Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381551285> ?p ?o ?g. }
Showing items 1 to 77 of
77
with 100 items per page.
- W4381551285 abstract "Given a natural language, a general robot has to comprehend the instruction and find the target object or location based on visual observations even in unexplored environments. Most agents rely on massive diverse training data to achieve better generalization, which requires expensive labor. These agents often focus on common objects and fewer tasks, thus are not intelligent enough to handle different types of instructions. To facilitate research in open-set vision-and-language navigation, we propose a benchmark named MO-VLN, aiming at testing the effectiveness and generalization of the agent in the multi-task setting. First, we develop a 3D simulator rendered by realistic scenarios using Unreal Engine 5, containing more realistic lights and details. The simulator contains three scenes, i.e., cafe, restaurant, and nursing house, of high value in the industry. Besides, our simulator involves multiple uncommon objects, such as takeaway cup and medical adhesive tape, which are more complicated compared with existing environments. Inspired by the recent success of large language models (e.g., ChatGPT, Vicuna), we construct diverse high-quality data of instruction type without human annotation. Our benchmark MO-VLN provides four tasks: 1) goal-conditioned navigation given a specific object category (e.g., fork); 2) goal-conditioned navigation given simple instructions (e.g., Search for and move towards a tennis ball); 3) step-by-step instruction following; 4) finding abstract object based on high-level instruction (e.g., I am thirsty)." @default.
- W4381551285 created "2023-06-22" @default.
- W4381551285 creator A5026148404 @default.
- W4381551285 creator A5028785469 @default.
- W4381551285 creator A5047533905 @default.
- W4381551285 creator A5047878798 @default.
- W4381551285 creator A5065503853 @default.
- W4381551285 creator A5075195203 @default.
- W4381551285 creator A5087686703 @default.
- W4381551285 date "2023-06-17" @default.
- W4381551285 modified "2023-10-17" @default.
- W4381551285 title "MO-VLN: A Multi-Task Benchmark for Open-set Zero-Shot Vision-and-Language Navigation" @default.
- W4381551285 doi "https://doi.org/10.48550/arxiv.2306.10322" @default.
- W4381551285 hasPublicationYear "2023" @default.
- W4381551285 type Work @default.
- W4381551285 citedByCount "0" @default.
- W4381551285 crossrefType "posted-content" @default.
- W4381551285 hasAuthorship W4381551285A5026148404 @default.
- W4381551285 hasAuthorship W4381551285A5028785469 @default.
- W4381551285 hasAuthorship W4381551285A5047533905 @default.
- W4381551285 hasAuthorship W4381551285A5047878798 @default.
- W4381551285 hasAuthorship W4381551285A5065503853 @default.
- W4381551285 hasAuthorship W4381551285A5075195203 @default.
- W4381551285 hasAuthorship W4381551285A5087686703 @default.
- W4381551285 hasBestOaLocation W43815512851 @default.
- W4381551285 hasConcept C107457646 @default.
- W4381551285 hasConcept C127413603 @default.
- W4381551285 hasConcept C13280743 @default.
- W4381551285 hasConcept C134306372 @default.
- W4381551285 hasConcept C154945302 @default.
- W4381551285 hasConcept C177148314 @default.
- W4381551285 hasConcept C177264268 @default.
- W4381551285 hasConcept C185798385 @default.
- W4381551285 hasConcept C199360897 @default.
- W4381551285 hasConcept C201995342 @default.
- W4381551285 hasConcept C205649164 @default.
- W4381551285 hasConcept C2780451532 @default.
- W4381551285 hasConcept C2780801425 @default.
- W4381551285 hasConcept C2781238097 @default.
- W4381551285 hasConcept C31972630 @default.
- W4381551285 hasConcept C33923547 @default.
- W4381551285 hasConcept C41008148 @default.
- W4381551285 hasConcept C90509273 @default.
- W4381551285 hasConceptScore W4381551285C107457646 @default.
- W4381551285 hasConceptScore W4381551285C127413603 @default.
- W4381551285 hasConceptScore W4381551285C13280743 @default.
- W4381551285 hasConceptScore W4381551285C134306372 @default.
- W4381551285 hasConceptScore W4381551285C154945302 @default.
- W4381551285 hasConceptScore W4381551285C177148314 @default.
- W4381551285 hasConceptScore W4381551285C177264268 @default.
- W4381551285 hasConceptScore W4381551285C185798385 @default.
- W4381551285 hasConceptScore W4381551285C199360897 @default.
- W4381551285 hasConceptScore W4381551285C201995342 @default.
- W4381551285 hasConceptScore W4381551285C205649164 @default.
- W4381551285 hasConceptScore W4381551285C2780451532 @default.
- W4381551285 hasConceptScore W4381551285C2780801425 @default.
- W4381551285 hasConceptScore W4381551285C2781238097 @default.
- W4381551285 hasConceptScore W4381551285C31972630 @default.
- W4381551285 hasConceptScore W4381551285C33923547 @default.
- W4381551285 hasConceptScore W4381551285C41008148 @default.
- W4381551285 hasConceptScore W4381551285C90509273 @default.
- W4381551285 hasLocation W43815512851 @default.
- W4381551285 hasOpenAccess W4381551285 @default.
- W4381551285 hasPrimaryLocation W43815512851 @default.
- W4381551285 hasRelatedWork W1837097281 @default.
- W4381551285 hasRelatedWork W1966410754 @default.
- W4381551285 hasRelatedWork W2007544051 @default.
- W4381551285 hasRelatedWork W2325242284 @default.
- W4381551285 hasRelatedWork W2363840281 @default.
- W4381551285 hasRelatedWork W2789220062 @default.
- W4381551285 hasRelatedWork W2975200075 @default.
- W4381551285 hasRelatedWork W3168256553 @default.
- W4381551285 hasRelatedWork W3186584605 @default.
- W4381551285 hasRelatedWork W4287124629 @default.
- W4381551285 isParatext "false" @default.
- W4381551285 isRetracted "false" @default.
- W4381551285 workType "article" @default.