Timezone: »

MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
Saim Wani · Shivansh Patel · Unnat Jain · Angel Chang · Manolis Savva

Tue Dec 08 09:00 AM -- 11:00 AM (PST) @ Poster Session 1 #565

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.

Author Information

Saim Wani (Indian Institute of Technology Kanpur)
Shivansh Patel (Indian Institute of Technology Kanpur)
Unnat Jain (University of Illinois at Urbana Champaign)
Angel Chang (Simon Fraser University)
Manolis Savva (Simon Fraser University)

More from the Same Authors