A Comparison of Prompt Engineering Techniques for Task Planning and Execution in Service Robotics

TL;DR

This work compares prompt engineering techniques and combinations thereof within the application of high-level task planning and execution in service robotics, and measures task completion accuracy and execution time for several state-of-the-art models.

Abstract

Recent advances in LLM have been instrumental in autonomous robot control and human-robot interaction by leveraging their vast general knowledge and capabilities to understand and reason across a wide range of tasks and scenarios. Previous works have investigated various prompt engineering techniques for improving the performance of LLM to accomplish tasks, while others have proposed methods that utilize LLMs to plan and execute tasks based on the available functionalities of a given robot platform. In this work, we consider both lines of research by comparing prompt engineering techniques and combinations thereof within the application of high-level task planning and execution in service robotics. We define a diverse set of tasks and a simple set of functionalities in simulation, and measure task completion accuracy and execution time for several state-of-the-art models.

Figures (3)

• Figure 1: Overview of our simulated experimental setup to evaluate task completion. The user specifies a task in natural language. The action set describes the robot capabilities. Task planning and action selection are performed by prompting an . The robot-environment simulation executes the action and provides feedback in form of a changed state.
• Figure 2: Control flow diagrams of the five prompt engineering techniques examined. See Sec. \ref{['sec:PE']} for description.
• Figure 3: Transcript showing a Fetch task using adaptive functions and .