Energy-based Potential Games for Joint Motion Forecasting and Control

2023/12/04 by Diehl, Christopher, Klosek, Tobias, Krüger, Martin +3 · 2 citations
#Artificial Intelligence (cs.AI) #Computer Science and Game Theory (cs.GT) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Multiagent Systems (cs.MA) #Robotics (cs.RO)

paper · doi:10.48550/arxiv.2312.01811

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.

Cited by

• Deep Fictitious Play-Based Potential Differential Games for Learning Human-Like Interaction at Unsignalized Intersections
• Recent Advances in Multi-Agent Human Trajectory Prediction: A Comprehensive Review

Related

• On a Connection between Differential Games, Optimal Control, and Energy-based Models for Multi-Agent Interactions
• Learning to Play Trajectory Games Against Opponents with Unknown Objectives
• Learning Two-agent Motion Planning Strategies from Generalized Nash Equilibrium for Model Predictive Control
• Blending Data-Driven Priors in Dynamic Games
• Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models