Robot Navigation from Human Demonstration: Learning Control Behaviors

When working alongside human collaborators in dynamic environments such as a disaster recovery, an unmanned ground vehicle (UGV) may require fast field adaptation to perform its duties or learn novel tasks. In disaster recovery situations, personnel and equipment are constrained, so training must be accomplished with minimal human supervision. In this paper, we introduce a novel framework which uses learned visual perception and inverse optimal control trained with minimal human supervisory examples. This approach is used to learn to mimic navigation behavior and is demonstrated through extensive evaluation in a real-world environment. Finally, we demonstrate the ability to learn an additional behavior with minimal human demonstration in the field.

[1]  Anind K. Dey,et al.  Maximum Entropy Inverse Reinforcement Learning , 2008, AAAI.

[2]  James S. Albus,et al.  Learning traversability models for autonomous mobile vehicles , 2008, Auton. Robots.

[3]  Jonathan R. Fink,et al.  Mapping with a ground robot in GPS denied and degraded environments , 2014, 2014 American Control Conference.

[4]  Siddhartha S. Srinivasa,et al.  Planning-based prediction for pedestrians , 2009, 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Junzhong Gu,et al.  A modified Hausdorff distance based algorithm for 2-dimensional spatial trajectory matching , 2010, 2010 5th International Conference on Computer Science & Education.

[6]  Oliver Brock,et al.  High Performance Outdoor Navigation from Overhead Data using Imitation Learning , 2009 .

[7]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[8]  Henrik I. Christensen,et al.  OmniMapper: A modular multimodal mapping framework , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[9]  David Baran,et al.  Application of Multi-Robot Systems to Disaster-Relief Scenarios with Limited Communication , 2015, FSR.

[10]  Sebastian Thrun,et al.  Reverse Optical Flow for Self-Supervised Adaptive Autonomous Robot Navigation , 2007, International Journal of Computer Vision.

[11]  J. Andrew Bagnell,et al.  Maximum margin planning , 2006, ICML.

[12]  Pieter Abbeel,et al.  Apprenticeship learning via inverse reinforcement learning , 2004, ICML.

[13]  Dumitru Erhan,et al.  Going deeper with convolutions , 2014, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[14]  Panagiotis Papadakis,et al.  Terrain traversability analysis methods for unmanned ground vehicles: A survey , 2013, Eng. Appl. Artif. Intell..

[15]  Sergey Levine,et al.  Nonlinear Inverse Reinforcement Learning with Gaussian Processes , 2011, NIPS.

[16]  Bolei Zhou,et al.  Learning Deep Features for Scene Recognition using Places Database , 2014, NIPS.

[17]  John G. Rogers,et al.  Unsupervised Semantic Scene Labeling for Streaming Data , 2017, 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[18]  Wolfram Burgard,et al.  Traversability analysis for mobile robots in outdoor environments: A semi-supervised learning approach based on 3D-lidar data , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[19]  Daniel Munoz,et al.  Inference Machines: Parsing Scenes via Iterated Predictions , 2013 .

[20]  Anil K. Jain,et al.  A modified Hausdorff distance for object matching , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[21]  Maxim Likhachev,et al.  Search-based planning for manipulation with motion primitives , 2010, 2010 IEEE International Conference on Robotics and Automation.

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

[23]  Bruce A. Draper,et al.  Reducing adaptation latency for multi-concept visual perception in outdoor environments , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[24]  Giulio Reina,et al.  A Self‐learning Framework for Statistical Ground Classification using Radar and Monocular Vision , 2015, J. Field Robotics.

[25]  Roberto Manduchi,et al.  Autonomous terrain characterisation and modelling for dynamic control of unmanned vehicles , 2002, IEEE/RSJ International Conference on Intelligent Robots and Systems.

[26]  Markus Wulfmeier,et al.  Watch this: Scalable cost-function learning for path planning in urban environments , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[27]  Kee-Eung Kim,et al.  Bayesian Nonparametric Feature Construction for Inverse Reinforcement Learning , 2013, IJCAI.

[28]  Martial Hebert,et al.  Activity Forecasting , 2012, ECCV.

[29]  Roberto Cipolla,et al.  SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[30]  Alberto Broggi,et al.  Traversability analysis using terrain mapping and online-trained Terrain type classifier , 2014, 2014 IEEE Intelligent Vehicles Symposium Proceedings.