MichaelFYang/far_planner

Health v2 · maintenance only

Flags: no_releases no_license

Adoption not part of the score

1011 stars · 208 forks observed · 2026-08-28

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

FAR Planner is a C++/ROS route planner for autonomous robots that builds a dynamically updated visibility graph to plan paths in both known and unknown environments. It handles dynamic obstacles by disconnecting and reconnecting visibility edges and was used by the CMU-OSU team in the DARPA Subterranean Challenge.

Use cases

• plan paths for a robot in unknown environments
• replan routes quickly around dynamic obstacles
• navigate a ground vehicle using a prior map
• build a visibility graph while exploring a subterranean site
• integrate a global planner into a ROS-based autonomous exploration stack

When to choose

• you need fast global path planning (millisecond-level) in a ROS navigation stack
• your robot must handle both known maps and unexplored areas
• you want a planner proven in real-world competitions like the DARPA SubT Challenge

When to avoid

• you need a planner outside the ROS ecosystem
• you require a permissively licensed dependency (the repo has no license)
• you need local/low-level motion control rather than global route planning

Facets

library · maturity stable

robotics simulation robotics autonomous-vehicles cpp path-planning visibility-graph ros autonomous-navigation unknown-environments cmu algorithm algorithms linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="MichaelFYang/far_planner")