Learning Autonomous Mobility Using Real Demonstration Data

This work proposed an efficient learning-based framework to learn feedback control policies from human teleoperated demonstrations, which achieved obstacle negotiation, staircase traversal, slipping control and parcel delivery for a tracked robot. Due to uncertainties in real-world scenarios, e.g. obstacle and slippage, closed-loop feedback control plays an important role in improving robustness and resilience, but the control laws are difficult to program manually for achieving autonomous behaviours. We formulated an architecture based on a long-short-term-memory (LSTM) neural network, which effectively learn reactive control policies from human demonstrations. Using data-sets from a few real demonstrations, our algorithm can directly learn successful policies, including obstacle-negotiation, stair-climbing and delivery, fall recovery and corrective control of slippage. We proposed decomposition of complex robot actions to reduce the difficulty of learning the long-term dependencies. Furthermore, we proposed a method to efficiently handle non-optimal demos and to learn new skills, since collecting enough demonstration can be time-consuming and sometimes very difficult on a real robotic system.

[1]  Andrew Y. Ng,et al.  Pharmacokinetics of a novel formulation of ivermectin after administration to goats , 2000, ICML.

[2]  Luc Van Gool,et al.  End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners , 2018, ECCV.

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

[4]  Pieter Abbeel,et al.  Autonomous Helicopter Aerobatics through Apprenticeship Learning , 2010, Int. J. Robotics Res..

[5]  Odest Chadwicke Jenkins,et al.  Human and robot perception in large-scale learning from demonstration , 2011, 2011 6th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[6]  Geoffrey J. Gordon,et al.  No-Regret Reductions for Imitation Learning and Structured Prediction , 2010, ArXiv.

[7]  Stefan Schaal,et al.  Learning and generalization of motor skills by learning from demonstration , 2009, 2009 IEEE International Conference on Robotics and Automation.

[8]  Peter Stone,et al.  Transfer learning for reinforcement learning on a physical robot , 2010, AAMAS 2010.

[9]  Tom Schaul,et al.  Learning from Demonstrations for Real World Reinforcement Learning , 2017, ArXiv.

[10]  Ann Nowé,et al.  Transfer Learning Across Simulated Robots With Different Sensors , 2019, ArXiv.

[11]  Taku Komura,et al.  Learning Whole-Body Motor Skills for Humanoids , 2018, 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids).

[12]  Kenneth Y. Goldberg,et al.  Cloud-based robot grasping with the google object recognition engine , 2013, 2013 IEEE International Conference on Robotics and Automation.

[13]  Pieter Abbeel,et al.  Learning from Demonstrations Through the Use of Non-rigid Registration , 2013, ISRR.

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

[15]  Michael Beetz,et al.  Learning models for constraint-based motion parameterization from interactive physics-based simulation , 2016, 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

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

[17]  Maya Cakmak,et al.  Keyframe-based Learning from Demonstration , 2012, Int. J. Soc. Robotics.

[18]  Maya Cakmak,et al.  Robot Programming by Demonstration with Crowdsourced Action Fixes , 2014, HCOMP.