Skip to content
#Data and simulation
Dec 4Thu
  1. SIGRobotics · X69

    Earth Rover Mini+ low-cost open-source autonomous mobile robot released, with 7TB of real teleoperation data

    Earth Rover Mini+ has been released. It is an open-source autonomous mobile robot priced under $300, has actually driven in multiple cities, comes with over 7TB of real teleoperation data, and supports LeRobot integration.

    Why it matters: The material gives a total unit cost of under $300 and 7TB of real street data, which lets readers judge how autonomous mobile robot experiments can move out of the lab.

  2. Dobot/越疆机器人36

    Dobot appears at IROS 2025, launches embodied intelligence robot platform combining humanoid, robotic arm, multi-legged, and wheeled forms

    At IROS 2025, Dobot exhibited the world's first embodied intelligence robot platform integrating humanoid, robotic arm, multi-legged, and wheeled forms, using a brain-cerebellum dual-system architecture. Its humanoid robot passed high-temperature and heavy-load aging tests, with precision reaching ±0.05mm; the X-Trainer dual-arm teleoperation AI training platform shortens the training cycle for new tasks by 70%, to about 2 hours. Dobot also cooperated with Tencent's Tairos platform, and the multi-legged robot Hexplorer achieved fully autonomous operation with high-precision 3D mapping and dynamic obstacle-avoidance guided tours.

Dec 3Wed
  2. AGIROS48

    AGIROS 25.06 released: over 1,500 ecosystem packages, TravoDDS, Alpha Platform, and AimRT three domestic components debut

    AGIROS 25.06 continues to enrich its ecosystem, with over 1,500 packages on systems such as openEuler-24.03-Lts and Ubuntu-22.04-Lts, supporting x86_64, aarch64, and RISC-V architectures. The release includes three domestic components: the high-performance messaging middleware TravoDDS, the Alpha Platform simulation software covering the full development, testing, training, and validation workflow, and the Modern C++-based lightweight runtime framework AimRT.

Dec 2Tue
  1. Pieter Abbeel76

    Amazon FAR open-sources Holosoma, a full-stack sim-to-real codebase for humanoid robots

    Amazon FAR has released Holosoma, a full-stack solution, and open-sourced a complete codebase covering multiple simulation backends, training, motion retargeting, and real-world inference. Pieter Abbeel shared and added that the infrastructure was built for humanoid robots and can also be readily adapted into a quadruped version (the quadruped part is already included), and that it contains a great deal of infrastructure experience and convenience tools the team relies on daily.

    Why it matters: The open-source full-stack codebase covers both humanoids and quadrupeds, so researchers can directly reuse its complete pipeline from simulation training to real-world inference.

Nov 28Fri
Nov 19Wed
  1. Tangible Robots · X42

    Tangible Robots unveils Eggie wheeled humanoid robot

    Yes. @tangiblerobots unveiled Eggie, a wheeled humanoid robot that isn't content with simple grippers. It is equipped with a full five-fingered bionic hand, designed for real, contact-intensive tasks. In a demo, Eggie wiped up a coffee stain in a real kitchen (not a staged lab setting), demonstrating the company's belief that real home robots need human-like dexterity, not shortcuts. CEO @bipashasen31 said: the world is built for humans, so robots need human hardware. The philosophy: no touch, no real AGI. Tangible is collecting tactile data in an extreme way—engineers wear sensor-packed exoskeletons to capture real tactile interactions, from gripping a glass to pressing a milk carton. The home is the long-term goal, but the company is starting from AI fundamentals and offering salaries of over $1 million to recruit top researchers. The wheeled humanoid robot race is already heating up, and now there is another contender betting that dexterity will win the home market!

Oct 27Mon
Oct 10Fri
  2. 天链机器人47

    Tianlian Robotics uses video learning to teach robots advanced motion

    Tianlian Robotics has published a video imitation learning training pipeline: extract reference motions with GVHMR/TRAM (or use motion capture datasets such as AMASS), then after human-to-robot joint mapping and training a motion orientation model, use PPO reinforcement learning in simulation with curriculum learning to progress from static poses to long-sequence complex motions, then optimize through domain randomization before deploying to the real robot, with fine-tuning via residual reinforcement learning or adaptive gains. The company says it has achieved key breakthroughs in dynamic force-control precision and stability, and that motions can also be reproduced in real robotic arm operation.

Sep 26Fri
  1. Keenon Robotics/擎朗智能47

    KEENON Robotics officially releases KOM 2.0, a self-developed VLA model for the service industry

    KEENON Robotics has officially released KOM 2.0 (KEENON Operator Model 2.0), which it calls the world's first VLA (vision-language-action) model for the service industry. The model uses a dual-system architecture with the K-Mind thinking system and the K-Act action system, is trained on hundreds of millions of real service interaction data points, and supports millisecond-level real-time decision-making.

Sep 2Tue
  1. LimX Dynamics48

    LimX Dynamics releases LimX DreamActor: a new embodied intelligence training paradigm combining Real2Sim2Real and real-robot reinforcement learning

    LimX Dynamics has introduced LimX DreamActor, an embodied intelligence training paradigm that for the first time deeply integrates Real2Sim2Real, imitation learning, and real-robot reinforcement learning into a full pipeline of "real-world environment data collection—simulation data pretraining—real-robot data post-training." The system can complete multi-view data collection using only a consumer-grade camera; through 3D reconstruction and physical parameter alignment it builds a highly realistic simulation scene, then uses a small amount of real-robot reinforcement learning to complete cross-domain transfer, aiming to improve sample efficiency, convergence speed, and deployment stability.

Aug 13Wed
  1. LimX Dynamics64

    LimX Dynamics showcases LimX Oli's human-like walking and TRON 1's extreme terrain capabilities at WRC

    Robot Lecture Hall reported on-site from the LimX Dynamics booth at the 2025 World Robot Conference. The full-size humanoid robot LimX Oli, 165 cm tall with 31 active degrees of freedom, made its first WRC appearance and went on sale, demonstrating outdoor live dancing and switching among multiple gaits such as a light quick step, model walk, and goose step, powered by a whole-body motion control algorithm combining traditional control, reinforcement learning, and imitation learning, with prices starting at 158,000 yuan.

    Why it matters: The author attended WRC in person and breaks down the gait switching, disturbance-rejection recovery, and teleoperation details at the LimX Dynamics booth item by item, so readers can understand its full-chain technology roadmap.

Jul 23Wed
  1. LimX Dynamics51

    SAIC Beijing and LimX Dynamics Sign Strategic Cooperation Memorandum to Build Joint Embodied Intelligence Laboratory

    SAIC Beijing and LimX Dynamics signed a strategic cooperation memorandum in Beijing, announcing the establishment of a joint embodied intelligence laboratory to conduct embodied robot algorithm R&D, system development, and toolchain deployment around automotive scenarios. LimX Dynamics will provide underlying technologies including robot bodies, whole-body motion control algorithms, VLA model frameworks, data engines, and toolchain platforms. The two parties will carry out humanoid robot data collection, training, and evaluation in automotive manufacturing scenarios, and gradually form a complete R&D process from data collection and model training to system testing.

May 7Wed
Apr 18Fri
Mar 25Tue
  1. Figure AI66

    Figure AI uses reinforcement learning to give Figure 02 humanoid robot a natural, human-like walk

    Figure AI released an end-to-end reinforcement learning walking controller that lets the Figure 02 humanoid robot learn a human-like gait in simulation by imitating human reference trajectories through rewards, including heel strike, toe push-off, and arm swing. Training runs in parallel across thousands of robots in GPU-accelerated physics simulation, collecting years of simulated data in hours, and combines domain randomization with kHz-level torque feedback control to achieve zero-shot transfer to the real robot; 10 Figure 02 units run the same neural network without individual tuning.

    Why it matters: The original text provides details on the training method and sim-to-real transfer for Figure 02's reinforcement-learning-based human-like walking, offering insight into its technical approach.

Mar 18Tue
  1. FieldAI39

    FieldAI Research Institute (FAIRI) studies embodied question answering in dynamic environments based on the NVIDIA Omniverse platform

    Field AI Research Institute (FAIRI) is collaborating with NVIDIA to study robotic embodied question answering (EQ&A) in dynamic environments. The team uses the NVIDIA Omniverse platform, Isaac Sim, Omniverse Replicator, and the USD Search API to build physically accurate 3D office scenes, simulate changes in the environment over time, and plans to open-source this long-term embodied question answering dataset.

Jul 29Mon
  1. FieldAI48

    FieldAI develops first risk-bounded robot foundation model FFM using NVIDIA Isaac platform

    FieldAI claims to have developed the first risk-bounded Field Foundation Models (FFM) robot foundation model, which enables multi-form robots to operate autonomously in hazardous, off-road, and other unstructured industrial environments without prior maps, GPS, or cloud communication, and has already been deployed at hundreds of sites.

Jan 26Fri
  1. 泡泡机器人SLAM · 微信公众号55

    M2DGR: A Multi-Sensor, Multi-Scenario SLAM Dataset for Ground Robots

    M2DGR is a large-scale SLAM dataset collected by a ground robot, comprising 36 indoor and outdoor scene sequences and about 1TB of data. Its sensor suite includes six fisheye cameras, a skyward-facing RGB camera, an infrared camera, an event camera, a visual-inertial sensor, an IMU, a lidar, a consumer-grade GNSS receiver, and a GNSS-IMU navigation system with RTK signals, all calibrated and synchronized and recorded in sync.

Oct 12Wed