4.6 Review

Behavior Trees in Robot Control Systems

Related references

Note: Only part of the references are listed.
Article Automation & Control Systems

Continuous-Time Behavior Trees as Discontinuous Dynamical Systems

Christopher Sprague et al.

Summary: Behavior trees are a hierarchical and modular approach to combining low-level control policies into a high-level task-switching policy. This letter presents the first continuous-time formulation of behavior trees, treating them as a subclass of discontinuous dynamical systems. Moreover, it provides sufficient conditions for the convergence of such systems to a desired region of the state space for general designs.

IEEE CONTROL SYSTEMS LETTERS (2022)

Article Robotics

On the Implementation of Behavior Trees in Robotics

Michele Colledanchise et al.

Summary: Behavior Trees (BTs) have gained increasing interest as a tool for describing and implementing robot behaviors. While there is consensus on how BTs work, certain characteristics depend on implementation choices in specific software libraries. Solutions developed by the robotics community are aimed at fully exploiting the advantages of BTs in real robots.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Proceedings Paper Automation & Control Systems

Learning Behavior Trees with Genetic Programming in Unpredictable Environments

Matteo Iovino et al.

Summary: The study proposes a method using genetic programming to learn the structure of a behavior tree for solving robotic tasks in unpredictable environments. After learning with a simple simulator, it is demonstrated that the learned behavior trees can solve the same tasks in a realistic simulator.

2021 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA 2021) (2021)

Article Robotics

An Expressiveness Hierarchy of Behavior Trees and Related Architectures

Oliver Biggar et al.

Summary: This letter presents a formal framework for comparing the expressive power of Behavior Trees (BTs) with other action selection architectures. By formalizing the concept of 'expressiveness', an expressiveness hierarchy of control architectures including BTs, Decision Trees (DTs), Teleo-reactive Programs (TRs), and Finite State Machines (FSMs) is established. The letter demonstrates a trade-off in BT design between readability and expressiveness and discusses the implications for BTs in practice.

IEEE ROBOTICS AND AUTOMATION LETTERS (2021)

Article Robotics

Convergence Analysis of Hybrid Control Systems in the Form of Backward Chained Behavior Trees

Petter Ogren

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Robotics

A Framework for Formal Verification of Behavior Trees With Linear Temporal Logic

Oliver Biggar et al.

IEEE ROBOTICS AND AUTOMATION LETTERS (2020)

Article Computer Science, Artificial Intelligence

Behavior tree design of intelligent behavior of non-player character (NPC) based on Unity3D

Xianwen Zhu

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS (2019)

Article Computer Science, Artificial Intelligence

Learning of Behavior Trees for Autonomous Agents

Michele Colledanchise et al.

IEEE TRANSACTIONS ON GAMES (2019)

Article Multidisciplinary Sciences

Grandmaster level in StarCraft II using multi-agent reinforcement learning

Oriol Vinyals et al.

NATURE (2019)

Proceedings Paper Computer Science, Software Engineering

Automatic difficulty management and testing in games using a framework based on behavior trees and genetic algorithms

Ciprian Paduraru et al.

2019 24TH INTERNATIONAL CONFERENCE ON ENGINEERING OF COMPLEX COMPUTER SYSTEMS (ICECCS 2019) (2019)

Proceedings Paper Computer Science, Artificial Intelligence

Representing Robot Task Plans as Robust Logical-Dynamical Systems

Chris Paxton et al.

2019 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS) (2019)

Proceedings Paper Automation & Control Systems

Towards Blended Reactive Planning and Acting using Behavior Trees

Michele Colledanchise et al.

2019 INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA) (2019)

Article Computer Science, Artificial Intelligence

Evolutionary Behavior Tree Approaches for Navigating Platform Games

Miguel Nicolau et al.

IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES (2017)

Proceedings Paper Engineering, Aerospace

Integration of an automated hierarchical task planner in ROS using behaviour trees

Jose A. Segura-Muros et al.

2017 6TH IEEE INTERNATIONAL CONFERENCE ON SPACE MISSION CHALLENGES FOR INFORMATION TECHNOLOGY (SMC-IT) (2017)

Article Computer Science, Artificial Intelligence

Query-Enabled Behavior Trees

Gonzalo Florez-Puga et al.

IEEE TRANSACTIONS ON COMPUTATIONAL INTELLIGENCE AND AI IN GAMES (2009)

Article Automation & Control Systems

Discontinuous dynamical systems -: A tutorial on solutions, nonsmooth analysis, and stability

Jorge Cortes

IEEE CONTROL SYSTEMS MAGAZINE (2008)

Article Computer Science, Artificial Intelligence

A comparison of bloat control methods for genetic programming

Sean Luke et al.

EVOLUTIONARY COMPUTATION (2006)