Alchemist: LLM-Aided End-User Development of Robot Applications
Authors
Large Language Models (LLMs) have the potential to catalyze a paradigm shift in end-user robot programming-moving from the conventional process of user specifying programming logic to an iterative, collaborative process in which the user specifies desired program outcomes while LLM produces detailed specifications.We introduce a novel integrated development system, Alchemist, that leverages LLMs to empower end-users in creating, testing, and running robot programs using natural language inputs, aiming to reduce the required knowledge for developing robot applications.We present a detailed examination of our system design and provide an exploratory study involving true end-users to assess capabilities, usability, and limitations of our system.Through the design, development, and evaluation of our system, we derive a set of lessons learned from the use of LLMs in robot programming.We discuss how LLMs may be the next frontier for democratizing end-user development of robot applications.
Research Questions / Practical Problems
Question signals indexed for this paper.
- 80%
Discovering the Syntax and Strategies of Natural Language Programming with Generative Language Models
CHI '22· Generative AI (Text, Image, Music, Video) +1
- 80%
"What It Wants Me To Say": Bridging the Abstraction Gap Between End-User Programmers and Code-Generating Large Language Models
CHI '23· Generative AI (Text, Image, Music, Video) +1
- 80%
D-Twins: Your Digital Twin Designed for Real-Time Boredom Intervention
CHI '25· Generative AI (Text, Image, Music, Video) +1
- 80%
Take It, Leave It, or Fix It: Measuring Productivity and Trust in Human-AI Collaboration
IUI '24· Generative AI (Text, Image, Music, Video) +1
- 67%
Method for Exploring Generative Adversarial Networks (GANs) via Automatically Generated Image Galleries
CHI '21· Generative AI (Text, Image, Music, Video) +2
- 67%
MUD: Towards a Large-Scale and Noise-Filtered UI Dataset for Modern Style UI Modeling
CHI '24· Generative AI (Text, Image, Music, Video) +1
- 67%
Ivie: Lightweight Anchored Explanations of Just-Generated Code
CHI '24· Generative AI (Text, Image, Music, Video) +2
- 67%
Can you pass that tool?: Implications of Indirect Speech in Physical Human-Robot Collaboration
CHI '25· Agent Personality & Anthropomorphism +2
- 67%
Generative AI Uses and Risks for Knowledge Workers in a Science Organization
CHI '25· Generative AI (Text, Image, Music, Video) +2
- 67%
How the Role of Generative AI Shapes Perceptions of Value in Human-AI Collaborative Work
CHI '25· Generative AI (Text, Image, Music, Video) +1
Based on Jaccard similarity of research subtopics & professions (≥60%)