Plan-and-Act using Large Language Models for Interactive Agreement
This work addresses the challenge of scaling LLMs to diverse HRI scenarios, though it appears incremental as it builds on existing LLM planning capabilities with specific skill design improvements.
The paper tackled the problem of using large language models (LLMs) for planning robot actions in situational human-robot interaction (HRI), balancing respect for human activity with task prioritization and timing, and achieved a success rate of 90% in test scenarios.
Recent large language models (LLMs) are capable of planning robot actions. In this paper, we explore how LLMs can be used for planning actions with tasks involving situational human-robot interaction (HRI). A key problem of applying LLMs in situational HRI is balancing between "respecting the current human's activity" and "prioritizing the robot's task," as well as understanding the timing of when to use the LLM to generate an action plan. In this paper, we propose a necessary plan-and-act skill design to solve the above problems. We show that a critical factor for enabling a robot to switch between passive / active interaction behavior is to provide the LLM with an action text about the current robot's action. We also show that a second-stage question to the LLM (about the next timing to call the LLM) is necessary for planning actions at an appropriate timing. The skill design is applied to an Engage skill and is tested on four distinct interaction scenarios. We show that by using the skill design, LLMs can be leveraged to easily scale to different HRI scenarios with a reasonable success rate reaching 90% on the test scenarios.