CommonRoad: Composable benchmarks for motion planning on roads

Numerical experiments for motion planning of road vehicles require numerous components: vehicle dynamics, a road network, static obstacles, dynamic obstacles and their movement over time, goal regions, a cost function, etc. Providing a description of the numerical experiment precise enough to reproduce it might require several pages of information. Thus, only key aspects are typically described in scientific publications, making it impossible to reproduce results - yet, re-producibility is an important asset of good science. Composable benchmarks for motion planning on roads (CommonRoad) are proposed so that numerical experiments are fully defined by a unique ID; all information required to reconstruct the experiment can be found on the CommonRoad website. Each benchmark is composed by a vehicle model, a cost function, and a scenario (including goals and constraints). The scenarios are partly recorded from real traffic and partly hand-crafted to create dangerous situations. We hope that CommonRoad saves researchers time since one does not have to search for realistic parameters of vehicle dynamics or realistic traffic situations, yet provides the freedom to compose a benchmark that fits one's needs.

I. Introduction

Reproducibility of results is a cornerstone of science [1], [2]. One obstacle towards reproducibility in motion planning of road vehicles is that details of the experimental results are often not fully provided-some reasons are page limitations of publications, an overwhelming number of required details, or simply because some details are taken for granted. Providing detailed benchmarks would help in this regard and also simplify comparing different planning methods.