Learning Behavior Trees From Demonstration

Robotic Learning from Demonstration (LfD) allows anyone, not just experts, to program a robot for an arbitrary task. Many LfD methods focus on low level primitive actions such as manipulator trajectories. Complex multistep task with many primitive actions must be learned from demonstration if LfD is to encompass the full range of task a user may desire. Existing methods represent the high level task in various forms including, finite state machines, decision trees, formal logic, among others. Behavior trees are proposed as an alternative representation of high level task. Behavior trees are an execution model for the control of a robot designed for real time execution, modularity, and, consequently, transparency. Real time execution allows the robot to reactively perform the task. Modularity allows the reuse of learned primitive actions and high level task in new situations, speeding up the process of learning in new scenarios. Transparency allows users to understand and interactively modify the learned model. Behavior trees are used to represent high level tasks by building on the relationship it has with decision trees. We demonstrate a human teaching our Fetch robot a household cleaning task.

[1]  R. Geoff Dromey,et al.  From requirements to design: formalizing the key steps , 2003, First International Conference onSoftware Engineering and Formal Methods, 2003.Proceedings..

[2]  P ? ? ? ? ? ? ? % ? ? ? ? , 1991 .

[3]  Petter Ögren,et al.  Towards a unified behavior trees framework for robot control , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[4]  Daniel H. Grollman,et al.  Can We Learn Finite State Machine Robot Controllers from Interactive Demonstration? , 2010, From Motor Learning to Interaction Learning in Robots.

[5]  Robert Platt,et al.  Localizing Handle-Like Grasp Affordances in 3D Point Clouds , 2014, ISER.

[6]  Wei-Yin Loh,et al.  Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[7]  Odest Chadwicke Jenkins,et al.  Scene-level Programming by Demonstration , 2017, ArXiv.

[8]  Glen Robertson,et al.  A Review of Real-Time Strategy Game AI , 2014, AI Mag..

[9]  Michele Colledanchise,et al.  Behavior Trees in Robotics , 2017 .

[10]  Leslie Pack Kaelbling,et al.  From Skills to Symbols: Learning Symbolic Representations for Abstract High-Level Planning , 2018, J. Artif. Intell. Res..

[11]  Sabrina Hirsch,et al.  Logic Minimization Algorithms For Vlsi Synthesis , 2016 .

[12]  Petter Ögren,et al.  How Behavior Trees Modularize Hybrid Control Systems and Generalize Sequential Behavior Compositions, the Subsumption Architecture, and Decision Trees , 2017, IEEE Transactions on Robotics.

[13]  Gregory D. Hager,et al.  A framework for end-user instruction of a robot assistant for manufacturing , 2015, 2015 IEEE International Conference on Robotics and Automation (ICRA).

[14]  Kaiming He,et al.  Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  Nripendra N. Biswas,et al.  Minimization of Boolean Functions , 1971, IEEE Transactions on Computers.

[16]  Yifeng Zeng,et al.  Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems , 2007, AAMAS 2007.

[17]  Scott Niekum,et al.  Learning grounded finite-state representations from unstructured demonstrations , 2015, Int. J. Robotics Res..

[18]  Benjamin Kuipers,et al.  Robot navigation with model predictive equilibrium point control , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[19]  W. Marsden.  I and J , 2012 .

[20]  Ismael Sagredo-Olivenza,et al.  Trained Behavior Trees: Programming by Demonstration to Support AI Game Designers , 2019, IEEE Transactions on Games.

[21]  Aaas News,et al.  Book Reviews , 1893, Buffalo Medical and Surgical Journal.

[22]  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).

[23]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[24]  Manuela M. Veloso,et al.  Confidence-based policy learning from demonstration using Gaussian mixture models , 2007, AAMAS '07.

[25]  Brett Browning,et al.  A survey of robot learning from demonstration , 2009, Robotics Auton. Syst..