Semantic Glitch: Agency and Artistry in an Autonomous Pixel Cloud
This work addresses the challenge of designing imperfect, narrative-driven robotic companions for artistic and creative applications, representing an incremental approach in robotics.
The paper tackles the problem of creating autonomous robotic art with character over efficiency by presenting the Semantic Glitch, a soft flying robot that uses a Multimodal Large Language Model for navigation instead of conventional sensors, resulting in emergent behaviors like landmark-based navigation and a 13-minute autonomous flight validated for distinct personas.
While mainstream robotics pursues metric precision and flawless performance, this paper explores the creative potential of a deliberately "lo-fi" approach. We present the "Semantic Glitch," a soft flying robotic art installation whose physical form, a 3D pixel style cloud, is a "physical glitch" derived from digital archaeology. We detail a novel autonomous pipeline that rejects conventional sensors like LiDAR and SLAM, relying solely on the qualitative, semantic understanding of a Multimodal Large Language Model to navigate. By authoring a bio-inspired personality for the robot through a natural language prompt, we create a "narrative mind" that complements the "weak," historically, loaded body. Our analysis begins with a 13-minute autonomous flight log, and a follow-up study statistically validates the framework's robustness for authoring quantifiably distinct personas. The combined analysis reveals emergent behaviors, from landmark-based navigation to a compelling "plan to execution" gap, and a character whose unpredictable, plausible behavior stems from a lack of precise proprioception. This demonstrates a lo-fi framework for creating imperfect companions whose success is measured in character over efficiency.