Robotics — Panduan belajar

Connect observations, state, maps and behavior through existing explanations and experiments.

Alur belajar terstruktur tentang robotika, kendali, pertanian lingkungan terkendali, energi, dan elektronika daya.

Before you start Start with sensor, position and velocity terminology. Frames use vectors and matrices; estimation uses probability. Each topic links to its background.

1. System and runtime

Trace sensing through commands, then inspect communication and logs.

The autonomous robot system
- GuidePeta jalan robotika dalam ruangan — dari sensor hingga kontrol gerakan
ROS 2 communication
- PrimerPengantar ROS 2 — Mendistribusikan Kontrol Robot dengan Aman di Seluruh Node, Topik, dan DDS
Recording and replaying logs

Background: ROS 2 communication
- Lab · Run in browserMereproduksi kegagalan robot dengan rosbag2: input, TF, dan waktu

2. Working with frames

Express the same point in different frames.

Coordinate transforms
- Primer · Run in browserTransformasi koordinat robot: matriks, kuaternion, dan TF

3. Estimating motion and state

Distinguish integrated motion from corrections using multiple sensors.

Wheel odometry

Background: Coordinate transforms
- PrimerPengantar Perhitungan Posisi Tanpa Navigasi — Mengintegrasikan Roda, IMU, dan GNSS untuk Melacak Pergerakan Robot
IMU bias and noise
- Lab · Run in browserMembaca log IMU stasioner: bias, scatter, dan deviasi Allan.
GNSS positioning and error
- Primer · Run in browserCara Kerja GNSS dan Produk Utama — u-blox, Trimble, Fixposition
Sensor fusion

Background: Frames and time · Kalman filtering
- PrimerPengantar Penggabungan Sensor — Membangun Satu Model Dunia dari Banyak Sensor
- Primer · Run in browserMengapa fusi sensor gagal — pengaturan waktu, bingkai, dan kalibrasi ekstrinsik

4. Registration and mapping

Explore registration failures before studying the full SLAM system.

Point-cloud registration with ICP

Background: Coordinate transforms
- Lab · Run in browserMengapa ICP gagal: inisialisasi, outlier, dan geometri simetris
LiDAR SLAM

Background: Point-cloud registration with ICP · Pose-graph update
- PrimerPengantar LiDAR-SLAM — Mengetahui "Di Mana Saya" dari Awan Titik Laser
Evaluating SLAM accuracy

Background: LiDAR SLAM
- Lab · Run in browserCara mengevaluasi SLAM — ATE, RPE, waktu eksekusi, dan kegagalan

Separate map representation, paths and behavior, then connect them with Nav2.

Occupancy grids

Background: Coordinate transforms
- PrimerPemetaan Grid Hunian — Mengubah Bukti LiDAR dan Kamera Menjadi Kemampuan Melintasi
More questions on this topic
- Read an additional check on occupancy probability and traversability.
Path search on a map

Background: Occupancy grids
- PrimerPengantar Teknik Kontrol: Perencanaan Jalur — A*, Dijkstra, RRT, RRT*, dan PRM
Behavior selection
- PrimerPengantar Perencanaan Perilaku: Bagaimana FSM, Pohon Perilaku, dan POMDP Memilih Apa yang Akan Dilakukan Kendaraan Otomatis Selanjutnya
More questions on this topic
- Read an additional check on behavior choice and feasibility.
Navigation integration and debugging

Background: Behavior selection · Frames and time · Path search on a map
- Lab · Run in browserDari pemetaan hingga navigasi di ROS 2 — prosedur Jazzy dan Nav2 minimal.
- Lab · Run in browserNav2 memiliki jalur tetapi tidak bergerak: alur kerja diagnostik.

1. System and runtime

The autonomous robot system

ROS 2 communication

Recording and replaying logs

2. Working with frames

Coordinate transforms

3. Estimating motion and state

Wheel odometry

IMU bias and noise

GNSS positioning and error

Sensor fusion

4. Registration and mapping

Point-cloud registration with ICP

LiDAR SLAM

Evaluating SLAM accuracy

5. From maps to motion

Occupancy grids

Path search on a map

Behavior selection

Navigation integration and debugging