal. We propose Blended DAgger (BlenDAgger), an approach for collecting data to train imitation learning policies by using shared control to blend the policy's and demonstrator's actions during interventions.

Themenseiten

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