Energy-based Potential Games for Joint Motion Forecasting and Control

• URL: http://arxiv.org/abs/2312.01811v1
• Date: Mon, 4 Dec 2023 11:30:26 GMT
• Title: Energy-based Potential Games for Joint Motion Forecasting and Control
• Authors: Christopher Diehl, Tobias Klosek, Martin Kr\"uger, Nils Murzyn, Timo Osterburg, Torsten Bertram
• Abstract summary: This work uses game theory as a mathematical framework to address interaction modeling in motion forecasting and control. 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. 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.
• Score: 0.125828876338076
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• MonoForce: Learnable Image-conditioned Physics Engine [1.03590082373586]
  We propose a novel model for the prediction of robot trajectories on rough offroad terrain from the onboard camera images. The proposed hybrid model integrates a black-box component that predicts robot-terrain interaction forces with a neural-symbolic layer. The differentiability, in conjunction with the rapid simulation speed, makes the model well-suited for various applications.
  arXiv  Detail & Related papers  (2025-02-14T13:36:00Z)
• Pre-Trained Video Generative Models as World Simulators [59.546627730477454]
  We propose Dynamic World Simulation (DWS) to transform pre-trained video generative models into controllable world simulators. To achieve precise alignment between conditioned actions and generated visual changes, we introduce a lightweight, universal action-conditioned module. Experiments demonstrate that DWS can be versatilely applied to both diffusion and autoregressive transformer models.
  arXiv  Detail & Related papers  (2025-02-10T14:49:09Z)
• Cyber Physical Games [0.0]
  We show that the non-determinism inherent in the communication medium between agents and the underlying physical environment gives rise to environment evolution. We name these emergent properties Cyber Physical Games and study its properties. We present an algorithmic model that determines the most likely system evolution, approximating Cyber Physical Games through Probabilistic Finite State Automata.
  arXiv  Detail & Related papers  (2024-07-08T10:54:14Z)
• A Deep Learning Method for Optimal Investment Under Relative Performance Criteria Among Heterogeneous Agents [2.330509865741341]
  Graphon games have been introduced to study games with many players who interact through a weighted graph of interaction. We focus on a graphon game for optimal investment under relative performance criteria, and we propose a deep learning method.
  arXiv  Detail & Related papers  (2024-02-12T01:40:31Z)
• Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation [50.01551945190676]
  Social robot navigation can be helpful in various contexts of daily life but requires safe human-robot interactions and efficient trajectory planning. We propose a systematic relational reasoning approach with explicit inference of the underlying dynamically evolving relational structures. We demonstrate its effectiveness for multi-agent trajectory prediction and social robot navigation.
  arXiv  Detail & Related papers  (2024-01-22T18:58:22Z)
• On a Connection between Differential Games, Optimal Control, and Energy-based Models for Multi-Agent Interactions [0.13499500088995461]
  We show a connection between differential games, optimal control, and energy-based models. Building upon this formulation, this work introduces a new end-to-end learning application. Experiments using simulated mobile robot pedestrian interactions and real-world automated driving data provide empirical evidence.
  arXiv  Detail & Related papers  (2023-08-31T08:30:11Z)
• Towards Optimal Strategies for Training Self-Driving Perception Models in Simulation [98.51313127382937]
  We focus on the use of labels in the synthetic domain alone. Our approach introduces both a way to learn neural-invariant representations and a theoretically inspired view on how to sample the data from the simulator. We showcase our approach on the bird's-eye-view vehicle segmentation task with multi-sensor data.
  arXiv  Detail & Related papers  (2021-11-15T18:37:43Z)
• Dynamic Visual Reasoning by Learning Differentiable Physics Models from Video and Language [92.7638697243969]
  We propose a unified framework that can jointly learn visual concepts and infer physics models of objects from videos and language. This is achieved by seamlessly integrating three components: a visual perception module, a concept learner, and a differentiable physics engine.
  arXiv  Detail & Related papers  (2021-10-28T17:59:13Z)
• Bidirectional Interaction between Visual and Motor Generative Models using Predictive Coding and Active Inference [68.8204255655161]
  We propose a neural architecture comprising a generative model for sensory prediction, and a distinct generative model for motor trajectories. We highlight how sequences of sensory predictions can act as rails guiding learning, control and online adaptation of motor trajectories.
  arXiv  Detail & Related papers  (2021-04-19T09:41:31Z)
• Learning Game-Theoretic Models of Multiagent Trajectories Using Implicit Layers [9.594432031144716]
  We propose an end-to-end trainable architecture that hybridizes neural nets with game-theoretic reasoning. For tractability, we introduce a new class of continuous potential games and an equilibrium-separating partition of the action space. We evaluate our approach on two real-world data sets, where we predict highway merging driver trajectories, and on a simple decision-making transfer task.
  arXiv  Detail & Related papers  (2020-08-17T13:34:12Z)
• Learning to Simulate Dynamic Environments with GameGAN [109.25308647431952]
  In this paper, we aim to learn a simulator by simply watching an agent interact with an environment. We introduce GameGAN, a generative model that learns to visually imitate a desired game by ingesting screenplay and keyboard actions during training.
  arXiv  Detail & Related papers  (2020-05-25T14:10:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.