Energy-based Potential Games for Joint Motion Forecasting and Control
Christopher Diehl, Tobias Klosek, Martin Krueger, Nils Murzyn, Timo Osterburg, Torsten Bertram
Abstract
This work uses game theory as a mathematical framework to address interaction modeling in multi-agent motion forecasting and control. Despite its interpretability, applying game theory to real-world robotics, like automated driving, faces challenges such as unknown game parameters. To tackle these, we establish a connection between differential games, optimal control, and energy-based models, demonstrating how existing approaches can be unified under our proposed Energy-based Potential Game formulation. Building upon this, we introduce a new end-to-end learning application that combines neural networks for game-parameter inference with a differentiable game-theoretic optimization layer, acting as an inductive bias. The analysis provides empirical evidence that the game-theoretic layer adds interpretability and improves the predictive performance of various neural network backbones using two simulations and two real-world driving datasets.
BibTeX
@inproceedings{
diehl2023energybased,
title={Energy-based Potential Games for Joint Motion Forecasting and Control},
author={Christopher Diehl and Tobias Klosek and Martin Krueger and Nils Murzyn and Timo Osterburg and Torsten Bertram},
booktitle={7th Annual Conference on Robot Learning},
year={2023},
url={https://openreview.net/forum?id=Eyb4e3GBuuR}
}