Saved in:
Bibliographic Details
Main Authors: Zheng, Dongzhe, Mei, Wenjie
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.19672
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915888419045376
author Zheng, Dongzhe
Mei, Wenjie
author_facet Zheng, Dongzhe
Mei, Wenjie
contents Stochastic optimal control methods often struggle in complex non-convex landscapes, frequently becoming trapped in local optima due to their inability to learn from historical trajectory data. This paper introduces Memory-Augmented Potential Field Theory, a unified mathematical framework that integrates historical experience into stochastic optimal control. Our approach dynamically constructs memory-based potential fields that identify and encode key topological features of the state space, enabling controllers to automatically learn from past experiences and adapt their optimization strategy. We provide a theoretical analysis showing that memory-augmented potential fields possess non-convex escape properties, asymptotic convergence characteristics, and computational efficiency. We implement this theoretical framework in a Memory-Augmented Model Predictive Path Integral (MPPI) controller that demonstrates significantly improved performance in challenging non-convex environments. The framework represents a generalizable approach to experience-based learning within control systems (especially robotic dynamics), enhancing their ability to navigate complex state spaces without requiring specialized domain knowledge or extensive offline training.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19672
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Memory-Augmented Potential Field Theory: A Framework for Adaptive Control in Non-Convex Domains
Zheng, Dongzhe
Mei, Wenjie
Robotics
Dynamical Systems
Stochastic optimal control methods often struggle in complex non-convex landscapes, frequently becoming trapped in local optima due to their inability to learn from historical trajectory data. This paper introduces Memory-Augmented Potential Field Theory, a unified mathematical framework that integrates historical experience into stochastic optimal control. Our approach dynamically constructs memory-based potential fields that identify and encode key topological features of the state space, enabling controllers to automatically learn from past experiences and adapt their optimization strategy. We provide a theoretical analysis showing that memory-augmented potential fields possess non-convex escape properties, asymptotic convergence characteristics, and computational efficiency. We implement this theoretical framework in a Memory-Augmented Model Predictive Path Integral (MPPI) controller that demonstrates significantly improved performance in challenging non-convex environments. The framework represents a generalizable approach to experience-based learning within control systems (especially robotic dynamics), enhancing their ability to navigate complex state spaces without requiring specialized domain knowledge or extensive offline training.
title Memory-Augmented Potential Field Theory: A Framework for Adaptive Control in Non-Convex Domains
topic Robotics
Dynamical Systems
url https://arxiv.org/abs/2509.19672