# Revision history [back]

One of the parameters for optimization that has considerable impact is penalty_epsilon.

As per documentation: http://wiki.ros.org/teb_local_planner

<name>/penalty_epsilon (double, default: 0.1)
Add a small safety margin to penalty functions for hard-constraint approximations


Teb local planner tends to get stuck is local minimum, by slightly incrementing this value, the behaviour may be avoided.

An excellent resource: https://wiki.ros.org/teb_local_planner/Tutorials