PhysicsAssistant: An LLM-Powered Interactive Learning Robot for Physics Lab Investigations

TL;DR

PhysicsAssistant is a multimodal robot leveraging LLMs and object detection to assist K-12 physics students in labs, providing timely responses and reducing teachers' workload, with performance comparable to GPT-4 in factual understanding.

Contribution

This work introduces the first interactive multimodal robotic assistant for K-12 physics education using LLMs and object detection, demonstrating real-time assistance capabilities.

Findings

PhysicsAssistant provides timely responses with lower latency than GPT-4.

Expert ratings show comparable factual understanding between PhysicsAssistant and GPT-4.

PhysicsAssistant has potential for real-time educational support despite slightly lower response quality.

Abstract

Robot systems in education can leverage Large language models' (LLMs) natural language understanding capabilities to provide assistance and facilitate learning. This paper proposes a multimodal interactive robot (PhysicsAssistant) built on YOLOv8 object detection, cameras, speech recognition, and chatbot using LLM to provide assistance to students' physics labs. We conduct a user study on ten 8th-grade students to empirically evaluate the performance of PhysicsAssistant with a human expert. The Expert rates the assistants' responses to student queries on a 0-4 scale based on Bloom's taxonomy to provide educational support. We have compared the performance of PhysicsAssistant (YOLOv8+GPT-3.5-turbo) with GPT-4 and found that the human expert rating of both systems for factual understanding is the same. However, the rating of GPT-4 for conceptual and procedural knowledge (3 and 3.2 vs 2.2 and 2.6, respectively) is significantly higher than PhysicsAssistant (p < 0.05). However, the response time of GPT-4 is significantly higher than PhysicsAssistant (3.54 vs 1.64 sec, p < 0.05). Hence, despite the relatively lower response quality of PhysicsAssistant than GPT-4, it has shown potential for being used as a real-time lab assistant to provide timely responses and can offload teachers' labor to assist with repetitive tasks. To the best of our knowledge, this is the first attempt to build such an interactive multimodal robotic assistant for K-12 science (physics) education.