Active Neural Localization
Active Neural Localization
复制标题
DOI：
--
复制
发表时间：
2018-01
期刊：
影响因子：
--
通讯作者：
Devendra Singh Chaplot;Emilio Parisotto;R. Salakhutdinov
中科院分区：
文献类型：
--
作者：
Devendra Singh Chaplot;Emilio Parisotto;R. Salakhutdinov
定位是从观察和环境地图中估计自治代理的位置的问题。传统的定位方法，过滤的信念的基础上的观察，是次优的步骤所需的数量，因为它们不决定采取的行动的代理。我们提出了“主动神经定位器”，这是一个完全可微的神经网络，可以学习准确有效地定位。该模型结合了传统的基于过滤的定位方法的思想，通过使用一个结构化的信念的状态与乘法的相互作用来传播信念，并将其与一个政策模型相结合，以准确定位，同时最大限度地减少定位所需的步骤。Active Neural Localizer通过强化学习进行端到端训练。我们使用各种模拟环境，我们的实验，其中包括随机的2D迷宫，随机迷宫的毁灭战士游戏引擎和虚幻游戏引擎中的照片般逼真的环境。在2D环境中的结果显示了在理想化设置中学习策略的有效性，而在3D环境中的结果显示了模型从基于原始像素的RGB观测中联合学习策略和感知模型的能力。我们还表明，在Doom环境中对随机纹理进行训练的模型可以很好地推广到虚幻引擎中的照片般逼真的办公空间环境。
Localization is the problem of estimating the location of an autonomous agent from an observation and a map of the environment. Traditional methods of localization, which filter the belief based on the observations, are sub-optimal in the number of steps required, as they do not decide the actions taken by the agent. We propose "Active Neural Localizer", a fully differentiable neural network that learns to localize accurately and efficiently. The proposed model incorporates ideas of traditional filtering-based localization methods, by using a structured belief of the state with multiplicative interactions to propagate belief, and combines it with a policy model to localize accurately while minimizing the number of steps required for localization. Active Neural Localizer is trained end-to-end with reinforcement learning. We use a variety of simulation environments for our experiments which include random 2D mazes, random mazes in the Doom game engine and a photo-realistic environment in the Unreal game engine. The results on the 2D environments show the effectiveness of the learned policy in an idealistic setting while results on the 3D environments demonstrate the model's capability of learning the policy and perceptual model jointly from raw-pixel based RGB observations. We also show that a model trained on random textures in the Doom environment generalizes well to a photo-realistic office space environment in the Unreal engine.