Rico's Nerd Cluster

「离开世界之前 一切都是过程」

Motion Estimation From Epipolar Constraints

This is an Introduction of Epipolar Constraints and 2D-2D Motion Estimation

Intro This blog is inspired by this great great book: 14 Lectures in Visual SLAM, authored by Dr. Gao Xiang et al. This article will walk you through 8-point algorithm when features lie on differe...

Autonomous Vehicle Introduction

General Project Flow What the robot sees - Perception localization + mapping Navigation - Motion Planning Planning + control Autonomy Levels from SAE (Society of Automotive Engineers) ...

Computation Tools - Eigen Expression Templates and SIMD

Fused Computation

Eigen Expression Template. Optimization Impact: ⭐️⭐⭐️️⚪⚪ Expression templates are one of those “powerful but mysterious” C++ features that libraries like Eigen, Blaze, and even TensorFlow (C++) us...

Computation Tools - OpenCV, Eigen, Sophus, PCL, PCD, NanoFLANN

A Running List of Opencv and Eigen Tools

OpenCV Image Processing cv::Mat Create a cv::Mat In C++: 1 2 3 4 5 6 7 8 // method 1 cv::Mat(another_mat); // method 2 cv::Mat A = (cv::Mat_<uchar>(1,2)<<1,2); //CV_8U // method ...

Robotics - [2D SLAM 1] Hands-On Mapping

Point-Point ICP, Point-Line ICP

🧪 Loop Detection Testing Procedure Phase 1: Baseline Verification (No Loop Closure) Objective: Confirm that submaps are constructed correctly before enabling loop closure. Steps: Disable loo...

Robotics - Gauss Newton (GN) and Levenberg Marquardt (LM) Optimizers

Newton's Method, GN, LM optimizers

Newton’s Method Solving An Equation To find an arbitrary equation’s root $f(x) = 0$, We start from an arbitrary point $x_0$ that’s hopefully close to the solution, $x_s$ The main idea of Ne...

Robotics - General ESKF Hands-on Test Notes

Primers Did you turn on the message debugging flag, or are you compiling with PRINT_DEBUG_MSGS? Are you sure you are launching the right test? IMU tools Velocity drift observed. Here, I’m ...

Robotics - [IMU Pre-integration Model 4] IMU Pre-integration Optimization Implementation

IMU Pre-Integration, GNSS, UTM

Using Pre-Integration Terms as Edges in Graph Optimization Formulating a graph optimization problem using pre-integration (as edges) and states as nodes is quite flexible. Recall that from here th...

Robotics - [IMU Pre-integration Model 3] Noise Model

Jacobian Derivation

Pre-integration Model In Graph Optimization using IMU pre-integration, $b_g$ and $b_a$ are factors under optimization. We have derived the Jacobians of pre-integrated intermediate values w.r.t the...

Robotics - [IMU Pre-integration Model 2] How To Update Pre-integration With Changing IMU Biases

Jacobian Derivation

Update Pre-integration When Updating Biases Pre-integration parts are functions are functions w.r.t gyro and acceleration biases: $b_{g,i}, b_{a,i}$. In graph optimization, we would usually need t...