MEKAWIRE
Research

Papers

New robotics and physical-AI papers, with what each one means for the industry.

413 papers
TopicAllManipulation · 76VLA · 65Navigation · 35General robotics · 32Robot learning · 27Perception · 22Humanoid · 21Simulation · 15Locomotion · 13Safety · 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
LevelAnyBeginnerIntermediateExpert
arXiv
Real-to-simExpert

LiteReality-Agent: An Agentic System for Interactable 3D Indoor Scene Reconstruction

Zhening Huang, Yueyan Li, Johnathan Chiu, Xiaoyang Lyu, Matt Zhou, Yuxin Yao, Joan Lasenby, Shangzhe Wu

This preprint introduces LiteReality-Agent, an agentic system that converts consumer RGB-D room scans into editable, articulated and MuJoCo-ready 3D scenes by having a coding agent iteratively maintain an executable Python scene program. On ten rooms and 620 capture views it reports PSNR 14.13 dB and depth MAE 10.5 cm, with zero detected furniture intersections, beating GPT-6 and Fable 5.1 baselines. The public code and capture app give robotics teams a practical real-to-sim authoring foundation.

Read the full paper (PDF)
arXiv
Multi-agent RLExpert

Test-time Multi-agent Coordination by Decomposed Value Gradient Flow

Dongsu Lee, Haoran Xu, Amy Zhang

This preprint introduces SCOUT, an offline multi-agent reinforcement learning framework that pairs a per-agent flow-matching behavior prior with a decomposed value function and applies test-time Stein variational refinement to action candidates. Across SMACv1 and MA-MuJoCo, it reports the best average scores among all listed baselines (SMACv1 average reward 16.1 vs 14.9 for MAC-Flow; MA-MuJoCo normalized score 82.12 vs 76.37 for MAC-Flow) and improves on all reported offline-to-online transitions. The result matters because it shifts the coordination/value trade-off from a fixed training-time regularization to an adjustable inference-time compute budget.

RL
Foundation
Read the full paper (PDF)
arXiv
Imitation LearningExpert

Experience-Based Feasibility-Aware Generative Adversarial Imitation from Observation under Embodiment Mismatch

Yoshiki Takebayashi, Giovanni Perantoni, Hikaru Sasaki, Matteo Saveriano, Takamitsu Matsubara

This arXiv preprint introduces EF-GAIfO, a feasibility-aware imitation-from-observation method that learns robot policies from state-only human demonstrations by scoring each demonstrated transition against the robot's own accumulated experience. On a Unitree Go2 quadruped, policies learned with EF-GAIfO reached 70–80% real-world object-grasping success versus 10–30% for WGAIfO and GAIfO baselines. The approach matters because it removes the need for action-labeled demonstrations or explicit robot dynamics models when learning from human motion that the robot may not be able to reproduce.

Read the full paper (PDF)
arXiv
World ModelsExpert

World Motion Models: Flexible Sequence Modeling of SE(3) Trajectories

Jiahui Lei, Qianqian Wang, Trevor Darrell, Angjoo Kanazawa

This preprint, World Motion Models (WMMs), casts dynamic 3D scenes as collections of sparse SE(3) pose trajectories and trains a single flow-matching transformer to answer arbitrary known/unknown conditioning queries. Across separate checkpoints it reports 87.2% macro success on Language Table (vs 80.0% for LCB, the best prior), a 90.0% success on B2B, and faster/higher-success humanoid retargeting than offline PHUMA. It matters because the same architecture can serve as policy, forward dynamics model, planner, and cross-embodiment retargeter.

Read the full paper (PDF)
arXiv
Event-camera VOExpert

Real-time Event-camera Stereo Visual Odometry via Keytime Gaussian Process Regression

Nikan Nobari, Jonathan D. Gammell

This preprint presents a real-time stereo visual odometry system for event cameras that represents the trajectory as a Gaussian process with sparse keytime states instead of one state per event observation. It achieves 22 Hz on MVSEC and 6 Hz on DSEC, with relative translation and rotation errors roughly an order of magnitude lower than the discrete ES-PTAM baseline. The approach preserves asynchronous event timing while making continuous-time estimation tractable for real-time operation.

Read the full paper (PDF)
arXiv
World Action ModelsExpert

World Action Modeling with Progressive Visual Planning

Fei Zhang, Zhaochong An, Duncan Frost, Yikai Wang, Pengfei Liu, Ya Zhang, Michal Drozdzal, Amir Bar

ProWAM is a preprint describing a world action model that predicts sparse visual sub-goals indexed by normalized progress and uses them to condition action chunks, rather than generating dense video. It sets new simulated state-of-the-art on LIBERO-Plus (85.8%) and randomized RoboTwin (75.7%) and reaches 70.0% zero-shot real-world success vs 55.0% for DreamZero. This matters because it offers a more efficient and robust way to transfer video-pretrained visual foresight into long-horizon robot control.

Read the full paper (PDF)
arXiv
Manipulation LfDExpert

Interaction-Stiffness-Guided Basis Allocation in Dynamic Movement Primitives for Efficient Skill Transfer

Chan Xu, Silu Chen, Dehao Wang, Xiyu Chen, Dexin Jiang, Chi Zhang, Guilin Yang, Chenguang Yang, Zaojun Fang

Reports an IEEE Transactions on Industrial Informatics-accepted method, SC-DMPs, that redistributes dynamic-movement-primitive basis functions according to a stage-criticality index built from operator-robot interaction stiffness and cross-demonstration trajectory variability. On handwriting and three real-robot tasks, it reduces task-critical trajectory error (e.g., 32.5% lower RMSE at geometric hotspots versus classical DMPs across letter settings) while keeping a roughly 1 kB model and millisecond adaptation. This provides a compact, task-aware trajectory representation for precision assembly and other tight-tolerance motions.

Read the full paper (PDF)
arXiv
Sim-to-real NavigationExpert

EIDA: Execution-Interface Dynamics Adaptation for Real-to-Sim-to-Real Robot Navigation

Yiwei Qian, Shanze Wang, Qingyuan Hu, Xinming Zhang, Wei Zhang

EIDA is a preprint that learns execution-interface dynamics models from real robot velocity-command, pose, and feedback data and embeds them into a lightweight GPU simulator for navigation policy training. On a physical Unitree Go2 it reached the goal without collision in 20/20 static-scene trials versus 4/20 for a standard simulator-trained baseline, and it led learned policies on 100 BARN environments with 89.33% success under global guidance versus 80.78% for Nominal. It offers a cheaper, platform-specific sim-to-real transfer route without detailed actuator modeling.

Read the full paper (PDF)
arXiv
Visual Reward ModelsExpert

CriticHack: Evaluating Visual Rewards Under Robot Policy Optimization

Jiaxuan Luo, Xingguo Xu, Shanshan Wang, Yuhan Zhou, Zhen Zhang

This arXiv preprint introduces CriticHack, a closed-loop benchmark that optimizes robot policies against learned visual rewards and measures simulated outcomes independently. On a drawer task, fine-tuning a diffusion policy with Robometer rewards raised task success by 10.2 points but wrong-object failures by 10.9 points on 512 seeds, while ground-truth completion rewards did not amplify wrong-object behavior. It matters because reward models can look healthy on aggregate metrics while policy optimization amplifies specific semantic mistakes.

Read the full paper (PDF)
arXiv
Legged ManipulationExpert

ReCo: Response-Consistent Locomotion with Policy-Aware MPC for Legged Manipulation

Kuankuan Sima, Yichao Gao, Chenxi Gu, Kefan Zhao, Lin Zhao

In this preprint, the authors present ReCo, a framework that trains a quadruped locomotion policy to have a predictable command response and then couples it with policy-aware MPC to jointly plan base motion and a six-DoF arm for continuous manipulation. In simulation, ReCo cuts end-effector position RMSE by 28.7% and orientation RMSE by 27.4% versus the best baselines and succeeds in 75/100 runs versus 42/100 for the strongest baseline; the full stack runs onboard a Unitree Go2 with an ARX X5 arm. This matters because it makes continuous world-frame manipulation while walking practical without a full accurate contact model.

RL
Read the full paper (PDF)
arXiv
Multi-robot manipulationExpert

Watch, Infer, Coordinate: Inferring Robot Partner Constraints for Zero-Shot Coordination

Suyu Ye, Zheyuan Zhang, Vaishnav Tadiparthi, Hossein Nourkhiz Mahjoub, Ehsan Moradi Pari, Tianmin Shu, Homanga Bharadhwaj, Nakul Agarwal

Preprint. The authors introduce Watch, Infer, Coordinate, a benchmark and inference method for a helper robot to watch a constrained partner collaborate with a demonstrator, infer the partner's low-level physical constraints, then coordinate zero-shot on a new joint-carrying task. In simulation across three manipulation settings, the approach reaches 85–93% success on obstacle tasks, close to an oracle that knows the true constraints, and far above baselines. This matters for multi-robot fleets where one unit may degrade or fault and partners must adapt without explicit communication.

Read the full paper (PDF)
arXiv
Latent World ModelsExpert

Supervise What Decides Success: Criterion-Aligned Auxiliary Losses for Latent World-Model Planning

Takumi Hara, Kanata Suzuki

This preprint introduces a training-time auxiliary loss for latent world models: a temporary linear head regresses the physical quantities used in a task's success criterion directly from latent states. On PushT and cube it raises planning success by 3.5 and 3.4 absolute points over the same baseline, with significant paired-test gains, while leaving test-time model and inputs unchanged. It matters because success criteria can tell world models exactly which physical quantities the latent state must retain for reliable planning.

World Models
Read the full paper (PDF)
arXiv
UAV SwarmsExpert

Managing Context and Communication in Distributed Agentic UAV Swarms

Andrea Iannoli, Ivan Zyrianoff, Angelo Trotta, Lorenzo Gigli, Marco Di Felice

This accepted IEEE CCNC 2027 paper presents a fully distributed UAV swarm architecture in which each drone runs an independent Small Language Model, a bounded context manager, and a deterministic interest-aware gossip engine. In 10-UAV simulated search-and-rescue trials, it completes 100% of runs, whereas unrestricted flooding completes 70–85% and SLM-delegated forwarding completes 0%, while cutting inference tokens roughly in half and transmitting under 0.5 MB per mission versus 6–7 MB. This matters because it shows edge-deployed language-model agents can control swarms without central connectivity, context rot, or bandwidth blowup.

Read the full paper (PDF)
arXiv
Soft manipulationExpert

Learning a Resolution-Consistent Jacobian Field for Bio-Inspired Rigid-Soft Finger

Tianyou Liang, Haisen Zeng, Shanjun Chen, YiMing Zhu, Zhongyue Lu, Zirong Luo

This preprint introduces Jacobian Flow Matching (JFM), a Conditional Flow Matching-based learned Jacobian field for a tendon-driven rigid-soft finger. On real finger data, it cuts global average single-step RMSE by over 53% versus a pointwise baseline and improves sparse-sampling trajectory fidelity, reducing median RMSE by 14.43% at stride 8. It matters because it gives compliant dexterous hands a resolution-consistent local model usable for both prediction and trajectory optimization.

Read the full paper (PDF)
arXiv
VLA manipulationExpert

ChunkVLA-AM: Parallel Action Chunking for Vision-Language-Action Robot Control in Additive Manufacturing

Zhugang Liu, Kaichuang Zhang, Jinman Zhang, Pu Sun, Martha Asare, Jose Hernandez, Maxim Ermolinsky, Efren Saenz, Qi Lu, Jinghao Yang

This arXiv preprint describes ChunkVLA-AM, a deployment pipeline that adapts an OpenVLA-OFT vision-language-action model to a FAIRINO FR3 robot for additive-manufacturing post-print retrieval. The robot predicts and executes 8-step chunks of 7-D Cartesian actions in a cloud-edge loop and completed 39 of 42 physical pick-and-transfer trials, a 92.9% success rate. The work provides a concrete feasibility check for using VLA-based automation in a fixed manufacturing workcell.

VLA
Read the full paper (PDF)
arXiv
Safety-critical controlExpert

Finite-Data Safety Informativity Under Dynamic Asymmetric Actuation

Abhinav Sinha, Praveen Kumar Ranjan, Yongcan Cao

This preprint presents a finite-data safety certificate that checks whether a commanded input can keep a partially unknown nonlinear system within prescribed output bounds even when actuators have asymmetric limits and bounded tracking error. In a simulated vehicle-tracking study, a data-selection strategy produced certificates at 76.27% of 11,241 validation queries, versus 32.09% for uniformly sampled and 1.03% for consecutively sampled records, and an exact-parameter benchmark reached 86.26%. The work matters because it gives a deterministic, model-uncertainty-aware safety filter for high-assurance control where a reliable dynamics model is unavailable.

Read the full paper (PDF)
arXiv
Dexterous manipulationExpert

FlashDexRetarget: Accelerating Dexterous Manipulation Data Generation through Multi-Motion Retargeting

Kyungmin Lee, Sibeen Kim, Dongyoon Hwang, Yoonsang Oh, Donghu Kim, Youngdo Lee, I Made Aswin Nahrendra, Jaegul Choo, Hojoon Lee

This preprint introduces FlashDexRetarget, a reinforcement-learning framework that jointly retargets many human hand-object demonstrations into dexterous robot trajectories with one policy. On a 50-motion benchmark it reaches 90% retargeting success on the XHand using about 29 GPU-hours, compared with 46% at roughly 3,000 GPU-hours for CHORD. The approach matters because it could make large human demonstration datasets practical for training dexterous robots.

Dexterous Manipulation
Sharpa
Read the full paper (PDF)
arXiv
3DGS datasetExpert

3DROID: A Renderable 3D Gaussian Dataset with Measured Per-Scene Reliability

Wonguen Cho, Junhoo Lee, Nojun Kwak

This preprint introduces 3DROID, a DROID-derived dataset that turns 114 robot manipulation episodes into renderable 3D Gaussian scenes anchored to the robot's metric workspace, with per-scene calibration and reconstruction-reliability metadata. Combining refined camera extrinsics with pose conditioning improves held-out view PSNR from 12.57 to 15.81 dB for YoNoSplat and from 12.75 to 16.27 dB for ZipSplat. The work matters because view-consistent synthetic robot data are useful for manipulation only if they preserve real-world scale and robot-frame alignment.

Read the full paper (PDF)
arXiv
Marine simulationExpert

H-SPAR: Hydrodynamic-aware Simulation for Particle Transport and Autonomous Robots

Navid Zarrabi, Nariman Yousefi, Sajad Saeedi

This arXiv preprint describes H-SPAR, an open-source ROS 2/Gazebo simulator that couples a shared precomputed flow field to both current-induced drag on an uncrewed surface vehicle and Lagrangian advection of sampled particles. In path-planning tests, SVF-RRT* cuts planned upstream cost by 69.4% versus RRT*, but the advantage falls to 41.7% during execution with time-varying currents; sweep orientation shifts particle sampling rates by up to 22.2% under the full hydrodynamic configuration. It matters because marine autonomy and particle-sampling performance can now be benchmarked together under consistent hydrodynamics.

ROS 2
Read the full paper (PDF)
arXiv
Unified world-action modelExpert

UniWAM: Unified World-Action Model

Jiayi Chen, Wenxuan Song, Jingbo Wang, Shuai Zhou, Xicheng Gong, Zehua Fan, Ziyang Zhou, Junwu E, Haodong Yan, Fuhao Li, Qize Yu, Xu Huang, Pengwei Wang, Wen Chen, Shunbo Zhou, Haoang Li

UniWAM is a preprint introducing a unified robot foundation model that combines a vision-language reasoner, a video-generation world model, and an action predictor. It reaches 99.2% success on LIBERO, 92.6% on LIBERO-Plus OOD perturbations, 68.32% on RoboTwin 2.0 Clean2Random, and 82.5% real-robot instruction-following rate. The work matters because it shows how co-training on robot, human egocentric, and VQA data can improve robustness, generalization, and long-horizon manipulation.

VLA
Read the full paper (PDF)

Topic pages

Manipulation · 76VLA · 65Navigation · 35General robotics · 32Robot learning · 27Perception · 22Humanoid · 21Simulation · 15Locomotion · 13Safety · 11World Action Models · 5World-action model · 3Aerial manipulation · 3Dexterous manipulation · 3Sim-to-Real Manipulation · 3Social Navigation · 3

Papers come from arXiv robotics feeds. Where our summary is not written yet, you see the opening lines of the abstract.