HKUST-Aerial-Robotics/Teach-Repeat-Replan

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1157 stars · 265 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

Teach-Repeat-Replan is a complete C++/ROS system enabling aggressive autonomous drone flight in complex environments. It converts a manually taught (demonstrated) trajectory into a smooth, safe repeating trajectory with local replanning to avoid unmapped or moving obstacles.

Use cases

• autonomous drone racing
• repeat a manually flown drone trajectory safely
• aggressive UAV flight in cluttered environments
• avoid unmapped or moving obstacles during flight
• infrastructure inspection with aerial robots
• search-and-rescue drone missions
• trajectory replanning for quadrotors

When to choose

• you need a full teach-and-repeat pipeline for UAV aggressive flight
• you want smooth, safe trajectory generation from jerky human-taught paths
• you are doing research on drone racing or aerial robotics replanning

When to avoid

• you need a simple waypoint-following autopilot without replanning
• your platform is not ROS-based or not a multirotor UAV
• you need a maintained product with recent updates and support

Facets

application · maturity maintenance

robotics simulation machine-learning developer-tools robotics autonomous-vehicles simulation cpp uav motion-planning drone-racing teach-and-repeat trajectory-optimization ros linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="HKUST-Aerial-Robotics/Teach-Repeat-Replan")