sensor-fusion-ekf

Use when estimating robot pose/odometry from multiple sensors (wheel odom, IMU, GPS, visual odom) — configure a robot_localization EKF/UKF with per-sensor state masks rather than trusting a single sou

SKILL.md

GitHub

When to use. Pose/odometry estimation or drift problems. Why: every sensor lies differently (wheel slip, IMU bias, GPS jumps); an EKF with correct per-sensor masks beats any one sensor.

Procedure.

  1. List sensors and which state dims each is trustworthy for (odom→x/y/yaw & velocities, IMU→orientation/angular-rate, GPS→global x/y).
  2. Write the *_config boolean masks accordingly; set frames (odom/base_link/world).
  3. Tune process/measurement covariance from real logs (system ID), not guesses.
  4. Done when: fused odom is continuous and drift-bounded over a test trajectory (plot pasted).

Knowledge: KNOWLEDGE-LIBRARY.md §B1. Example: the ekf.yaml there.

Related in other

limits-colimits

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context polluti...

by parcadei
3,392

ddttom-allaboutv2-claude-skills-block-collection-and-party

The Block Collection and Block Party are repositories for existing AEM blocks, build tools, code snippets, integration p...

by mattnigh
20

nodnarbnitram-claude-code-extensions-claude-skills-esphome-confi

This skill should be used when the user asks to "create an esphome config", "set up an esp32 device", "configure esphome...

by mattnigh
20