Dexterous Hand Practice 22 builds a closed-loop process from visually recognizing a cup to grasping it stably, connecting perception output into the control stage to complete the grasp. The content is organized around the task chain of "seeing the cup—grasping it stably" and is practical, tutorial-style instruction.
Dexterous Hand Practice 21 focuses on how VLA (vision-language-action models) control a dexterous hand, outlining the process from language instruction input to the generation of constrained actions. The content is tutorial in nature, explaining this control chain, and does not provide specific robot models, experimental data, or success rate metrics.
The 25th installment of the Dexterous Hand Practice series works backward from job posting requirements to outline a learning path for dexterous hand engineers and identify the skills the role requires. The content centers on the correspondence between job requirements and skills, and is a learning-path analysis aimed at newcomers to the field; it does not cover specific robot models or experimental data.
Tactile perception in dexterous hands mainly comes from three types of sensing solutions: joint angle, fingertip force, and slip. The article separately analyzes how joint angle sensing, fingertip force sensing, and slip sensing are implemented, and explains the role and differences of each solution in dexterous hands. The content is aimed at robotics developers and outlines approaches for selecting tactile sensors.
The author turned to high-quality Gaussian Splats of real sites to build augmentable, relightable photorealistic simulation environments, because policies trained in animated simulation were hard to transfer to real machines. The pipeline, refined over hundreds of iterations, converts iPhone scans into Splats plus meshes, selects robot-operable assets, and splits them by unit to generate detailed assets placed back at their original positions in the Splat. Physics and rendering use MuJoCo Warp, and the robot is a Franka Panda.
Point clouds are discrete geometric samples of three-dimensional space. Unlike regular images, they must be converted into a computable BEV representation through structured processing such as voxels or pillar bucketing. The article reviews point cloud algorithms along the chain from data fundamentals to models, engineering deployment, and quantization, and organizes common computation modules.
Reeman unmanned forklifts completed on-site commissioning for multi-peripheral integration with automatic doors and wrapping machines, enabling automated workflows in warehouse scenarios where unmanned forklifts interface with automatic doors and wrapping machines. The article reviews the on-site commissioning record of this integration project, covering the interfacing process between the unmanned forklifts and the two types of peripherals.
In a Shanxi project, the Rhino unmanned forklift had its radar raised by 1 m; this is not parameter tuning but a structural design for shelf compatibility. Using the unmanned forklift as an example, the article notes that robot engineering deployment failures are often due to misalignment between on-site requirements and equipment configuration, rather than inadequate algorithms.
A source code walkthrough of GlanceWAM examines its visual imagination, Goal Attention, time conditioning, Flow Matching training, and asynchronous inference mechanisms. The approach reduces WA through low-frequency future frame generation and high-frequency action prediction (the original text is truncated here and does not give the complete metric).
Embodied intelligence data collection centers on teleoperation architecture and the Demonstration data pipeline, explaining how to collect demonstration data through teleoperation. The content focuses on the practical data collection workflow, covering the setup of the teleoperation architecture and how the demonstration data pipeline is organized.
The article discusses why injecting only Gaussian white noise in ROS2 mobile robot simulation is insufficient for validating fusion algorithms, focusing on systematic errors such as bias, scale, and mounting misalignment that cannot be averaged out by filtering, and provides a complete approach for injecting systematic errors into odom, lidar, and IMU.
The 18th installment of the Dexterous Hand Practice series discusses how to integrate impedance control and admittance control into the closed loop to avoid crushing objects during grasping. The content focuses on how these two control methods are integrated into the force-control closed loop of a dexterous hand.
The 19th installment of Gu Yue Ju's "Dexterous Hand Practice" series explains how to teach a robot using motion capture gloves, focusing on how teleoperation data is collected. The material provides only the title and summary; it does not give specific devices, procedures, or data metrics.
The 17th installment of the Dexterous Hand Practice series focuses on the differences between piezoresistive and capacitive tactile sensor approaches, and discusses how to use them to determine contact and slip. The content addresses the tactile perception stage in dexterous hand R&D and is part of this tutorial series.
This introductory tutorial covers six-step commutation for brushless DC (BLDC) motors, explaining three key implementation areas: Hall sensor signals, building commutation tables, and STM32 complementary PWM output. Aimed at robotics developers, it maps commutation logic to MCU timer configuration. It is a combined theory-and-practice explanation and does not provide specific experimental platform parameters or test results.
The 20th installment of the Dexterous Hand Practice series explains how to build a single-finger simulation environment in MuJoCo and, on that basis, understand the Isaac simulation chain. The content centers on the process of setting up the single-finger environment, used to compare how the MuJoCo and Isaac simulation pipelines connect.
The implementation path of dexterous hand force control from position loop and current loop to impedance control is systematically reviewed. The content is organized around these three control layers, explaining the role of each layer in dexterous hand force control and how they connect.
AMR forklifts rely on onboard LiDAR and laser SLAM for mapping and localization, enabling autonomous path planning and obstacle avoidance without ground infrastructure such as magnetic tape, guide wires, or reflectors; route changes are usually made via software. The REEMAN Ironhide 3.0 is a 1.5-ton autonomous forklift with ±5 cm pick-and-place accuracy on 1.2 × 1.2 m pallets, 6 hours of runtime at full load and 8 hours empty, and a maximum mapping area of 40,000 m².
Addressing the problem of step loss in open-loop stepper motors, this article presents a practical retrofit using encoder closed-loop control and stall detection. The material provides only the title and summary; it does not give a specific retrofit plan, hardware selection, or measured data.
The article reviews the core issues in robotic tactile classification, pointing out that robots need to judge material, attributes, and state from contact signals rather than simply categorizing them. It emphasizes that task definitions must distinguish between material, attributes, and state to avoid label confusion, and notes that tactile readings are affected by action conditions and must be modeled in temporal and conditional contexts.
Episode 16 of Dexterous Hand Practice focuses on analyzing contact with grasp matrices and explains how to hold a cup steadily. The content centers on the grasp matrix as an analysis tool, used to assess the contact state and stability when a dexterous hand grasps a cup.
The article provides an in-depth analysis of the ros2_control hardware interface, covering three areas: controller management, joint command dispatch, and motor state readback. Aimed at robotics developers, it explains how the hardware interface passes commands and states between controllers and motors.
This article examines grasp obstacle avoidance in MoveIt 2, breaking it down into three parts: planning scene construction, collision geometry setup, and real-robot trajectory validation. It focuses on how to configure the planning scene and collision objects in MoveIt 2 and confirm grasp obstacle avoidance performance through real-robot trajectory validation.
Stereo distance measurement calculates depth from disparity using Z=f×B/d, showing near-accurate, far-sparse characteristics: a longer baseline is better suited for long distances, and a longer focal length gives higher depth resolution. Stereo calibration consists of two steps: monocular intrinsic calibration and stereo extrinsic calibration. Extrinsic angle error is the main source of amplified error at long distances, and calibration accuracy largely determines the system's accuracy ceiling. Calibration targets should be selected by scenario: standard glass checkerboards for routine industrial inspection, dot calibration boards for high-precision micro-assembly, large-size calibration boards for large-field outdoor use, and ChArUco or AprilTag for dynamic workstations.
Reinforcement learning policy optimization has evolved from REINFORCE and Actor-Critic to TRPO and then PPO, with the core goal of making policy gradient updates more stable and efficient. PPO uses clipping on the probability ratio between the new and old policies to limit the size of each update, balancing implementation complexity and stability, and is suitable for both continuous and discrete actions. The article also reviews GAE advantage estimation, the on-policy data flow, and tuning approaches for key hyperparameters such as learning rate and clip range.
The article focuses on ROS2 mobile robot simulation based on ros2_control, covering interface development, ground-truth validation, and the boundaries of the approach, for use in scenarios such as navigation benchmarks and SLAM algorithm comparison. Starting from the problem of the wheels not turning, it outlines how ros2_control is integrated into simulation and its scope of application.
Zhang Zhengyou calibration, nine-point calibration, and hand-eye calibration are not parallel alternatives; they are progressive layers, from camera optical calibration to planar coordinate alignment to 3D cross-system pose unification. Zhang Zhengyou calibration solves only the camera intrinsic matrix and distortion coefficients and requires 15–25 calibration board images at different poses; nine-point calibration uses 9 corresponding points of robot coordinates and pixel coordinates to compute a planar hand-eye matrix, suitable for 2D sorting, loading/unloading, and placement; hand-eye calibration solves the 6-DOF pose transformation via the AX=XB equation, targeting 3D grasping and precision assembly. Selection should match the scenario; more complex is not always better.
Ollobot Robotics Limited offers robot pet space recommendations: usable floor space matters more than total room area. The L1 measures 1200–660 × 434 × 343 mm, and the S1 measures 650 × 434 × 343 mm; both have a nominal movement speed of about 0.5 m/s.
In indoor light-load AMR projects, overly tight coupling between the chassis and the top module can cause problems that were hidden in the prototype stage to surface en masse during mass production. Using the integration from a hoverboard chassis to a complete food delivery robot as an example, this article discusses design and engineering integration approaches for decoupling the chassis and top module.
Centered on implementing GNSS positioning and PPS timing, the content covers three stages: NMEA sentence parsing, time synchronization, and positioning quality assessment. The original text does not provide specific module models, accuracy metrics, or experimental conditions; it only identifies these three technical points at the title level.
ROS 2 robot model description involves three parts: URDF, Xacro, and joint transform publishing. URDF defines the robot's link and joint structure, Xacro simplifies model authoring through macros and parameterization, and joint transform publishing connects the joint states in the model to the ROS 2 coordinate transform system.
Odometry calibration for a differential drive mobile chassis must address two key parameters: wheel diameter error and effective wheelbase, and the calibration effect must be verified through real-vehicle trajectories. The article analyzes these two sources of error, explaining their impact on odometry accuracy and the calibration approach.
Transferring motion capture data to a humanoid robot body requires handling skeleton alignment and scale factors, and setting up a final safety gate. The article centers on these three points, explaining how to adapt motion capture data to the joint and size differences of the humanoid body and add safety limits before execution.
The article traces the architectural evolution of three generations of robot foundation models: RT-1, OpenVLA, and π0. It focuses on the architectural changes across these three generations and is a technical evolution analysis rather than the release of a new model.
Warehouse layout optimization requires balancing space shape and capacity, equipment, labor, technology, SKU variety, and budget to improve efficiency, speed, storage density, and space utilization. The four common layouts—I-shape, U-shape, L-shape, and T-shape—each involve trade-offs: I-shape offers one-way flow but goods must travel the full length; U-shape places receiving and shipping adjacent, which can easily cause vehicle congestion; L-shape and T-shape separate receiving and shipping to reduce congestion. Ultra-high-density cube ASRS such as AutoStore are suited to increasing storage density within an existing footprint, and simulation tools and automation partners can help validate designs and reduce bottlenecks before implementation.
Engineers tested payload compensation on custom STS32XX firmware for the SO-ARM101/102; under a 250 g load, gravity compensation calibrated with an empty gripper reduced deviation from about 70 mm to about 35 mm. The team is seeking input on how to automatically adapt to different payloads, and the relevant code has been placed in the repository.
A quadrotor tracks a yellow target ball using only a 64×64 camera image. The official pretrained policy was loaded to complete tracking experiments in Isaac Lab, with the target visible about 40% of the time and the quadrotor autonomously hovering to reacquire the target after losing it. The article also discusses known gaps when migrating the policy to the DJI Tello.
Guyueju released a tutorial explaining the complete workflow from URDF modeling to MoveIt2 grasping operations for a robotic arm plus dexterous hand. The material provides only the title and does not give specific steps, parameters, or code details.
Embedded configuration data migration must address three issues: version identification, legacy parameter compatibility, and power-loss recovery. The article analyzes these three aspects, explaining how to identify configurations when versions change, remain compatible with legacy parameters, and recover configuration data after power loss.
Incremental encoder acquisition involves three stages: quadrature decoding, hardware counting, and high-speed pulse loss troubleshooting. The content covers quadrature signal decoding methods and hardware counter implementation approaches, and provides troubleshooting ideas for pulse loss under high-speed operating conditions.