Log In Sign Up

MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation

by   Saim Wani, et al.

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:


page 7

page 21


Navigating to Objects in Unseen Environments by Distance Prediction

Object Goal Navigation (ObjectNav) task is to navigate an agent to an ob...

Teaching Agents how to Map: Spatial Reasoning for Multi-Object Navigation

In the context of visual navigation, the capacity to map a novel environ...

Towards Versatile Embodied Navigation

With the emergence of varied visual navigation tasks (e.g, image-/object...

PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning

State-of-the-art approaches to ObjectGoal navigation rely on reinforceme...

Exploiting Scene-specific Features for Object Goal Navigation

Can the intrinsic relation between an object and the room in which it is...

Stubborn: A Strong Baseline for Indoor Object Navigation

We present a strong baseline that surpasses the performance of previousl...

Wayfinding through an unfamiliar environment

Strategies for finding one's way through an unfamiliar environment may b...