Blog
Solving IMU State Estimation Divergence During AGV Stationary States: A Two-Step Error-State Kalman Filter Approach with Covariance Constraints
1. The Problem: Why IMU State Estimation Diverges When AGVs Are Stationary1.1 The Stop-and-Go Nature of AGV OperationsDuring intelligent AGV operations, AGVs frequently exhibit...
How to Build a Motion Capture Suit: Wearable IMU System with Complementary Filtering for Real-Time Human Posture Tracking
Why IMU-Based Motion Capture?Motion capture technology is the method of tracking and recording human body movement. A motion capture suit equipped with IMU sensors...
A Lightweight Deep Learning Approach for IMU-Based Human Activity Recognition: From Sensor Data to Action Classification
1. What Is Human Activity Recognition and Why IMU?
Human Activity Recognition (HAR) is a technology that determines a person’s various postures and daily activities...
How Modulation-LSTM Neural Networks Reduce IMU Drift in AGV Navigation: A Deep Learning Approach to Dynamic State Estimation
Discover how the ML-UKF algorithm eliminates IMU drift in industrial AGVs, slashing position errors by 65.43% for flawless indoor navigation.
IMU Calibration vs. Datasheet: The Real Cost of Cheap Sensors
Paper specs don't predict field performance. Learn why calibration quality, temperature compensation, and unit-to-unit consistency matter more than datasheet numbers when selecting IMUs for autonomous driving and robotics.
C-NCAP’s 2027 Active Safety Threshold Increases Significantly: Why Does Your ADAS Test Require the IFS3000 Ground Truth System?
C-NCAP 2027 raises active safety thresholds, making ground truth systems essential for repeatable, precise, and verifiable ADAS validation in NCAP tests.
Intelligent AGVs Based on IMU
In-depth exploration of state estimation technology for Intelligent AGVs, focusing on IMU applications. Critical analysis comparing single-sensor navigation (magnetic, vision, LiDAR) with multi-sensor fusion approaches, featuring key research breakthroughs for logistics automation and indoor positioning.
In-Depth Analysis of Visual-LiDAR-IMU SLAM
Explore how the LiDAR-camera-IMU fusion SLAM overcomes the difficulties in poor lighting, textureless areas and motion deterioration. This review compares methods for loose and tight coupling for robust and high precision positioning and mapping including V-LOAM, LVI-SAM, factor graph optimization, and deep learning integration.
In-Depth Analysis of LiDAR-Inertial SLAM
This article reviews the LiDAR-Inertial SLAM technology in detail, comparing the filter-based and graph optimization fusion algorithms such as FAST-LIO and LIO-SAM. It touches on point cloud processing, dynamic environment processing and the emergence of deep learning enhanced semantic SLAM, and solves current challenges in the field.
In-Depth Analysis of Visual-Inertial SLAM
Explore visual-inertial SLAM systems that combine cameras and IMUs to overcome challenges like weak textures, lighting changes, and scale ambiguity. Compare filtering and optimization techniques, important algorithms such as MSCKF, VINS-Mono and ORB-SLAM3, as well as recent progress in feature enhancement and fusion techniques.