{"paper":{"title":"Exploring Human-Robot Collaboration: Analysis of Interaction Modalities in Challenging Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Proactive robot assistance was preferred by 67% of participants and rated most useful by 78%, even though it increased completion time compared to working alone.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Alessandro Giusti, Antonio Paolillo, Cristina Iani, Lorenzo Sabattini, Simone Arreghini, Valeria Villani","submitted_at":"2026-05-13T11:35:47Z","abstract_excerpt":"This work compares three interaction modalities for human-robot collaboration: passive, reactive, and proactive. We studied 18 participants assembling a seven-layer colored tower from memory while using nearby and distant blocks. In the passive modality participants worked alone; in the reactive modality a mobile robot helped only upon request; in the proactive modality it initiated brick delivery and error signaling without explicit requests. Although robot assistance increased completion time, most participants preferred collaboration: 67% preferred proactive behavior and 78% judged it most "},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"Although robot assistance increased completion time, most participants preferred collaboration: 67% preferred proactive behavior and 78% judged it most useful. These results suggest that timely proactive support can improve user experience in controlled collaborative tasks.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The single controlled memory-tower task with 18 participants is representative of broader human-robot collaboration scenarios and that preference ratings translate to real-world usefulness.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Proactive robot assistance was preferred by 67% of participants and rated most useful by 78%, even though it increased completion time compared to working alone.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"cc99f8c02373147cd8e526386e189ac2d5172614ba3a878dc2a1b08a8d5a0ce5"},"source":{"id":"2605.13380","kind":"arxiv","version":1},"verdict":{"id":"038cf4bd-a9a1-409a-98f8-cb6813ecc65f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T17:52:28.508519Z","strongest_claim":"Although robot assistance increased completion time, most participants preferred collaboration: 67% preferred proactive behavior and 78% judged it most useful. These results suggest that timely proactive support can improve user experience in controlled collaborative tasks.","one_line_summary":"Proactive robot assistance was preferred by 67% of participants and rated most useful by 78%, even though it increased completion time compared to working alone.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The single controlled memory-tower task with 18 participants is representative of broader human-robot collaboration scenarios and that preference ratings translate to real-world usefulness.","pith_extraction_headline":""},"references":{"count":56,"sample":[{"doi":"","year":null,"title":"S. Arreghini and G. Abbate and A. Giusti and A. Paolillo , title =","work_id":"be62177d-0de3-4187-bbbf-3735e424146e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Science Robotics , volume =","work_id":"b87c05b0-b9c1-428f-9452-dd57e1efe9a2","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"How robots influence humans: A survey of nonverbal communication in social human--robot interaction , author=","work_id":"24615cbf-d067-416c-8fe6-9122275579ab","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Factors for personalization and localization to optimize human--robot interaction: A literature review , author=","work_id":"dce73069-26e8-4b33-b075-56c748b56ad5","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Evaluating fluency in human-robot collaboration , author=","work_id":"818cf729-27d3-473e-8838-cd476b988b8f","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":56,"snapshot_sha256":"217585f41cf4119641f46b7871bb9852ae69de35d2757da0cfef3735454f0a6f","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}