New answers tagged

1

The most traditional method is to keep looking at the trajectory and see if your current location is close enough to the previously visited place. Once this happens run the ICP. If ICP converged normally, that is your loop closure. A bit more advanced method is doing a place recognition. Generate a keyframe every few meters and extract a feature descriptor ...


0

The cost map is indeed an important sub problem within robot navigation, because it guides a solver into a certain direction. The idea is, that a sampling based solver like RRT is searching in the cost map for a gradient descent which reduces the state space to interesting regions. A fast path planner and a well created cost map are the same. Uniform cost ...


Top 50 recent answers are included