MEKAWIRE
Research

Papers

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

276 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
Federated 3D PerceptionIntermediate

FedCKA: Representation-Guided Layer Personalization for Federated 3D Perception Across Driving Domains

Jolle Verhoog, Ali Burak Ünal, Holger Caesar

This preprint presents FedCKA, a federated learning method that uses layer-wise Centered Kernel Alignment scores to decide which parts of a multimodal 3D object detector should stay local versus be shared across clients. On a five-domain nuScenes split covering Boston and Singapore, day/night and clear/rain, FedCKA reaches a validation-weighted NDS of 0.635, versus 0.545–0.559 for the strongest prior personalized baselines, about 7 percentage points higher. It matters because it removes the need for hand-picked layer partitions or fixed personalization ratios in cross-fleet driving perception.

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
Humanoid Tool UseIntermediate

HumanoidToolBench: Benchmarking Humanoid Tool Use from Selection to Mobile Execution

Kyochul Jang, Seohyeon Park, Ohchul Kwon, Sangjun Park, Junhyeok Choi, Seungyeop Yi, Chaeyun Kim, Sangkyu Lee, Idan Szpektor, Avi Caciularu, Jongmin Park, Youngjae Yu

HumanoidToolBench is a preprint benchmark and dataset for humanoid tool use, containing 18 tasks across three scenarios, three execution levels, and standard/decoy tool sets, along with 3,094 teleoperated demonstrations on simulated and real Unitree G1 robots. Seven policies were evaluated in simulation and three on the real robot, revealing large gaps between selecting the right tool and actually completing the task. Focused GR00T N1.7 probes further show reduced selection accuracy on unseen tools and continued execution under unrelated instructions.

Humanoid
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
Quadruped locomotionIntermediate

PROMO: Preference-conditioned Multi-Objective Reinforcement Learning for Quadrupedal Robots

Amr Mousa, Rifny Rachman, Neil Karavis, Michele Caprio, Richard Allmendinger

In this preprint, PROMO conditions a single quadruped locomotion policy on a three-way semantic preference over tracking, stability, and energy efficiency. On a Unitree Go2, changing only the preference reduces specific energy by up to 30.4%, position error by 38.7%, and peak body-attitude deviation by 59.0% relative to a balanced setting. This gives legged robots an operator-facing trade-off dial without retraining or switching controllers.

RL
Read the full paper (PDF)
arXiv
Failure recoveryIntermediate

Recova: Agent-Guided Failure Recovery for Autonomous Robotic Manipulation

Isabella Liu, An-Chieh Cheng, Johan Bjorck, Zhiding Yu, Hongxu Yin, Jan Kautz, Linxi Fan, Yuke Zhu, Sifei Liu

This preprint presents Recova, an agent-guided framework that jointly develops task execution and failure recovery in a reconstructed digital twin and refines both through real-robot data collection. It attains 78.8% mean success on LIBERO-Pro and 64.9% on MolmoSpaces, versus 71.7% and 38.0% for the strongest baselines; on four real-robot tasks it reaches 87.5% success and cuts observed human intervention from 87.5% to 0% over four collection rounds. The work matters because it turns failures into reusable recovery skills and reduces the human supervision needed to keep manipulation policies running.

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
Motion PlanningIntermediate

RUL-Aware RRT*: Degradation-Balanced Motion Planning for Robotic Manipulators

Haibo Li, Zhiguo Zeng, Xu Li

This preprint introduces RUL-aware RRT*, a motion planner that adds joint remaining-useful-life penalties to standard RRT* so a robotic manipulator distributes wear across actuators. In simulated UR5 pick-and-place trials it extended time-to-first-failure by 48–56% in a localized-degradation scenario, and improved bottleneck lifetime by 23.8–29.2% in a heterogeneous-degradation scenario. It matters because it connects predictive maintenance to path planning rather than leaving health information at the monitoring layer.

Read the full paper (PDF)
arXiv
Surgical roboticsIntermediate

Ex vivo breach detection using electrical conductivity during robotic pedicle drilling in the spine

Jorge Andrés Pérez Velásquez, François Teyssere, Thibault Chandanson, Quentin Grimal, Brahim Tamadazte

This preprint presents a robotic pedicle-drilling system that uses a SpineGuard electrical bioimpedance drill tip and a real-time dual-threshold algorithm to stop drilling before a spinal canal breach. In ex vivo tests on 51 fresh porcine vertebrae, it prevented breaches in 100% of cases, with 6 grade A and 45 grade B results and a mean canal deformation of 0.7 mm. The work offers an imaging-free safety layer for robotic spine surgery.

Read the full paper (PDF)
arXiv
Underwater RoboticsIntermediate

Towards Physical Underwater Robotic Assistance for Scuba Diver Movement in Confined Spaces

Demetrious T. Kutzke, Junaed Sattar

Preprint: The authors built RADMCS, a low-cost wearable thruster pack that straps to a scuba tank and gives divers haptic yaw cues to hold a set distance from walls or structures. In pool and ocean tests with eight divers, perceptible guidance required only about 10% of maximum thruster force; with stable visual distance estimates, the robot issued correct left/right corrections. This suggests a practical alternative to bulky exoskeletons for diver safety in confined underwater work.

Read the full paper (PDF)
arXiv
Multi-Robot ManipulationIntermediate

DuoMind: Enabling Distributed Multi-Robot Coordination with Semantic Communication

Hanchu Zhou, Dechen Gao, Hang Wang, Brendan Lynch, Boqi Zhao, Qiyao Ma, Raman Goyal, Junshan Zhang

In this preprint, the authors introduce DuoMind, a distributed multi-robot framework that pairs per-robot VLM orchestrators with low-level VLA action policies and structured semantic messages. Across two simulation benchmarks, it raises long-horizon success substantially over finetuned single policies, for example 39.25% vs 1.00% on Cook Pot and 78.00% vs 52.25% on Hang Bag. The work matters because it shows multi-robot coordination can be added to off-the-shelf foundation models without centralized control or joint multi-agent training.

VLA
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
MAV guidanceIntermediate

LiDARFlow: Real-Time Panel-Based MAV Guidance in Unknown Environments

João Machado, Zeynep Bilgin, Matthieu Verdoucq, Murat Bronz

This preprint describes a lightweight onboard guidance system for micro aerial vehicles in unknown environments, combining a guiding vector field for nominal motion with panel-method potential-flow obstacle avoidance. In indoor flight tests at 0.5 m/s, a quadrotor using only a Livox MID-360 LiDAR and Raspberry Pi 5 successfully completed waypoint-navigation and direction-following tasks while avoiding all obstacles. The result matters because it shows map-free sense-and-avoid can run in real time on constrained onboard hardware, reducing operator workload for cluttered or emergency missions.

LiDAR
Read the full paper (PDF)
arXiv
AMR OperationsBeginner

Autonomous mobile robot operations logistics: a dataset of jobs, dispatch events and robot states

Jan-Felix Klein, Yongkuk Jeong

This preprint releases MoRoOp, a dataset linking 1,382 jobs, 4,815 operations, 19,352 dispatch events and 140,386 robot-state observations from nine eight-hour shifts of a single autonomous mobile robot in a laboratory kit-supply scenario. The data combine planning and control records with robot telemetry, including per-wheel battery state and navigation diagnostics, and deliberately retain operational disturbances. It provides a missing single-resource reference for evaluating AI-based dispatch agents, disturbance detection, operation prediction and data-driven simulation in production logistics.

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)

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.