MEKAWIRE
Forschung

Studien

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

413 Studien
ThemaAlleManipulation 76VLA 65Navigation 35Robotik allgemein 32Roboterlernen 27Wahrnehmung 22Humanoide 21Simulation 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 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 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 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 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 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 models 1World-Action Models 1
NiveauAlleEinstiegFortgeschrittenExperten
Noch nicht auf Deutsch verfügbar: Anzeige im englischen Original.
arXiv
Battery-aware RLExperten

Batteriebewusstes Reinforcement Learning für aggressiven Quadrocopter-Flug

Alejandro Sanchez Roncero, Olov Andersson, Petter Ogren

Der Preprint stellt eine RL-Policy für einen 38 g Crazyflie Brushless vor, die eine gefilterte Batteriespannung beobachtet und einen erweiterten Schubkommando-Bereich nutzt. Gegenüber der Standard-Autoritäts-Baseline sinkt der Trackingfehler beim Kreisen mit 3,84 m/s um 49,3 % (von 14,26 cm auf 7,23 cm RMSE), und die mittlere 20-Runden-Rennzeit fällt von 106,22 s auf 95,24 s. Das zeigt, dass explizite Spannungsinformation die vorhandene Firmware-Kompensation bei aggressivem Flug ergänzt.

RL
Vollständige Studie lesen (PDF)
arXiv
RoboticsExperten

doPlan: A Variable-Horizon Dataset for Multi-Stage Language-Conditioned Planning in Autonomous Driving

Parthib Roy, Yash Tandon, Marcus Blennemann, Giovanni Tapia Lopez, Angel Martinez-Sanchez, Mohan M. Trivedi, Ross Greer

Autonomous vehicles interacting with passengers through natural language must reason beyond immediate commands. Passenger intent may span multiple stages of behavior, depend on future events, refer to surrounding agents or landmarks, and remain relevant as driving conditions evolve.

Vollständige Studie lesen (PDF)
arXiv
LearningExperten

Anisotropic Representations Improve Planning in JEPA World Models

Mingu Kang, Yoori Oh, Sookyung Kim, Joonseok Lee

Latent world models learn action-conditioned dynamics in representation space and often score candidate actions by Euclidean distance to a goal representation. Joint training typically regularizes the representation to prevent collapse, but the resulting representation geometry also determines how terminal errors are weighted during planning.

Weltmodelle
Vollständige Studie lesen (PDF)
arXiv
HumanoidExperten

Counterfactual Video Generation Enables Scalable Humanoid Loco-Manipulation

Zihan Wang, Zhen Wu, Pieter Abbeel, Rocky Duan, Jitendra Malik, Carmelo Sferrazza, C. Karen Liu, Guanya Shi, Angjoo Kanazawa

Teaching humanoids loco-manipulation skills, such as carrying diverse objects, via visual imitation is a promising path toward generalist robots. However, collecting diverse, high-quality interaction videos, such as clips that clearly show a person's full body and unoccluded interactions with objects, poses a practical barrier to scaling this approach.

Vollständige Studie lesen (PDF)
arXiv
HumanoidExperten

Learning Expressive and Compositional Motion Representation via Spectral Skills

Feiyang Wu, Chenxiao Gao, Chen Yang, Ye Zhao, Bo Dai, Anqi Wu

Robotic foundation models offer a promising path toward general-purpose humanoid robot control, often through hierarchical architectures. However, their effectiveness depends on the command interface between the planner and the controller, which must support accurate execution while remaining easy to predict, and ideally allow new behaviors to be composed from prior ones.

Vollständige Studie lesen (PDF)
arXiv
NavigationExperten

Brain-SAD: A Brain-Inspired Safe Autonomous Driving Control Framework with Dynamic Fear-Oriented Constraint on Dual-Policy

Huan Rong, Chao Yin, Anouar Imel, Yijie Xia, Tinghuai Ma

Constrained Reinforcement Learning has recently gained increasing attention in the field of Safe Autonomous Driving, where the general mechanism is to maximize the expected reward while keeping the overall action risk bounded. In this way, the safety issues arising in AD can be mitigated through constrained actions.

RL
Vollständige Studie lesen (PDF)
arXiv
ManipulationExperten

In-context Robot Learning Made Simple: A Democratized Recipe for Manipulation Tasks

Minxing Li, Minghao Han, Weizhi Zhao, Hanwen Wang, Xiangshuo Liu, Shuyao Shang, Jingxiang Zhou, Mingchao Sun, Hongyu Pan, Mu Xu, Yu Liu, Lue Fan, Zhaoxiang Zhang

We study robotic in-context learning (ICL), an emerging paradigm that enables robots to infer and execute tasks from visual demonstrations. Despite its growing promise, the problem itself remains under-defined: a visual demonstration simultaneously conveys action trajectories, object semantics, manipulation affordances, spatial relations, and task goals, making it unclear what information the robot is actually expected to follow.

Vollständige Studie lesen (PDF)
arXiv
World-Action ModelsExperten

DEWO: Weltmodell-Optimierung aus direkter Erfahrung für World-Action Models

Xiangcheng Zhan, Zirui Chen, Yicheng Zhao, Ziteng Gao, Shuo Yang

Das Preprint stellt Direct Experience World-Model Optimization (DEWO) vor, ein Post-Deployment-Lernverfahren für World-Action Models, das neben Aktionsimitation auch visuelle Vorhersagen aus beobachteten Interaktionsverläufen aktualisiert. In fünf DexJoCo-Aufgaben verbessert DEWO den durchschnittlichen Erfolg über alle drei getesteten WAM-Formulierungen; auf echten Roboterplattformen steigt der Erfolg in Zellen mit mindestens einem anfänglichen Erfolg von 51,0 % auf 71,7 %. Damit wird Weltmodellierung zu einem aktiven Teil der Anpassung nach dem Einsatz.

Feinmanipulation
Vollständige Studie lesen (PDF)
arXiv
LearningExperten

When to Adapt: Multi-Signal Domain Shift Detection for Efficient Training-Free Adaptation in Open-Vocabulary Segmentation

Michele Antonazzi, Alejandra C. Hernandez, José Araujo, Olov Andersson, Patric Jensfelt

Robust and reliable perception is essential for autonomous robots operating in real-world environments, particularly in long-term missions where environmental conditions may change significantly over time. Although recent advances in Visual Foundation Models (VFMs) have improved open-vocabulary semantic segmentation, these models can still suffer from domain shift, which can significantly degrade performance if they are not adapted to the current environment.

Vollständige Studie lesen (PDF)
arXiv
Humanoid whole-body controlExperten

CrossBFM: Ein gemeinsamer latenter Verhaltensraum für unterschiedliche Humanoide per Destillation

Tan-Dzung Do, Tuan Dat Phuong, Nico Bohlinger, Cuc T. Trinh, Siwei Ju, Vien Anh Ngo, Jan Peters, Xinchao Wang, An T. LeVinRobotics, National University of Singapore, TU Darmstadt, VinUniversity, DFKI, Hessian AI

Ein Ganzkörper-Steuerungsmodell, mit dem ein Humanoide auf einen einzigen Prompt hin einen Tanz nachahmt, eine Pose einnimmt oder einer Belohnung folgt, kostet je Roboter normalerweise mehr als 100 GPU-Stunden Training. Dieser Preprint von VinRobotics, der National University of Singapore und der TU Darmstadt überträgt das für Unitrees G1 trainierte Modell auf Booster T1, Fourier N1 und einen hauseigenen Roboter namens M3, mit weniger als einer Stunde für einen gemeinsamen Encoder und weniger als zehn GPU-Stunden je Roboter, bei fast gleicher Tracking-Genauigkeit wie ein spezialisierter Regler.

Robotik-BasismodelleRLSim-to-Real-Transfer
Unitree RoboticsBooster RoboticsFourier
Vollständige Studie lesen (PDF)
arXiv
VLA robustnessExperten

Self-Compensating VLA: Online-Anpassung gegen Ausführungsfehler von Robotern

Sohyun Lee, Yoonjae Baek, Jaesang Won, Jinnyeong Kim, Kang Hyunwoo, Seung-Hwan Baek, Ivan Laptev, Suha Kwak

Das Paper stellt Self-Compensating VLA vor, eine Methode zur Deployment-Zeit-Anpassung von Vision-Language-Action-Policies, die sich ohne Belohnungen oder Labels an Ausführungsfehler des Roboters anpasst. Sie nutzt die Differenz zwischen kommandierter und tatsächlich ausgeführter Bewegung als Selbstüberwachungssignal. In Simulation (RoboStress) und auf zwei realen Roboterarmen erzielt die Methode deutlich höhere Erfolgsraten als Baselines und Trainingszeit-Robustheitsverfahren; es handelt sich um ein Preprint.

VLA
Vollständige Studie lesen (PDF)
arXiv
PerceptionExperten

Does Local Video Understanding Transfer Across Encounters? The EgoGears Benchmark

Yuedong Tan, Lei Qi, Yu Liu, Di Wen, Ruiping Liu, Xiaoye Wang, Yufan Chen, Junwei Zheng, Chengzhi Wu, Chen Zhang, Zhihang Chen, Haiwen Sun, Zongwei Wu, Radu Timofte, Danda Pani Paudel, Kunyu Peng

Embodied systems must make knowledge acquired during one encounter usable in another despite changes in viewpoint, motion, and illumination. Yet aggregate cross-video accuracy conflates failures of local perception with failures to preserve observation identity, establish correspondence, and compose evidence, obscuring whether local video understanding actually transfers.

Vollständige Studie lesen (PDF)
arXiv
ManipulationExperten

Wrench-ACT: Enhancing Robot Policies for Contact Rich Behavior Using Direct Wrench Control

Johannes Hechtl, Yannik Blei, Simon Ball, Reihaneh Mirjalili, Michael Krawez, Seongjin Bien, Philipp Schmitt, Wolfram Burgard

While contact-rich manipulation requires deliberate regulation of interaction forces, recent approaches to robot manipulation learning predominantly represent actions as target positions or poses. Even methods that incorporate force sensing either use it solely as an observation or, when predicting forces as part of the output, rely on a hybrid force controller.

ImitationslernenTeleoperation
Vollständige Studie lesen (PDF)
arXiv
NavigationExperten

Risk-Aware Semantic Grounding for Trustworthy LLM-Based Robot Planning

Łukasz Sobczak, Nur Keleşoğlu, Sławomir Piotr Nowak

Large language models (LLMs) are increasingly used as high-level planners in robot navigation, but their outputs may become unreliable when instructions are ambiguous, unsupported by the environment, or semantically inconsistent. This paper presents a Risk-Aware Semantic Grounding framework for trustworthy LLM-based robot planning.

Vollständige Studie lesen (PDF)
arXiv
ManipulationExperten

RoboHarn-Evo: Evolving Hierarchical Physical Knowledge for Self-Improving Robotic Manipulation

Shifeng Bao, Fanding Huang, Yihan Lin, Youhe Feng, Guanlin Li, Chen Zhao, Yang Li, Jiawei He, Cheng Chi, Jing Zhang

Vision-language models can coordinate long-horizon robot manipulation, yet successful task reasoning still depends on whether local physical interactions produce the intended effects. We study how repeated interaction can improve this capability without updating the base model.

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.