MEKAWIRE
Research

Papers

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

199 papers
TopicAllManipulation · 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
LevelAnyBeginnerIntermediateExpert
arXiv
ManipulationExpert

DynaHarness: A Dynamic Physical Harness for Self-Evolving Robot Agents

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

DynaHarness is an arXiv preprint that adds a dynamic physical harness around a frozen vision-language-action policy: a slow Qwen3-VL-4B planner proposes capabilities, while a fast 2 Hz governor grounds, monitors, substitutes and recovers them. On LIBERO-Pro it reaches 75.2% success on 800 newly sampled states versus 17.5% for the frozen π0.5 policy, and its self-evolution gains transfer to new states. This gives robot-agent builders a retraining-free way to govern and improve existing policies from execution evidence.

VLA
Read the full paper (PDF)
arXiv
Sonar SLAMExpert

BatSLAM 2.0: Sequence-Verified Sonar Place Recognition in a Robust Pose Graph

Jan Steckel

BatSLAM 2.0 is a preprint describing a sonar-only simultaneous localization and mapping system that uses a biomimetic binaural acoustic front-end, sequence-verified place recognition, and a factor-graph pose graph. In 12 simulated long-range drives with calibrated odometry, it produced consistent maps with no wrong loop closures and a post-alignment trajectory error of 0.18–0.53 m; on a real beamformed sonar recording, it cut error from 3.62 m to 0.67 m. This matters for robots that must operate in darkness, smoke, or dust where cameras and lidar fail.

Read the full paper (PDF)
arXiv
Safe VLAExpert

Learning from Runtime Feedback through Failure-Bank Self-Evolution for Vision-Language-Action Models

Mingyue Cui, Zheyuan Liu, Yihan Zhu, Zheyuan Zhang, Meng Jiang

This preprint presents FailBank, a framework that turns an observe-only safety teacher's runtime corrections into training records for vision-language-action policies. On VLA-Arena static-obstacle tasks, it raises task success by 8.5 and 6.9 percentage points over base policies for two VLA backbones while cutting policy-induced cumulative cost by 35.6% and 23.8%. The method matters because it lets robot policies learn a persistent balance between completing a task and avoiding unintended contact, instead of relying on temporary runtime shields.

VLA
Read the full paper (PDF)
arXiv
Skill DiscoveryExpert

Game-Guided Skill Discovery through Self-Play for Playable Agent Control

Seungeun Rho, Jeonghwan Kim, Xue Bin Peng, Sehoon Ha

This preprint introduces Game-Guided Skill Discovery (GGSD), a self-play framework that learns a small set of discrete motor skills that humans can directly use to control simulated agents. Across Ant, Franka arm, and Unitree G1 embodiments, GGSD produced semantically distinct skills and let users with brief practice solve unseen maze and cube-push tasks with 84–100% success. It matters because it points to compact, human-playable skill interfaces for high-degree-of-freedom robots without task-specific retraining.

Read the full paper (PDF)
arXiv
SafetyExpert

Neuro-Symbolic Predicate Learning for Semantic Safe Robot Control

Zihan Ye, Jiayi Liu, Puze Liu, Jiayun Li, Georgia Chalvatzaki, Jan Peters, Kristian Kersting

This preprint introduces NEUPRO, a neuro-symbolic safety system that learns reusable visual safety predicates from human-written symbolic rules through a differentiable graph reasoner. On the REASON real-robot benchmark it reaches 92% mean safety-classification accuracy across seven tasks versus 55% for Qwen3.5 and 44% for DeepSeek-VL2, and it can explain violations in first-order logic. The result matters because it offers a path to interpretable, transferable safety constraints instead of opaque per-task cost functions.

Read the full paper (PDF)
arXiv
Tactile ExplorationExpert

Tactile Curiosity Drives Robot Interaction

Klemens Iten, Alexander Proshkin, Bhavya Sukhija, Stelian Coros, Andreas Krause, Pieter Abbeel, Carmelo Sferrazza

This preprint presents TacEx, a framework that directs reinforcement-learning exploration by weighting tactile predictive uncertainty instead of total state uncertainty. In simulation, tactile-driven exploration produces contact-rich examples, emergent grasping without task rewards, and improved offline pick-and-place and frozen VLA post-training. It matters because it makes manipulation data collection and VLA adaptation far more sample-efficient by focusing learning where contact occurs.

RL
Read the full paper (PDF)
arXiv
Adaptive action horizonsExpert

SplineWAM: Adaptive Action Horizons for World Action Models via B-Spline Representations

Jun Guo, Xiaoshen Han, Qiwei Li, Nan Sun, Peiyan Li, Heyun Wang, Hang Lai, Weinan Zhang, Xinghang Li, Huaping Liu

This preprint introduces SplineWAM, which replaces the fixed-length action chunk of a world action model with a fixed-size window of cubic B-spline knot times and control points, letting each prediction adapt its temporal horizon and resolution. On LIBERO-Plus and RoboCasa it improves success rate by 8.2 and 4.4 points over an action-chunking WAM while issuing 22% and 26% fewer policy calls per episode; on three real bimanual tasks it matches or beats the baseline while decoding 1.2–1.6× more executed motion per call. This matters for cloud-served robot fleets because fewer calls per task directly increase throughput.

Read the full paper (PDF)
arXiv
MAPFExpert

Belief-Aware Multi-Agent Path Finding under Map Uncertainty

Viraj Parimi, Shao-Hung Chan, Han Zhang, Jingkai Chen, Brian Williams

This arXiv preprint describes MAGIC, a framework that adds online spatial belief inference to multi-agent path finding under unknown map obstacles. On standard MAPF benchmarks it reduces executed sum of costs on 96.3% of instances and scales to 800 agents. The work is relevant for warehouse robot fleets that must route around fallen pallets, spills, or other local map discrepancies without building expensive contingent plans.

Read the full paper (PDF)
arXiv
UAV NavigationExpert

DiffWAM: A Fast and Efficient Navigation World Action Model

Mo Zhu, Yuze Wu, Xijie Huang, Xiao Cui, Fei Gao, Xin Zhou

DiffWAM is a preprint that introduces a UAV navigation world-action model. It recovers camera trajectories directly from the predictive features of a frozen video model, avoiding future-video decoding and multi-frame geometric reconstruction at deployment. The paper reports a trajectory RMSE of 0.3492 m and adds FastDreamer, an execution system that overlaps computation with flight for continuous UAV control.

Read the full paper (PDF)
arXiv
VLAExpert

When Instructions Retrieve Trajectories: Diagnosing and Mitigating Generalization Failures in VLA Models

Hung-Jen Chen, Yu-Hsun Hou, Yan-Hong Chen, Yan-Fu Chen, Binghua Cai, Min Sun, Chun-Yi Lee

This preprint identifies a failure mode in vision-language-action (VLA) policies where instructions retrieve familiar trajectory families but do not bind language to scene-dependent action choices, so robots can execute a clean but wrong task. It introduces Equivariant Counterfactual Training (ECT), a paired data and loss scheme that supplies same-instruction demonstrations with different scenes and trains counterparts jointly. In controlled LIBERO-PRO tests, mean position-swap success rises from 36% to 59%, and on a real UR5e, unseen-position success rises from 3/40 to 35/40, showing the approach reduces counterfactual task errors.

VLA
Read the full paper (PDF)
arXiv
Submovement decompositionExpert

Identifiable Decomposition of Submovements in Human Hand Trajectories

Adrian Prados, James Hermus, Ramon Barber, Sylvain Calinon

The authors present Sub-ID, a submovement decomposition method for human hand trajectories that uses a spatiotemporal kernel correlation as an identifiability criterion, and it is described as a preprint. On synthetic tests with 3, 8, and 15 overlapping primitives it recovers ground-truth parameter distributions where baselines degrade or fail, holding position error to 0.012 m at K=15 and keeping critical primitive overlaps to about 3%. This gives robotics and motor-control researchers a practical way to extract physiologically grounded motion primitives from long, three-dimensional movements.

Imitation Learning
Read the full paper (PDF)
arXiv
Egocentric dataExpert

Ego4WAM: What Matters When Scaling Egocentric Human Data for Robot Learning?

Zhihao Sun, Liu Liu, Xinjiang Wang, Haoyi Jiang, Wei Feng, Huiqiang Zhang, Xiaosong Jia, Zhizhong Su, Zuxuan Wu

Preprint. The paper presents Ego4WAM, a controlled study of how to scale and stage egocentric human data for bimanual robot manipulation under a world-action model. Its headline result is that video-only world-model pre-training on 15K hours of egocentric video plus only about 0.1K hours of robot data reaches a 20.29 average RoboDojo score and 14.35% success rate, roughly matching or exceeding several models trained with far more robot data. The work matters because it identifies which data properties—human-robot alignment, duration, task diversity, and supervision—actually improve closed-loop robot generalization.

Read the full paper (PDF)
arXiv
Continuum sensingExpert

Magnetic based In-situ Self 3D Pose Estimation for a Modular Soft Tendon-Driven Continuum Robot via IMU-Fusion

Zheng Cao, Guo Ning Sue, Xiangyun Bu, David Quinn, Junzhe Hu, Carmel Majidi

This arXiv preprint introduces a camera-free shape-sensing system for a modular tendon-driven continuum robot. Onboard IMUs and PCB-coil magnetic fields are fused through a learned joint model, producing 16.7 Hz backbone updates and pooled 10.0 mm backbone RMSE across 20 real-robot trials. It matters because it enables closed-loop control of soft manipulators when external vision is unavailable or occluded.

Read the full paper (PDF)
arXiv
ManipulationExpert

Dream4ACT: A Shared Visual Action Interface for Multi-Embodiment Video-Action Modeling

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

Dream4ACT is a preprint video-action world model that turns target robot joint configurations into four fixed virtual-camera 'action views' rendered from URDF models, so a single model can control different robot arms without per-robot action heads. On RoboTwin 2.0 it averages 88.98% success, scores 65.66 on TriWorldBench, and on two common real-world tasks averages 85.0–90.0% across four robot platforms. It matters because the shared visual action interface removes physical-camera calibration for action encoding and uses training-free joint recovery, simplifying multi-embodiment manipulation models.

Read the full paper (PDF)
arXiv
Soft Pneumatic ActuatorsExpert

TO-mdiSPAs: Topology Optimization of multi-directional Soft Pneumatic Actuators

Swagatam Islam Sarkar, Prabhat Kumar

This preprint introduces a topology optimization method for designing multi-directional soft pneumatic actuators using Darcy-law pressure modeling and a robust three-field formulation. Optimized chambers are assembled into a simulated three-arm gripper; Abaqus tests at 0.15 MPa show single-arm tip displacements up to about 15.8 mm, with bending directions tracking the vector sum of activated chamber pressures. If experimentally validated, it could replace heuristic soft actuator design with systematic multi-axis bending for soft grippers.

Read the full paper (PDF)
arXiv
World-action modelExpert

Magic-W0: A Structured World-Action Foundation Model for Physical Intelligence

Xuhua Chen, Zhenhan Yin, Yuan Zhang, Lingfeng Zhang, He Zheng, Tong Mu, Shun Zuo, Dian Zhou, Di Wu, Xuan Zhou, Shaojie Wan, Rongtian Shen, Qiulong Xu, Yiduo Li, Yinglong Wang, Yanqian Wang, Kun Wang, Tao Zhang

This preprint introduces Magic-W0, a robot manipulation foundation model that couples continuous action generation with explicit latent predictions of current 3D geometry, action-induced 3D motion, and future semantics. On RoboDojo-Sim it posts the highest average score among world-action models at 27.10, and on five real-robot tasks it reaches 94.6% average success after fine-tuning, beating π0.5 at 91.8%. The result matters because it shifts policies from blind imitation toward predicting how candidate actions will change the physical world, with gains in generalization and long-horizon manipulation.

Physical Intelligence
Read the full paper (PDF)
arXiv
GroundingExpert

GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives

Qize Yu, Lianrui Fan, Boyu Chen, Jiaqi Liang, Xini Ding, Yue Chen, Zetian Song, Yuran Wang, Yi Zou, Kaixuan Wang, Tianxing Chen, Wenxuan Song, Bohan Zhou, Mingleyang Li, Siqiao Huang, Yuqi Ye, Caigao Jiang, Wei Wei, Ruihai Wu, Hang Zhang

This preprint introduces GroundingPI, a 4B grounding foundation model that predicts object points and boxes as quantized token coordinates rather than using a general-purpose vision-language backbone. Across 34 grounding benchmarks it averages 73.68%, ahead of a larger GPT-6 Astra baseline at 71.54%, and as a visual backbone it improves downstream manipulation (RoboTwin 2.0, RoboCasa-GR1) and autonomous driving (nuScenes L2 0.296 m). The result matters because it argues grounding is a distinct perceptual layer that can make embodied foundation models more precise.

VLARL
Physical Intelligence
Read the full paper (PDF)
arXiv
Aerial ManipulationExpert

From Local Whole-Body VLA Behaviors to Scene-Scale Aerial Manipulation

Weixiang Guo, Rui Jin, Haotian Jin, Xinhang Xu, Ruiyang Liu, Haoran Zhao, Yi Wang, Weiqi Gai, Kun Cao, Lihua Xie

This preprint introduces a framework for scene-scale aerial manipulation on an articulated uncrewed aerial manipulator, combining synthetic whole-body VLA training, measured-progress-aligned trajectory realization, and scene-graph-guided mission composition. In simulation, local skills achieve 39/60 successes under oracle handoff, and full multi-site missions achieve 21/50 (42.0%), while a monolithic whole-task VLA baseline achieves 0/50. Physical trials validate representative tasks without platform demonstrations, reducing risk and data cost for aerial manipulation.

VLA
Read the full paper (PDF)
arXiv
Preference LearningExpert

PrefPI: Preference-Guided Steering into Out-of-Distribution Behaviors

Seungeun Rho, Wontaek Kim, Danfei Xu, Sehoon Ha

This preprint introduces PrefPI, an iterative framework that steers pretrained generative robot policies toward user-preferred behaviors using only relative preference labels on the robot's own rollouts. On a real-robot cube pick-and-place task, it lifted object transport height from 10.7 cm to 19.8 cm after 150 labeled trajectories and cut completion time from 19.8 s to 10.8 s. It matters because it shows preference feedback can push policies outside their original behavior distribution without new demonstrations or reward functions.

VLA
Read the full paper (PDF)
arXiv
Floorplan SLAMExpert

MVP-SLAM: Multi-Camera Visual-Inertial Floorplan-Prior SLAM

Asier Bikandi-Noya, Miguel Fernandez-Cortizas, Muhammad Shaheer, Holger Voos, Jose Luis Sanchez-Lopez

This preprint introduces MVP-SLAM, an online visual-inertial SLAM system for construction sites that uses an as-planned floor plan to correct drift using only two back-to-back fisheye cameras and an IMU. It ranked 2nd of 22 teams in the Localization task of the Hilti–Trimble SLAM Challenge 2026 with 0.29 m mean RMSE, and 5th of 62 teams in SLAM with 0.24 m, the best among systems that integrate floor plans online. The work matters because it enables drift-bounded, plan-aligned localization during active site traversal without depth sensors.

Read the full paper (PDF)

Topic pages

Manipulation · 27VLA · 21Perception · 12General robotics · 11Navigation · 10Humanoid · 9Robot learning · 8Safety · 5World Action Models · 5Simulation · 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.