{"ID":2838910,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.16048","arxiv_id":"2511.16048","title":"Semantic Glitch: Agency and Artistry in an Autonomous Pixel Cloud","abstract":"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.","short_abstract":"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 ar...","url_abs":"https://arxiv.org/abs/2511.16048","url_pdf":"https://arxiv.org/pdf/2511.16048v1","authors":"[\"Qing Zhang\",\"Jing Huang\",\"Mingyang Xu\",\"Jun Rekimoto\"]","published":"2025-11-20T05:10:13Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.HC\"]","methods":"[\"Language Model\"]","has_code":false}