ABSTRACT
As a reactive and modular policy control architecture, Behavior Tree (BT) has been used in computer games and robotics for autonomous agents' task switching. However, constructing BTs manually for complex tasks requires expert domain-knowledge and is error-prone. As a solution, researchers have proposed to auto-construct BTs using evolutionary algorithms such as Genetic Programming (GP) and Grammatical Evolution (GE). Nevertheless, their effectiveness in practical situations is in doubt and there are different drawbacks in the application.
In this paper, we present a novel BT evolutionary system that integrates both GE and GP as modules and auto-checks the complexity of a given task to select which module to use. In addition, our system collects BTs that are either previously generated or manually designed by the user, which are utilized to further improve the convergence speed and the quality of generated trees for new tasks.
- Michele Colledanchise and Petter Ögren. 2018. Behavior trees in robotics and AI: An introduction. CRC Press.Google Scholar
- Michele Colledanchise, Ramviyas Parasuraman, and Petter Ögren. 2018. Learning of behavior trees for autonomous agents. IEEE Transactions on Games 11, 2 (2018), 183--189.Google ScholarCross Ref
- Jonatan Wilhelm Hoff and Hallvard Jore Christensen. 2016. Evolving Behaviour Trees:-Automatic Generation of AI Opponents for Real-Time Strategy Games. Master's thesis. NTNU.Google Scholar
- Matteo Iovino, Edvards Scukins, Jonathan Styrud, Petter Ögren, and Christian Smith. 2022. A survey of behavior trees in robotics and ai. Robotics and Autonomous Systems 154 (2022), 104096.Google ScholarDigital Library
- Matteo Iovino, Jonathan Styrud, Pietro Falco, and Christian Smith. 2021. Learning behavior trees with genetic programming in unpredictable environments. In 2021 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 4591--4597.Google ScholarDigital Library
- Simon Jones, Matthew Studley, Sabine Hauert, and Alan Winfield. 2018. Evolving behaviour trees for swarm robotics. In Distributed Autonomous Robotic Systems. Springer, 487--501.Google Scholar
- Chong-U Lim, Robin Baumgarten, and Simon Colton. 2010. Evolving behaviour trees for the commercial game DEFCON. In European conference on the applications of evolutionary computation. Springer, 100--110.Google ScholarDigital Library
- Aadesh Neupane and Michael A Goodrich. 2019. Learning Swarm Behaviors using Grammatical Evolution and Behavior Trees.. In IJCAI. 513--520.Google Scholar
- Aadesh Neupane, Michael A Goodrich, and Eric G Mercer. 2018. GEESE: grammatical evolution algorithm for evolution of swarm behaviors. In Proceedings of the Genetic and Evolutionary Computation Conference. 999--1006.Google ScholarDigital Library
- Miguel Nicolau, Diego Perez-Liebana, Michael O'Neill, and Anthony Brabazon. 2016. Evolutionary behavior tree approaches for navigating platform games. IEEE Transactions on Computational Intelligence and AI in Games 9, 3 (2016), 227--238.Google ScholarCross Ref
- Diego Perez, Miguel Nicolau, Michael O'Neill, and Anthony Brabazon. 2011. Evolving behaviour trees for the mario ai competition using grammatical evolution. In European Conference on the Applications of Evolutionary Computation. Springer, 123--132.Google ScholarDigital Library
- Franz Rothlauf and Marie Oetzel. 2006. On the locality of grammatical evolution. In European conference on genetic programming. Springer, 320--330.Google ScholarDigital Library
- Jonathan Styrud, Matteo Iovino, Mikael Norrlöf, Mårten Björkman, and Christian Smith. 2022. Combining planning and learning of behavior trees for robotic assembly. In 2022 International Conference on Robotics and Automation (ICRA). IEEE, 11511--11517.Google ScholarDigital Library
Index Terms
- Learning Behavior Trees by Evolution-Inspired Approaches
Recommendations
Crossover in Grammatical Evolution
We present an investigation into crossover in Grammatical Evolution that begins by examining a biologically-inspired homologous crossover operator that is compared to standard one and two-point operators. Results demonstrate that this homologous ...
Grammatical Evolution Using Tree Representation Learning
Neural Information ProcessingAbstractGrammatical evolution (GE) is one of the evolutionary computations, which evolves genotype to map phenotype by using the Backus-Naur Form (BNF) syntax. GE has been widely employed to represent syntactic structure of a function or a program in ...
Automated Design of Genetic Programming Classification Algorithms for Financial Forecasting Using Evolutionary Algorithms
Theory and Practice of Natural ComputingAbstractIn this work two metaheuristic algorithms namely, a genetic algorithm (GA) and grammatical evolution (GE) are used to configure genetic programming classification algorithms for financial forecasting. The performance of the classifiers evolved ...
Comments