Path Planning

Michele Cavaioni
Jul 25, 2017 · 1 min read

Path planning for a vehicle includes the following steps: behavior, prediction and trajectory.

- The Behavior step takes into account the estimates coming from the prediction stage and depicts what maneuvers the “ego” vehicle should perform next.

- The Prediction step evaluates what others might do next.

- The Trajectory step defines the actual path the vehicle has to follow, based on the decisions coming from the Behavior results.

The inputs for the behavior planning are: a map, the starting location, the goal location and a cost function.

The goal is to find the minimum cost path.

The following schematic shows the interactions among the different modules. Each module constantly updates its status. It should be noted that the module on the top of the diagram (the behavior module) is the slowest in terms of data update and, as we move down the graph, the update rate increases. The motion control module updates more frequently than any other module.

In the following lectures I will go in details on each module (behavior, prediction, trajectory).


This article has been inspired by the Udacity Self-Driving Car Nanodegree lectures (http://www.udacity.com)

Self-driving car bites

Projects and lectures on Autonomous Vehicle technology

Michele Cavaioni

Written by

Passionate about AI, ML, DL, and Autonomous Vehicle tech. CEO of CritiqueMatch.com, a platform that helps writers and bloggers to connect and exchange feedback.

Self-driving car bites

Projects and lectures on Autonomous Vehicle technology

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade