karlkurzer/path_planner

Health v2 · maintenance only

Flags: no_releases

Adoption not part of the score

1911 stars · 571 forks observed · 2026-08-28

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

A C++ implementation of the Hybrid A* path planning algorithm for nonholonomic autonomous vehicles, developed for the KTH Research Concept Vehicle. It combines continuous-space A* search with discretized headings, dual heuristics, and Dubin's shots to generate smooth, real-time (~10 Hz) paths from LIDAR-generated obstacle maps.

Use cases

• plan paths for a nonholonomic autonomous vehicle around obstacles
• implement hybrid A* motion planning in C++ with ROS
• generate smooth drivable paths for parking and maze navigation
• study hybrid A* with constrained and unconstrained heuristics
• compute Dubin's shot paths for car-like vehicles
• visualize path planning search in RViz

When to choose

• you need real-time path planning for a car-like, nonholonomic vehicle
• you work in a ROS environment and want a reference hybrid A* implementation
• you want a well-documented, thesis-backed implementation of Dolgov/Thrun's hybrid A*
• your input is a binary obstacle map from LIDAR or similar sensors

When to avoid

• you need planning for holonomic robots or drones
• you want a maintained production library with active support
• you need dynamic obstacle avoidance or multi-vehicle coordination
• you don't use ROS or C++ in your stack

Facets

library · maturity maintenance

simulation robotics robotics autonomous-vehicles cpp hybrid-a-star motion-planning path-planning nonholonomic dubins-path ros autonomous-driving algorithm algorithms linux

Member repositories

For agents

markdown · JSON · MCP: product_card(name="karlkurzer/path_planner")