{"ID":5443751,"CreatedAt":"2026-07-01T02:07:11.383974684Z","UpdatedAt":"2026-07-03T13:50:35.156039308Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.31682","arxiv_id":"2606.31682","title":"HABIT: Human-Aware Behavior and Interaction Training Dataset for Robot Manipulation","abstract":"Large-scale demonstration datasets have been central to recent progress in general-purpose robot policies. However, existing datasets are collected in human-absent settings, and policies trained on such data may perform tasks competently in isolation but fail to exhibit human-aware behaviors. To address this gap, we introduce HABIT, a large-scale robot demonstration dataset for human-present environments. We organize tasks into three roles capturing distinct modes of human-robot interaction: Collaborator, where human and robot jointly accomplish a task; Coworker, where they pursue separate tasks in a shared space; and Supervisor, where the human directs the robot. The dataset comprises over 10K episodes and over 160 hours across 60 tasks. Our experiments show that training on human-present data elicits human-aware behaviors that robot-only data fails to produce: spatiotemporal synchronization in Collaborator tasks, yielding in Coworker tasks, and gesture grounding in Supervisor tasks. Moreover, training on HABIT enables rapid adaptation to new human-robot interaction tasks. By introducing human presence as a new axis of dataset diversity, HABIT extends robot policies to environments shared with humans.","short_abstract":"Large-scale demonstration datasets have been central to recent progress in general-purpose robot policies. However, existing datasets are collected in human-absent settings, and policies trained on such data may perform tasks competently in isolation but fail to exhibit human-aware behaviors. To address this gap, we in...","url_abs":"https://arxiv.org/abs/2606.31682","url_pdf":"https://arxiv.org/pdf/2606.31682v1","authors":"[\"Jaehwi Song\",\"Suchae Jeong\",\"Byeongguk Jeon\",\"Sungdong Kim\",\"Minjoon Seo\",\"Hyungmok Son\",\"Kimin Lee\"]","published":"2026-06-30T13:58:19Z","proceeding":"cs.RO","tasks":"[\"cs.RO\"]","methods":"[\"Generative Adversarial Network\"]","has_code":false}