arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.04783cs.CVcs.RO
收藏

从真实世界的部分观测中学习预测性世界模型

Predictive World Models from Real-World Partial Observations

Nagoya University（名古屋大学）；Gifu University（岐阜大学）；TIER IV

Robin Karlsson, Alexander Carballo, Keisuke Fujii, Kento Ohtani, Kazuya Takeda

备注：
Best Paper Award at IEEE MOST 2023
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出一种用于真实道路环境的概率预测世界模型框架，采用分层VAE并设计新颖的序列训练方法，仅从部分观测状态学习预测完整状态，在确定性区域达96.21 IoU，并将随机区域预测差距缩小62%。

摘要：

认知科学家认为，像人类这样具有适应性的智能体通过对智能体和环境进行学习到的因果心理模拟来执行推理。学习这种模拟的问题被称为预测性世界建模。最近，利用世界模型的强化学习（RL）智能体在游戏环境中取得了SOTA性能。然而，了解如何将世界建模方法应用于与移动机器人相关的复杂真实世界环境仍然是一个开放问题。在本文中，我们提出了一个用于学习真实世界道路环境的概率预测世界模型的框架。我们使用分层VAE（HVAE）实现该模型，该模型能够从累积的传感器观测中预测多种完全观测的合理世界。虽然先前的HVAE方法需要完整状态作为学习的真值，但我们提出了一种新颖的序列训练方法，使HVAE能够仅从部分观测状态学习预测完整状态。我们通过实验证明了对确定性区域的准确空间结构预测，实现了96.21 IoU，并使用最佳预测将随机区域与完美预测之间的差距缩小了62%。通过将HVAE扩展到不存在完整真值状态的情况，我们促进了空间预测的持续学习，作为实现真实世界移动机器人应用的可解释且全面的预测性世界模型的一步。代码可在https://github.com/robin-karlsson0/predictive-world-models获取。

英文摘要：

Cognitive scientists believe adaptable intelligent agents like humans perform reasoning through learned causal mental simulations of agents and environments. The problem of learning such simulations is called predictive world modeling. Recently, reinforcement learning (RL) agents leveraging world models have achieved SOTA performance in game environments. However, understanding how to apply the world modeling approach in complex real-world environments relevant to mobile robots remains an open question. In this paper, we present a framework for learning a probabilistic predictive world model for real-world road environments. We implement the model using a hierarchical VAE (HVAE) capable of predicting a diverse set of fully observed plausible worlds from accumulated sensor observations. While prior HVAE methods require complete states as ground truth for learning, we present a novel sequential training method to allow HVAEs to learn to predict complete states from partially observed states only. We experimentally demonstrate accurate spatial structure prediction of deterministic regions achieving 96.21 IoU, and close the gap to perfect prediction by 62% for stochastic regions using the best prediction. By extending HVAEs to cases where complete ground truth states do not exist, we facilitate continual learning of spatial prediction as a step towards realizing explainable and comprehensive predictive world models for real-world mobile robotics applications. Code is available at https://github.com/robin-karlsson0/predictive-world-models.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑