Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation
Intention-Net: Integrating Planning and Deep Learning for Goal-Directed Autonomous Navigation
复制标题
DOI：
--
复制
发表时间：
2017-10
期刊：
影响因子：
--
通讯作者：
Wei Gao-;David Hsu;Wee Sun Lee;Shengmei Shen;K. Subramanian
中科院分区：
文献类型：
--
作者：
Wei Gao-;David Hsu;Wee Sun Lee;Shengmei Shen;K. Subramanian
送货机器人如何在事先信息最少的情况下可靠地导航到新办公楼的目的地？为了应对这一挑战，本文引入了一种两级分层方法，该方法集成了无模型深度学习和基于模型的路径规划。在底层，神经网络运动控制器（称为意图网络）经过端到端训练，以提供强大的本地导航。意图网络将来自单个单目相机的图像和“意图”直接映射到机器人控制。在高层，路径规划器使用粗略地图（例如二维平面图）来计算从机器人当前位置到目标的路径。规划的路径向意图网提供意图。初步实验表明，学习的运动控制器对于感知不确定性具有鲁棒性，并且通过与路径规划器集成，它可以有效地推广到新的环境和目标。
How can a delivery robot navigate reliably to a destination in a new office building, with minimal prior information? To tackle this challenge, this paper introduces a two-level hierarchical approach, which integrates model-free deep learning and model-based path planning. At the low level, a neural-network motion controller, called the intention-net, is trained end-to-end to provide robust local navigation. The intention-net maps images from a single monocular camera and "intentions" directly to robot controls. At the high level, a path planner uses a crude map, e.g., a 2-D floor plan, to compute a path from the robot's current location to the goal. The planned path provides intentions to the intention-net. Preliminary experiments suggest that the learned motion controller is robust against perceptual uncertainty and by integrating with a path planner, it generalizes effectively to new environments and goals.