Level 02 / 11

Getting Familiar with SLAM

Geometry, optimization, and the anatomy of a SLAM system

Programming (core)

C++: OOP, Modern C++, Data structures & Algorithms, Compilers, CMake/Makefile/Ninja, Design patterns, OpenCV C++
C
Git/GitHub
OpenCV (opencv-python)
Python: Deep learning, Graph plots, System scripts
Bash/Linux: ssh, CLI text editor/Vim/tmux
Math libraries: Eigen, Ceres-solver/GTSAM/g2o
C++/Python interop: PyBind11, nanobind
ROS/ROS2
Docker

Programming (optional — engineering skills for SLAM jobs)

Concurrency: SIMD-SSE/AVX/Neon, OpenMP, CUDA
Edge deployment: TensorRT/ONNX export of learned frontends, Jetson benchmarking
Mobile: Android (Java/Kotlin), iOS (Objective-C/Swift)
C#: Unity AR, Microsoft HoloLens
CI/CD: GitHub Actions
Simulation: Gazebo, Isaac Sim

Image Processing

Keypoints → Detector/Descriptor
- SIFT, FAST, ORB, AKAZE
- Deep features: R2D2, SuperPoint
Image pyramid, oFAST, rBRIEF

Local Feature Matching

Global Feature Matching

Feature Tracking

Optical flow, KLT Tracker

Multiple View Geometry

2D-2D correspondence: Essential/Fundamental, Homography
2D-3D correspondence: P3P, PnP, SVD
3D-3D correspondence: ICP

Outlier Rejection

RANSAC, PROSAC, M-Estimator, MAXCON, Convex relaxation
Robust pose-graph optimization: Switchable constraints, Dynamic covariance scaling (DCS), Pairwise consistency maximization (PCM)

Certifiably Optimal Algorithms

System	Author/Year	Key Concepts
SE-Sync	Rosen 2019	Certifiable pose graph optimization via SDP + Riemannian opt (arXiv 2016, IJRR 2019)
TEASER++	Yang 2020	Point cloud registration, 90%+ outlier robust, TLS + Max Clique (T-RO/RSS 2020)
GNC	Yang 2020	Graduated Non-Convexity, continuation from convex → robust cost
QUASAR	Yang 2019	Certifiably optimal rotation search (Wahba problem with outliers), quaternion QCQP + SDP relaxation

Least Squares Optimization

Motion Model

Proprioceptive sensor: IMU, Wheel
Odometry (pose)

Observation Model

Factor Graph Optimization

Factor graph: SLAM as a bipartite graph of variables (poses, landmarks) and factors (measurements)
MAP inference as sparse nonlinear least squares; variable elimination and the Bayes tree
Incremental smoothing: iSAM / iSAM2
Marginalization and fixed-lag smoothing
Reference: Dellaert & Kaess, Factor Graphs for Robot Perception (2017); GTSAM tutorials

Gaussian Belief Propagation

System	Author/Year	Key Concepts
FutureMapping 1	Davison 2018	Computational structure of Spatial AI, GBP for SLAM
FutureMapping 2	Davison 2019	GBP as core Spatial AI primitive, visual intro to GBP
BA on Graph Processor	Ortiz 2020	Bundle Adjustment on Graphcore IPU, tile-based parallelism
DANCeRS	Patwardhan 2025	GBP-based distributed consensus in robot swarms

Mapping

Point cloud, Occupancy grid mapping, TSDF, Surfel, Voxel map

Sensors

Camera device: Wide/telecentric lens, Lens MTF, CCD/CMOS, Rolling/Global shutter, Exposure/ISO, Stereo vision, RGB-D, Structured light, Active IR/ToF
LiDAR → Visual-LiDAR fusion
IMU → VIO
RADAR → Sensor fusion, Extended Kalman filter
Sonar
Multi-sensor calibration: Camera-IMU, Camera-LiDAR (Kalibr)

Evaluation

Metrics: ATE (Absolute Trajectory Error), RPE (Relative Pose Error)
Consistency: NEES (Normalized Estimation Error Squared)
Datasets: KITTI, TUM RGB-D, EuRoC, TartanAir, TUM-VI, 4Seasons, Hilti SLAM Challenge, Newer College, Project Aria
Tools: evo (trajectory evaluation)