no code implementations • 17 Apr 2023 • Marvin Klimke, Benjamin Völz, Michael Buchholz
In this work, we propose a method to employ a trained deep reinforcement learning policy for dedicated high-level behavior planning.
no code implementations • 30 Jan 2023 • Marvin Klimke, Benjamin Völz, Michael Buchholz
The present work proposes to leverage reinforcement learning and a graph-based scene representation for cooperative multi-agent planning.
no code implementations • 18 Jul 2022 • Marvin Klimke, Jasper Gerigk, Benjamin Völz, Michael Buchholz
In this work, we build upon a previously presented graph-based scene representation and graph neural network to approach the problem using reinforcement learning.
no code implementations • 23 Feb 2022 • Marvin Klimke, Benjamin Völz, Michael Buchholz
Learning-based behavior planning poses several challenges, demanding for a suited input and output representation as well as large amounts of ground-truth data.
no code implementations • 2 Feb 2021 • Florian Wirthmüller, Marvin Klimke, Julian Schlechtriemen, Jochen Hipp, Manfred Reichert
To plan safe and comfortable trajectories for automated vehicles on highways, accurate predictions of traffic situations are needed.
no code implementations • 23 Sep 2020 • Florian Wirthmüller, Marvin Klimke, Julian Schlechtriemen, Jochen Hipp, Manfred Reichert
Already today, driver assistance systems help to make daily traffic more comfortable and safer.