Comparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation

Comparison of Model-Free and Model-Based Learning-Informed Planning for PointGoal Navigation
复制标题

PointGoal 导航的无模型和基于模型的学习知情规划的比较

DOI:
--
复制
发表时间:
2022
期刊:
arXiv.org
影响因子:
--
通讯作者:
J. Kosecka
J. Kosecka
中科院分区:
--
文献类型:
--
作者:
Yimeng Li;Arnab Debnath;Gregory J. Stein;J. Kosecka

文献摘要

参考文献

被引文献

相似文献

近年来,已经提出了几种在以前看不见的环境中进行点目标导航的学习方法。它们在环境的表征、问题分解和实验评价方面各不相同。在这项工作中,我们将最先进的基于深度强化学习的方法与点目标导航问题的部分可观察马尔可夫决策过程(POMDP)公式进行了比较。我们采用[1]提出的(POMDP)子目标框架,并通过使用从图像的语义分割构建的室内场景的部分语义图来修改估计边界属性的组件。除了众所周知的基于模型的方法的完整性,我们证明了它是强大的和有效的,因为它利用了信息丰富,学习性能的边界相比,一个乐观的基于边界的规划。我们还展示了与端到端深度强化学习方法相比的数据效率。我们使用Habitat Simulator将我们的结果与Matterport 3D数据集上的乐观规划者ANS和DD-PPO进行比较。我们显示出可比的,虽然比SOTA DD-PPO方法稍差的性能,但数据少得多。
In recent years several learning approaches to point goal navigation in previously unseen environments have been proposed. They vary in the representations of the environments, problem decomposition, and experimental evaluation. In this work, we compare the state-of-the-art Deep Reinforcement Learning based approaches with Partially Observable Markov Decision Process (POMDP) formulation of the point goal navigation problem. We adapt the (POMDP) sub-goal framework proposed by [1] and modify the component that estimates frontier properties by using partial semantic maps of indoor scenes built from images' semantic segmentation. In addition to the well-known completeness of the model-based approach, we demonstrate that it is robust and efficient in that it leverages informative, learned properties of the frontiers compared to an optimistic frontier-based planner. We also demonstrate its data efficiency compared to the end-to-end deep reinforcement learning approaches. We compare our results against an optimistic planner, ANS and DD-PPO on Matterport3D dataset using the Habitat Simulator. We show comparable, though slightly worse performance than the SOTA DD-PPO approach, yet with far fewer data.
基于学习增强模型的视觉探索规划
DOI: --
发表时间: 2023
期刊: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS
影响因子: --
作者:
Yimeng Li;Arnab Debnath;Gregory J. Stein;Jana Košecká
通讯作者: Jana Košecká
DOI: 10.1146/annurev-control-091420-084139
发表时间: 2021-01-01
期刊: ANNUAL REVIEW OF CONTROL, ROBOTICS, AND AUTONOMOUS SYSTEMS, VOL 4, 2021
影响因子: --
作者:
Garrett, Caelan Reed;Chitnis, Rohan;Lozano-Perez, Tomas
通讯作者: Lozano-Perez, Tomas
学习用于导航的视图和目标不变视觉伺服
DOI: --
发表时间: 2020
期刊: IEEE International Conference on Robotics and Automation
影响因子: --
作者:
Li, Yimeng;Kosecka, Jana
通讯作者: Kosecka, Jana