2020/12/07 by Saim Wani, Wani, Saim, Shivansh Patel +7 · 44 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Artificial Intelligence (cs.AI) #Artificial intelligence #Computer Vision and Pattern Recognition (cs.CV) #Computer science #Computer vision #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Feature (linguistics) #Human–computer interaction #Machine Learning (cs.LG) #Mobile robot #Mobile robot navigation #Multimodal Machine Learning Applications #Navigation system #Observability #Oracle #Robot #Robotics (cs.RO) #Set (abstract data type) #Task (project management) #cs.AI #cs.CV #cs.LG #cs.RO
paper · pdf · doi:10.48550/arxiv.2012.03912
published in arXiv (Cornell University) (Cornell University) · Project page: https://shivanshpatel35.github.io/multi-ON/ ; the first three authors contributed equally
arxiv created 2020/12/07 · openalex publication_date 2020/12/07 · arxiv updated 2020/12/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Navigation tasks in photorealistic 3D environments are challenging because they require perception and effective planning under partial observability. Recent work shows that map-like memory is useful for long-horizon navigation tasks. However, a focused investigation of the impact of maps on navigation tasks of varying complexity has not yet been performed. We propose the multiON task, which requires navigation to an episode-specific sequence of objects in a realistic environment. MultiON generalizes the ObjectGoal navigation task and explicitly tests the ability of navigation agents to locate previously observed goal objects. We perform a set of multiON experiments to examine how a variety of agent models perform across a spectrum of navigation task complexities. Our experiments show that: i) navigation performance degrades dramatically with escalating task complexity; ii) a simple semantic map agent performs surprisingly well relative to more complex neural image feature map agents; and iii) even oracle map agents achieve relatively low performance, indicating the potential for future work in training embodied navigation agents using maps. Video summary: https://youtu.be/yqTlHNIcgnY