Behavior Trees for Robotics Systems: Tools, Applications, and Lessons Learned

Michele Colledanchise1, Lorenzo Natale2, Petter Ogren3

  • 1KTH - The Royal Institute of Technology
  • 2Istituto Italiano di Tecnologia
  • 3Royal Institute of Technology (KTH)

Details

09:00 - 18:00 | Mon 4 Nov | LG-R16 | MoW-R16.1

Session: Behavior Trees for Robotics Systems: Tools, Applications, and Lessons Learned

Abstract

Behavior Trees is a new powerful tool for task switching and decision making that is receiving an increasing amount of attention in robotics. Recent research is beginning to explore areas such as learning, planning and control in domains from Micro Air Vehicles to Assembly robotics. The objectives of this workshop are as follows For the first time, gather everyone within the robotics community that is interested in Behavior Trees at the same place, and give them a chance to discuss and interact. We also provide attendees with an updated picture of where behavior tree research within robotics stands today. Behavior Trees were developed in the video game industry as a tool to achieve modular, reusable, and flexible behaviors for Non-Player Characters (NPCs), and are now an established tool to the point that they integral parts of game AI textbooks as well as major game engines such as Unity3d, and the Unreal Engine. In the last decade, Behavior Trees have received an increasing amount of attention in robotic as well, with applications in both academia and industry. The main advantages of Behavior Trees with respect to conventional execution architectures like FSMs, are their ability to combine reactivity with deliberation in a very modular way. This workshop has two main objectives: gather professionals and researchers with experience in using Behavior Trees for robotics applications, and sharing experiences and ideas to professionals and researchers interested in modeling complex behaviors for robots. The intended outcome of the workshop is to: (1) Lay the basis for a community of researchers working on Behavior Trees with robotic applications; (2) Discuss the current state of the art and identify the open challenges; (3) Discuss and compare available tools for Behavior Trees; (4) Discuss and compare the challenges of using Behavior Trees in robotics, compared to computer games. (5)Provide an opportunity to initiate new collaborations.