{"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/zson-zero-shot-object-goal-navigation-using","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","arxiv_id":"2206.12403","date":"2022-06-24","proceeding":null,"authors":["Arjun Majumdar","Gunjan Aggarwal","Bhavika Devnani","Judy Hoffman","Dhruv Batra"],"abstract":"We present a scalable approach for learning open-world object-goal navigation (ObjectNav) -- the task of asking a virtual robot (agent) to find any instance of an object in an unexplored environment (e.g., \"find a sink\"). Our approach is entirely zero-shot -- i.e., it does not require ObjectNav rewards or demonstrations of any kind. Instead, we train on the image-goal navigation (ImageNav) task, in which agents find the location where a picture (i.e., goal image) was captured. Specifically, we encode goal images into a multimodal, semantic embedding space to enable training semantic-goal navigation (SemanticNav) agents at scale in unannotated 3D environments (e.g., HM3D). After training, SemanticNav agents can be instructed to find objects described in free-form natural language (e.g., \"sink\", \"bathroom sink\", etc.) by projecting language goals into the same multimodal, semantic embedding space. As a result, our approach enables open-world ObjectNav. We extensively evaluate our agents on three ObjectNav datasets (Gibson, HM3D, and MP3D) and observe absolute improvements in success of 4.2% - 20.0% over existing zero-shot methods. For reference, these gains are similar or better than the 5% improvement in success between the Habitat 2020 and 2021 ObjectNav challenge winners. In an open-world setting, we discover that our agents can generalize to compound instructions with a room explicitly mentioned (e.g., \"Find a kitchen sink\") and when the target room can be inferred (e.g., \"Find a sink and a stove\").","url_abs":"https://arxiv.org/abs/2206.12403v2","url_pdf":"https://arxiv.org/pdf/2206.12403v2.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":"zson-zero-shot-object-goal-navigation-using","repo_url":"https://github.com/gunagg/zson","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.12403","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}