Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Results of the 2023 CommonRoad Motion Planning Competition for Autonomous Vehicles

Niklas Kochdumper, Youran Wang, Johannes Betz, Matthias Althoff

TL;DR

The results of a large-scale motion planning competition for autonomous vehicles based on the CommonRoad benchmark suite are presented, where the solutions are evaluated considering efficiency, safety, comfort, and compliance with a selection of traffic rules.

Abstract

In recent years, different approaches for motion planning of autonomous vehicles have been proposed that can handle complex traffic situations. However, these approaches are rarely compared on the same set of benchmarks. To address this issue, we present the results of a large-scale motion planning competition for autonomous vehicles based on the CommonRoad benchmark suite. The benchmark scenarios contain highway and urban environments featuring various types of traffic participants, such as passengers, cars, buses, etc. The solutions are evaluated considering efficiency, safety, comfort, and compliance with a selection of traffic rules. This report summarizes the main results of the competition.

Results of the 2023 CommonRoad Motion Planning Competition for Autonomous Vehicles

TL;DR

The results of a large-scale motion planning competition for autonomous vehicles based on the CommonRoad benchmark suite are presented, where the solutions are evaluated considering efficiency, safety, comfort, and compliance with a selection of traffic rules.

Abstract

In recent years, different approaches for motion planning of autonomous vehicles have been proposed that can handle complex traffic situations. However, these approaches are rarely compared on the same set of benchmarks. To address this issue, we present the results of a large-scale motion planning competition for autonomous vehicles based on the CommonRoad benchmark suite. The benchmark scenarios contain highway and urban environments featuring various types of traffic participants, such as passengers, cars, buses, etc. The solutions are evaluated considering efficiency, safety, comfort, and compliance with a selection of traffic rules. This report summarizes the main results of the competition.

Paper Structure

This paper contains 13 sections, 4 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Format of the Competition
  3. Evaluation
  4. Feasible Trajectories
  5. Cost Function
  6. Participants
  7. Stony Brook University
  8. Technical University of Munich
  9. FRENETIX Architecture
  10. FRENTIX Performance
  11. FRENETIX Enhancements with Modules
  12. Results
  13. Conclusion

Figures (5)

  • Figure 1: Example for a motion planning problem defined by the CommonRoad scenario DEU_Flensburg-73_1_T-1, where the goal set is depicted in yellow, the initial position and velocity of the ego vehicle in green, and the other traffic participants in blue.
  • Figure 2: Visualization of the single steps for the reachability-based decision module Kochdumper2024 used by the motion planner from Stony Brook University, where the goal set is depicted in yellow, the space occupied by other traffic participants in blue, the drivable area for the ego vehicle in red, and the provided reference trajectory in black.
  • Figure 3: The individual steps during trajectory sampling and trajectory evaluation in the FRENETIX motion planner.
  • Figure 4: One of the scenarios in which FRENETIX was tested involves dynamic overtaking, a complex maneuver that requires precise trajectory planning and real-time adjustments. FRENETIX successfully navigated this scenario, demonstrating its capability to handle high-stakes driving situations where safety and accuracy are paramount.
  • Figure 5: Performance comparison on benchmark scenarios that are solved by both planners.