ISoLA 2024

International Symposium On Leveraging Applications of Formal Methods, Verification and Validation • Crete, Greece

Talk

Systematic Translation from Natural Language Robot Task Descriptions to STL

Time: Saturday, 2.11

Room: Room 2

Authors: Jyo Deshmukh

Abstract: Natural language is an intuitive way for humans to communicate formal requirements of cyber-physical systems, such as safety specifications, performance requirements, and task objectives with autonomous cyber-physical systems such as robots. While natural language (NL) is ambiguous, real world tasks and their safety requirements need to be communicated unambiguously. Signal Temporal Logic (STL) is a formal logic that can serve as a versatile, expressive, and unambiguous formal language to describe robotic tasks. On one hand, existing work in using STL for the robotics domain typically requires end-users to express task specifications in STL, which is a challenge for non-expert users. On the other, translating from NL to STL specifications is currently restricted to specific fragments. In this work, we propose DialogueSTL, an explainable and interactive approach for learning correct and concise STL formulas from (often) ambiguous NL descriptions. We use a combination of semantic parsing, pre-trained transformer-based language models, and user-in-the-loop clarifications aided by a small number of user demonstrations to predict the best STL formula to encode NL task descriptions. An advantage of mapping NL to STL is that there has been considerable recent work on the use of reinforcement learning (RL) to identify control policies for robots. We show we can use Deep Q-Learning techniques to learn optimal policies from the learned STL specifications. We demonstrate that DialogueSTL is e!cient, scalable, and robust, and has high accuracy in predicting the correct STL formula with a few number of demonstrations and a few interactions with an oracle user.

Paper: Download