Adding Neural Network Controllers to Behavior Trees without Destroying Performance Guarantees
This work addresses the challenge for AI designers who need efficient behaviors with reliability guarantees, though it is incremental as it builds on existing modular Behavior Tree frameworks.
The paper tackles the problem of integrating machine learning components into Behavior Trees while preserving safety and goal convergence guarantees, demonstrating the approach with an inverted pendulum example.
In this paper, we show how Behavior Trees that have performance guarantees, in terms of safety and goal convergence, can be extended with components that were designed using machine learning, without destroying those performance guarantees. Machine learning approaches such as reinforcement learning or learning from demonstration can be very appealing to AI designers that want efficient and realistic behaviors in their agents. However, those algorithms seldom provide guarantees for solving the given task in all different situations while keeping the agent safe. Instead, such guarantees are often easier to find for manually designed model-based approaches. In this paper we exploit the modularity of behavior trees to extend a given design with an efficient, but possibly unreliable, machine learning component in a way that preserves the guarantees. The approach is illustrated with an inverted pendulum example.