Technical Directions
Robotics coverage relating to open artifacts.
309 selected reportsLast 30 days 306 recordsAll coverage 824 records
This research presents LOGIV, a framework for agentic robot execution that uses an explicit task graph to link symbolic planning, observation-based verification, and embodied action.
This research presents a three-stage framework for dexterous retargeting that aligns human and robot hand kinematics and tactile information through contact wrench space. The method achieves 96.7% replay success in real robot experiments, demonstrating effective transfer of physical interaction data for manipulation tasks.
This research paper introduces a method to transfer robot data across diverse embodiments and controllers without conflicting action interpretations. The proposed framework uses a transformer context encoder to summarize behavioral interactions, enabling a single policy to adapt in context. Experiments show the method improves average success by 33 percentage points over naive data pooling, achieves 50% success on unseen controller modes, and 52% on unseen controller gains. The approach is demonstrated on contact-rich tasks like USB insertion and surface wiping, with results available at https://controller-transfer.github.io.
This research investigates how an 8B-scale navigation system should organize information for zero-shot vision-and-language navigation.
At the 2026 Zhiyuan Innovation Day forum in Shanghai, Zhiyuan presented its transition from stage demonstrations to industrial deployment. The company unveiled the GO-3 Preview foundation model, Genie Master agent framework, and the G2 Max heavy-load industrial robot. Specific metrics highlighted improvements in task success rates through collective experience learning and post-training scaling. Early deployments are occurring in electronics manufacturing and retail logistics settings.
On October 29, 2026, Angtu Investment announced the completion of an angel round investment in Linghang Zhixing Robotics (Shanghai) Co., Ltd. The funding aims to support R&D in intelligent robot end-effectors and advance industrial automation technologies. Founded on December 20, 2023, the company specializes in flexible tool-switching solutions for robotic applications across industries such as welding, material handling, assembly, and electronics manufacturing.
CVTE (002841) announced in October 2026 that its embodied intelligence products have moved beyond concept to mass commercial deployment. The company's commercial cleaning robots are operating in airports and retail centers across Europe, Japan, and South Korea, with Q3 overseas orders up 217%. Industrial quadruped robots (CV-QUAD-X1) are deployed for inspection in battery manufacturing plants, while flexible robotic arms equipped with safety-certified OS are used in vocational training. The company attributes improved cash flow to streamlined production cycles and new credit settlement systems.
In October 2026, embodied AI financing trends shifted upstream toward core components like tactile sensors and electronic skin. While the firm highlights mass production capabilities and orders from major integrators, challenges remain regarding standardization, cost, and durability before tactile skins become essential infrastructure.
MIT engineers have developed a soft robotic enteroscope that can navigate the small intestine, perform imaging, deliver drugs, and remove tissue samples. Inspired by snake locomotion and kirigami, the robot uses inflatable actuators and textured coatings to enhance traction and maneuverability, offering a potential alternative to traditional endoscopic procedures.
UT Robotics, the first publicly listed company in the humanoid robotics sector。
This paper introduces a training recipe and learned safety filter for dexterous in-hand object pose reaching on a LEAP hand. The approach uses diverse resets, generated grasp datasets, an adaptive friction curriculum, and system identification to achieve zero-shot transfer from simulation to real hardware using either motion capture or a single wrist-mounted depth camera. Over 13.3 hours of real-robot evaluation across 4,800 unseen goals on four objects, the state-based policy reaches 95.2% of goals within 2 cm and 0.4 rad, while the safety filter reduces object drops by 75% while maintaining 91.5% goal reach. The full recipe is released as an open artifact for studying performance, reliability, and safety in high-dimensional dexterous systems.
VicOne LAB R7 explores how adversarial inputs can alter robot behavior, challenging safety assumptions. The article discusses risks from manipulated sensor data, cyber attacks, and the importance of testing safety systems against deliberate threats. It also outlines five key questions for safety and security teams to ensure robot behavior remains safe under adversarial conditions.
This research presents RynnVLA-Latent, a framework that converts heterogeneous interaction videos into scalable supervision for robot policy pretraining. By learning continuous, 3D-grounded latent actions from visual transitions without requiring native robot controls, the system achieves high success rates on benchmarks like LIBERO (98.8%) and LIBERO-Plus (84.7%), as well as strong performance on real-world manipulation tasks across dexterous-hand and mobile-gripper platforms.
This research presents MOON, a framework that equips frozen vision-and-language navigation policies with lightweight modules for detecting deviations and recovering from them. By clearing visual history upon deviation detection and training a recovery policy via GRPO, MOON improves success rates on R2R-CE and RxR-CE benchmarks by 5.2 and 6.0 points respectively, outperforming compared methods without retraining the base policy.
Zhiyuan Robotics has deployed the G2 Max, an industrial-grade embodied robot, in JD Logistics' Zhi Wang warehouse for inbound handling tasks. The robot can carry up to 50kg with high precision, achieving over 99% operational success rate. This marks a real-world application of embodied intelligence, with JD Logistics emphasizing the importance of industrial scenarios for testing and refining such technologies.
Neura Robotics, a German humanoid robot company, is shifting focus from hardware production to training infrastructure. Their TUM RoboGym and Neuraverse platform aim to systematize the teaching of physical tasks, enabling scalable and reusable skills across different robots and industries. The company emphasizes the importance of real-world data and physical interaction in training robots for industrial applications.
110 humanoid robots completed complex synchronized actions in 5 minutes and 43 seconds, successfully breaking the Guinness World Record. The system achieved high levels of autonomous operation, including autonomous positioning, dynamic formation, and task scheduling, marking an important step toward the practical application of humanoid robots.
This paper introduces OpenTac, a novel resistive tactile skin and full-stack ecosystem designed for customizable, scalable, and transferable 3D tactile sensing.
This paper presents WholeBodyMem, an object-guided perceptual memory system that retains pre-history information for humanoid loco-manipulation in dynamic environments. By using SAM3 to track task objects and causally selecting key frames within an adaptive budget, the action expert integrates these frames via cross-attention with object tokens encoding appearance, geometry, and time. The authors also release HuMeGo, a benchmark featuring six simulated and six real-world Unitree G1 tasks. WholeBodyMem improves success rates from 29.1% to 72.6% in simulation and from 36.7% to 88.3% on the real robot, while also enhancing performance on standard SIMPLE tasks from 70.2% to 86.9%.
ZeroDex is a zero-shot framework for long-horizon dexterous manipulation that grounds language instructions into executable 3D task plans using calibrated multi-view RGB images. It extends vision-language model (VLM) grounding from 2D to 3D by fusing multi-view data, enabling contact points, placement targets, and tool-motion anchors. The system executes complex instructions by decomposing them into atomic tasks using a small library of primitives, and outperforms zero-shot visual-prompting and constraint-based baselines. It also demonstrates robustness to intermediate failures and generalization to novel objects and tool-use tasks.
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).