Learning Behavior Trees with Genetic Programming in Unpredictable Environments

by   Matteo Iovino, et al.

Modern industrial applications require robots to be able to operate in unpredictable environments, and programs to be created with a minimal effort, as there may be frequent changes to the task. In this paper, we show that genetic programming can be effectively used to learn the structure of a behavior tree (BT) to solve a robotic task in an unpredictable environment. Moreover, we propose to use a simple simulator for the learning and demonstrate that the learned BTs can solve the same task in a realistic simulator, reaching convergence without the need for task specific heuristics. The learned solution is tolerant to faults, making our method appealing for real robotic applications.



page 4

page 5


Combining Planning and Learning of Behavior Trees for Robotic Assembly

Industrial robots can solve very complex tasks in controlled environment...

Evolving Shepherding Behavior with Genetic Programming Algorithms

We apply genetic programming techniques to the `shepherding' problem, in...

Multitask Evolution with Cartesian Genetic Programming

We introduce a genetic programming method for solving multiple Boolean c...

Off Environment Evaluation Using Convex Risk Minimization

Applying reinforcement learning (RL) methods on robots typically involve...

Flexible Robotic Grasping with Sim-to-Real Transfer based Reinforcement Learning

Robotic manipulation requires a highly flexible and compliant system. Ta...

Recreating Bat Behavior on Quad-rotor UAVs-A Simulation Approach

We develop an effective computer model to simulate sensing environments ...

Multi-task Reinforcement Learning with a Planning Quasi-Metric

We introduce a new reinforcement learning approach combining a planning ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.