arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1706.09520cs.LGcs.AIcs.RO
收藏

神经SLAM:学习探索外部记忆

Neural SLAM: Learning to Explore with External Memory

University of Freiburg(弗赖堡大学);The Hong Kong University of Science and Technology(香港科技大学)

Jingwei Zhang, Lei Tai, Ming Liu, Joschka Boedecker, Wolfram Burgard

摘要:

我们提出了一种方法,代理从传感器数据中学习表示的全球地图,以帮助他们在新的环境中探索。为了实现这一点,我们嵌入程序模仿传统的同时定位与地图构建(SLAM)到软注意力为基础的寻址外部存储器架构,其中外部存储器作为一个内部的环境表示。这种结构鼓励在完全可微的深层神经网络中进化出类似SLAM的行为。我们表明,这种方法可以帮助强化学习代理成功地探索新的环境中,长期记忆是必不可少的。我们验证我们的方法在具有挑战性的网格世界环境和初步的露台实验。我们的实验视频可以在https://goo.gl/G2Vu5y上找到。

英文摘要:

We present an approach for agents to learn representations of a global map from sensor data, to aid their exploration in new environments. To achieve this, we embed procedures mimicking that of traditional Simultaneous Localization and Mapping (SLAM) into the soft attention based addressing of external memory architectures, in which the external memory acts as an internal representation of the environment. This structure encourages the evolution of SLAM-like behaviors inside a completely differentiable deep neural network. We show that this approach can help reinforcement learning agents to successfully explore new environments where long-term memory is essential. We validate our approach in both challenging grid-world environments and preliminary Gazebo experiments. A video of our experiments can be found at: https://goo.gl/G2Vu5y.

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。

↑