DREAMer-VXS: A Latent World Model for Sample-Efficient AGV Exploration in Stochastic, Unobserved Environments

Fuente: arXiv
Saved in:
Bibliographic Details
Main Author: Chakraborty, Agniprabha
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911293721542656
author Chakraborty, Agniprabha
author_facet Chakraborty, Agniprabha
contents The paradigm of learning-based robotics holds immense promise, yet its translation to real-world applications is critically hindered by the sample inefficiency and brittleness of conventional model-free reinforcement learning algorithms. In this work, we address these challenges by introducing DREAMer-VXS, a model-based framework for Autonomous Ground Vehicle (AGV) exploration that learns to plan from imagined latent trajectories. Our approach centers on learning a comprehensive world model from partial and high-dimensional LiDAR observations. This world model is composed of a Convolutional Variational Autoencoder (VAE), which learns a compact representation of the environment's structure, and a Recurrent State-Space Model (RSSM), which models complex temporal dynamics. By leveraging this learned model as a high-speed simulator, the agent can train its navigation policy almost entirely in imagination. This methodology decouples policy learning from real-world interaction, culminating in a 90% reduction in required environmental interactions to achieve expert-level performance when compared to state-of-the-art model-free SAC baselines. The agent's behavior is guided by an actor-critic policy optimized with a composite reward function that balances task objectives with an intrinsic curiosity bonus, promoting systematic exploration of unknown spaces. We demonstrate through extensive simulated experiments that DREAMer-VXS not only learns orders of magnitude faster but also develops more generalizable and robust policies, achieving a 45% increase in exploration efficiency in unseen environments and superior resilience to dynamic obstacles.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00005
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DREAMer-VXS: A Latent World Model for Sample-Efficient AGV Exploration in Stochastic, Unobserved Environments
Chakraborty, Agniprabha
Robotics
The paradigm of learning-based robotics holds immense promise, yet its translation to real-world applications is critically hindered by the sample inefficiency and brittleness of conventional model-free reinforcement learning algorithms. In this work, we address these challenges by introducing DREAMer-VXS, a model-based framework for Autonomous Ground Vehicle (AGV) exploration that learns to plan from imagined latent trajectories. Our approach centers on learning a comprehensive world model from partial and high-dimensional LiDAR observations. This world model is composed of a Convolutional Variational Autoencoder (VAE), which learns a compact representation of the environment's structure, and a Recurrent State-Space Model (RSSM), which models complex temporal dynamics. By leveraging this learned model as a high-speed simulator, the agent can train its navigation policy almost entirely in imagination. This methodology decouples policy learning from real-world interaction, culminating in a 90% reduction in required environmental interactions to achieve expert-level performance when compared to state-of-the-art model-free SAC baselines. The agent's behavior is guided by an actor-critic policy optimized with a composite reward function that balances task objectives with an intrinsic curiosity bonus, promoting systematic exploration of unknown spaces. We demonstrate through extensive simulated experiments that DREAMer-VXS not only learns orders of magnitude faster but also develops more generalizable and robust policies, achieving a 45% increase in exploration efficiency in unseen environments and superior resilience to dynamic obstacles.
title DREAMer-VXS: A Latent World Model for Sample-Efficient AGV Exploration in Stochastic, Unobserved Environments
topic Robotics
url https://arxiv.org/abs/2512.00005