机器人与深度学习

Paper

2017

Tateno, K., Tombari, F., Laina, I., & Navab, N. (2017). CNN-SLAM: Real-time dense monocular SLAM with learned depth prediction. arXiv preprint arXiv:1704.03489. 利用CNN从单目相机中预测深度信息，进行SLAM构建，获得RGBD的三维语义构建. http://campar.in.tum.de/Chair/ProjectCNNSLAM

2016

From Perception to Decision: A Data-driven Approach to End-to-end Motion Planning for Autonomous Ground Robots - Mark Pfeiffer etc. 2016 ETH 室内导航, 从感知到决策端到端的自主机器人运动规划

Deep Learning for Laser based Odometry Estimation - Nicolai 2016 激光里程计

Learning Hand-Eye Coordination for Robotic Grasping with Deep Learning and Large-Scale Data Collection - Levine , ISER, 2016. DeepMind 物体抓取

Unsupervised Learning for Physical Interaction through Video Prediction, Chelsea Finn, Ian Goodfellow, Sergey Levine, NIPS, 2016. 非监督学习物理交互

End-to-end training of deep visuomotor policies 2016 Berkeley 拧瓶盖

Sim-to-Real Robot Learning from Pixels with Progressive Nets 提出了一种叫progressive networks来桥接模拟和现实世界，把模拟环境中学习到的策略转移到现实世界中。Progressive network是一个可以重用把从low-level的视觉特征到high-level的策略转移到新任务上，而且能简单组合实现复杂的技巧的通用框架。

2015

Deep Neural Network for Real-Time Autonomous Indoor Navigation - Dong Ki Kim, Tsuhan Chen 2015 NYTU 无人机室内导航

A Machine Learning Approach to the Visual Perception of Forest Trails for Mobile Robots - Alessandro Giusti, Luca M.Gambardella 2015 无人机导航 深度学习

Learning visual odometry with a convolutional network - Konda 2015 视觉里程计

more

Learning monocular reactive uav control in cluttered natural environments 2013 CMU 无人机穿越森林