Open Artifacts Latest coverage

MIRA: A Modular Open-Source Micro-UAV for Indoor Research

This paper presents MIRA, an open-source micro-UAV designed for indoor research. Built around a 3D-printed PLA airframe with detachable arms and a containerized software package, MIRA supports modular customization and rapid development. The system is evaluated through autonomous flight tests, showing low-latency communication and stable structural behavior during dynamic maneuvers. All design files and software are released openly to support replication and extension by other laboratories.

Online World Modeling Enables Real-World Inverse Reinforcement Learning from Observation

This research presents MPAIL2, the first method to learn visual manipulation in the real world from scratch using observational learning via Inverse Reinforcement Learning from Observation (IRLfO). It achieves 82% performance in pick-and-place tasks within 40 minutes, surpassing reinforcement learning and behavior cloning approaches with comparable interaction and demonstration budgets.

Ropedia W0: Scaling Loco-Manipulation World Models across Embodiments with Human Experience

This research presents Ropedia W0, the first egocentric loco-manipulation world foundation model spanning humans and robots with diverse embodiments. The model is trained on 10k hours of human egocentric data and 3,000 hours of robot data with unified multimodal annotations. It achieves state-of-the-art performance across five cross-embodiment benchmarks and supports real-time VR interaction after distillation.

PhantomTac: Hijacking Robotic Tactile Systems with Deploy-and-forget Tags

This research introduces PhantomTac, a physical-layer security attack on magnetic tactile sensors used in robotic manipulation. By attaching a thin, battery-free magnetic tag to an object, an attacker can spoof force readings and compromise robotic control. The attack is 'deploy-and-forget' and can be concealed with a barcode sticker. Real-world evaluations on robotic arms show over 95% attack success rate under certain conditions, with a proposed defense mechanism based on multimodal consistency.

VLA-Roll, Fewer Denoising Steps, Better Control via Adaptive Action Reuse

This research proposes VLA-Rolling, a framework that reuses action tails from vision-language-action models to enhance control efficiency. By adapting denoising budgets and refining actions through confidence-guided steps, the method achieves faster inference and improved success rates across multiple benchmarks.

DexOAK: Object-Aware Kinematic Retargeting

DexOAK is a learning-based framework that generates contact-consistent robot hand references from human motion-capture data. It uses an interaction-graph Laplacian objective to reproduce object-relative interaction geometry, and a feed-forward network conditioned on human keypoints and object point clouds to learn retargeting. Object-aware finetuning refines the network under contact, non-penetration, and self-collision losses, improving performance on tasks like OakInk-v2 and ARCTIC. The model transfers to unseen data and enables dexterous robot data generation from human data.

Self-Crystalizing Behavior Trees: Amortizing Foundation-Model Reasoning into Deterministic Control for Autonomous Drones

This research proposes Self-Crystallizing Behavior Trees (SCBT), a method that integrates foundation models into deterministic control systems for autonomous drones. SCBT uses an LLM as a compiler to generate and refine control patches during runtime, which are then crystallized into deterministic behavior trees. The approach demonstrates improved mission success rates compared to unpatched and hand-coded trees, though it faces challenges in correctly attributing certain failure scenarios.

T(R,O) Grasp++: Cross-Embodiment Dexterous Grasping in Cluttered Environments at Scale

This research introduces T(R,O) Grasp++, a scalable diffusion-based framework for cross-embodiment dexter, grasping in cluttered environments. The model achieves an average success rate of 88% across eight dexterous embodiments, with 0.3s inference latency and improved sample efficiency.

Compile Once, Run Cheap: Frozen, Portable Skills for Embodied Agents, and What Recursive Self-Improvement Adds

This research proposes Skill-RSI, a framework for creating reusable manipulation skills for embodied agents through recursive self-improvement. Skills are compiled in simulation and run as standalone code or under a cheap caller, achieving high success rates on new layouts. The study evaluates performance across 7 RoboTwin 2.0 tasks, demonstrating the effectiveness of inheritance over from-scratch rewriting and the cost-efficiency of frozen skills.

Localization and Neural Splatting on the Edge: An FPGA Scene Memory for Robots

This research presents LENS, an edge scene-memory acceleration system for resource-constrained robots and autonomous vehicles. LENS runs on an AMD KR260 FPGA/ARM platform, combining an INT16 SCR accelerator and a fixed-point 3DGS renderer to enable efficient localization and rendering without a GPU. The system achieves performance comparable to GPU-based methods while reducing power consumption by up to 5.7x.

UMI-WM: Interactive World Modeling for Biman-ual Manipulation from Wrist Cameras

UMI-WM is an action-conditioned bimanual world model that jointly generates both wrist views from observation history, per-arm relative camera poses, and gripper widths, with cross-view consistency, action following, and visual fidelity. The model outperforms baselines in action following and generates paired wrist videos 6.9 times faster than the Teacher model.

Isaac Lab 3.0 Released: Multi-Backend Architecture for Robot Learning

Isaac Lab 3.0 is now generally available, offering a unified framework for robot learning with support for multiple physics, rendering, and visualization backends. Key features include Newton physics, OV libraries, and Isaac Sim integration, along with improved simulation tools and reinforcement learning compatibility.

Pulkit Agrawal@pulkitology· 19:02SignalEditorial score7878

This paper presents a breakthrough in robotic manipulation by showing that contact-based joint position signals can enable precise, zero-shot insertion tasks such as pegs, gears, and nuts without cameras or tactile sensors. The approach leverages joint drift to perform blind, fine-grained assembly tasks, marking a significant step toward general-purpose robotics.

Swift-ROS2 3.0: Native Swift ROS 2 Client Library with Generated Common Interfaces and Own Organization

Swift-ROS2 3.0 is a stable release of a native Swift client library for ROS 2, enabling direct integration with ROS 2 graphs using Zenoh or DDS. It includes generated common interfaces, a new GitHub organization, and support for multiple platforms, with improved compatibility and a migration guide for users upgrading from 2.x.

U.S. Army Launches New Robotics Technician Role at Fort Bragg, Plans Army-Wide Expansion

The U.S. Army has introduced a new warrant-officer job, Military Occupational Specialty 390A, training robotics technicians to build, reprogram, and sustain robotic systems. The first 10 graduates completed a 19-week course at Fort Bragg, focusing on technical skills and adaptability in contested environments. The role is part of a broader Army push for autonomy and robotics integration across all units.

World Models × Embodied Intelligence | 2026 Five Representative Companies' Technical Paths and Scene Deployment Observations

This article observes the technical paths and scene deployment progress of five Chinese companies in the field of world models and embodied intelligence. It evaluates their core competencies and development prospects, emphasizing the transition from parameter scale to system-level performance and the importance of real-world data feedback in model iteration.

Asimov Open SDK, Humanoid Robot Competition Shifts to Developer Ecosystem

Menlo Research has released the Python SDK for its Asimov 1 humanoid robot, enabling developers to control movement, access sensors, and integrate media. While the SDK is open-source under Apache 2.0, the control layer Asimov Edge remains unverified. This marks a shift in the industry toward software-driven development, with challenges in real-world integration and safety.

538 Hours of 'Extremely Messy' Human Data, Real Robot Takes Less Than an Hour: Hong Kong University Teaches Robots to Unpack Packages, Use Hot Glue Guns, and Make Cold Drinks

The MMLab team at the University of Hong Kong proposed the EgoWild2Dex method, using uncurated real human first-person operation data to train robots, successfully completing complex tasks such as unpacking packages, using a hot melt glue gun to fix figurines, and making cold drinks, with an average success rate of 96.7%. The study aligns human and robot perspectives through the GeoFormer module and adopts a progressive human-robot joint training paradigm, unifying open scene data, task-related data, and real robot data into the robot's action space.

Self-Building Labs

This paper introduces the self-building laboratory (SBL), a system that designs, configures, and operates its own laboratory setup given a high-level scientific goal. SBL can start from an empty room or an existing self-driving laboratory and build missing capabilities including lab layout, digital twin, robot skills, and experimental workflows. The system is demonstrated across different robots and setups, scaling from a single workstation to multi-robot laboratories. Validation is provided through a real-world quantum-dot synthesis experiment, showing that SBL shifts human researchers from manually configuring device automation to specifying scientific objectives, making scientific automation more accessible, flexible, and scalable.

HexaShell: A Universal Harness for Robot Coding Agents in Simulation and the Real World

This paper presents HexaShell, a thin, task-agnostic harness designed to test general tools for robot coding agents.