{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/interactively-picking-real-world-objects-with","title":"Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions","arxiv_id":"1710.06280","date":"2017-10-17","proceeding":null,"authors":["Jun Hatori","Yuta Kikuchi","Sosuke Kobayashi","Kuniyuki Takahashi","Yuta Tsuboi","Yuya Unno","Wilson Ko","Jethro Tan"],"abstract":"Comprehension of spoken natural language is an essential component for robots\nto communicate with human effectively. However, handling unconstrained spoken\ninstructions is challenging due to (1) complex structures including a wide\nvariety of expressions used in spoken language and (2) inherent ambiguity in\ninterpretation of human instructions. In this paper, we propose the first\ncomprehensive system that can handle unconstrained spoken language and is able\nto effectively resolve ambiguity in spoken instructions. Specifically, we\nintegrate deep-learning-based object detection together with natural language\nprocessing technologies to handle unconstrained spoken instructions, and\npropose a method for robots to resolve instruction ambiguity through dialogue.\nThrough our experiments on both a simulated environment as well as a physical\nindustrial robot arm, we demonstrate the ability of our system to understand\nnatural instructions from human operators effectively, and how higher success\nrates of the object picking task can be achieved through an interactive\nclarification process.","url_abs":"http://arxiv.org/abs/1710.06280v2","url_pdf":"http://arxiv.org/pdf/1710.06280v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"interactively-picking-real-world-objects-with","repo_url":"https://github.com/pfnet-research/picking-instruction","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}}],"tasks":[{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"}],"methods":[],"datasets_introduced":[{"slug":"pfn-pic","name":"PFN-PIC","full_name":"PFN Picking Instructions for Commodities Dataset"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1710.06280","atlas_url":"https://app.syntology.ai/?focus=1710.06280","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}