Learning Transferable Policies for Monocular Reactive MAV Control

The ability to transfer knowledge gained in previous tasks into new contexts is one of the most important mechanisms of human learning. Despite this, adapting autonomous behavior to be reused in partially similar settings is still an open problem in current robotics research. In this paper, we take a small step in this direction and propose a generic framework for learning transferable motion policies. Our goal is to solve a learning problem in a target domain by utilizing the training data in a different but related source domain. We present this in the context of an autonomous MAV flight using monocular reactive control, and demonstrate the efficacy of our proposed approach through extensive real-world flight experiments in outdoor cluttered environments.

[1]  Trevor Darrell,et al.  DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition , 2013, ICML.

[2]  Martial Hebert,et al.  Learning monocular reactive UAV control in cluttered natural environments , 2012, 2013 IEEE International Conference on Robotics and Automation.

[3]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[4]  Sergey Levine,et al.  End-to-End Training of Deep Visuomotor Policies , 2015, J. Mach. Learn. Res..

[5]  Jürgen Schmidhuber,et al.  A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots , 2016, IEEE Robotics and Automation Letters.

[6]  Martial Hebert,et al.  Vision and Learning for Deliberative Monocular Cluttered Flight , 2014, FSR.

[7]  Brian C. Lovell,et al.  Unsupervised Domain Adaptation by Domain Invariant Projection , 2013, 2013 IEEE International Conference on Computer Vision.

[8]  Ivor W. Tsang,et al.  Domain Adaptation via Transfer Component Analysis , 2009, IEEE Transactions on Neural Networks.

[9]  Geoffrey J. Gordon,et al.  A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning , 2010, AISTATS.

[10]  Martial Hebert,et al.  Semi-Dense Visual Odometry for Monocular Navigation in Clutt ered Environment , 2015 .

[11]  Michael I. Jordan,et al.  Learning Transferable Features with Deep Adaptation Networks , 2015, ICML.

[12]  Mengjie Zhang,et al.  Domain Adaptive Neural Networks for Object Recognition , 2014, PRICAI.

[13]  Martial Hebert,et al.  Robust Monocular Flight in Cluttered Outdoor Environments , 2016, ArXiv.

[14]  Ashutosh Saxena,et al.  High speed obstacle avoidance using monocular vision and reinforcement learning , 2005, ICML.

[15]  Dean Pomerleau,et al.  ALVINN, an autonomous land vehicle in a neural network , 2015 .

[16]  Horst Bischof,et al.  Building with drones: Accurate 3D facade reconstruction using MAVs , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[17]  Sivaraman Balakrishnan,et al.  Optimal kernel choice for large-scale two-sample tests , 2012, NIPS.

[18]  Yoshua Bengio,et al.  How transferable are features in deep neural networks? , 2014, NIPS.