An OpenRAVE plugin for circular trajectory blending
C++ CMake Python
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Failed to load latest commit information.


An OpenRAVE Plugin for trajectory timing

This is an OpenRAVE wrapper to an algorithm for converting a linear joint space path into a timed trajectory with bounded acceleration and velocity. It does this by adding circular blends between consecutive linear path segments, and computing the time-optimal motion along the linear-circular-linear segments.

The resulting trajectory is then reinterpolated at a fixed discretization to return a quadratic polynomial spline approximation of the solution.

It is based on code provided by Tobias Kunz:

which implements the technique described in the paper:

  • Tobias Kunz and Mike Stilman, Time-Optimal Trajectory Generation for Path Following with Bounded Acceleration and Velocity, RSS 2008


This algorithm takes the following parameters (with the specified default values):

  • <check_collision>False</check_collision>: If the blended trajectory should be re-checked for collisions
  • <integration_step>0.001</integration_step>: The integration step size.
  • <interpolation_step>0.01</interpolation_step>: The interpolation step size.
  • <max_deviation>0.1</max_deviation>: The maximum allowed deviation from the original trajectory