Spot the Difference: A Novel Task for Embodied Agents in Changing Environments

by   Federico Landi, et al.

Embodied AI is a recent research area that aims at creating intelligent agents that can move and operate inside an environment. Existing approaches in this field demand the agents to act in completely new and unexplored scenes. However, this setting is far from realistic use cases that instead require executing multiple tasks in the same environment. Even if the environment changes over time, the agent could still count on its global knowledge about the scene while trying to adapt its internal representation to the current state of the environment. To make a step towards this setting, we propose Spot the Difference: a novel task for Embodied AI where the agent has access to an outdated map of the environment and needs to recover the correct layout in a fixed time budget. To this end, we collect a new dataset of occupancy maps starting from existing datasets of 3D spaces and generating a number of possible layouts for a single environment. This dataset can be employed in the popular Habitat simulator and is fully compliant with existing methods that employ reconstructed occupancy maps during navigation. Furthermore, we propose an exploration policy that can take advantage of previous knowledge of the environment and identify changes in the scene faster and more effectively than existing agents. Experimental results show that the proposed architecture outperforms existing state-of-the-art models for exploration on this new setting.


page 1

page 3

page 6

page 10

page 13


GraphMapper: Efficient Visual Navigation by Scene Graph Generation

Understanding the geometric relationships between objects in a scene is ...

Out of the Box: Embodied Navigation in the Real World

The research field of Embodied AI has witnessed substantial progress in ...

Auxiliary Tasks and Exploration Enable ObjectNav

ObjectGoal Navigation (ObjectNav) is an embodied task wherein agents are...

Focus on Impact: Indoor Exploration with Intrinsic Motivation

Exploration of indoor environments has recently experienced a significan...

Explore and Explain: Self-supervised Navigation and Recounting

Embodied AI has been recently gaining attention as it aims to foster the...

Embodied Navigation at the Art Gallery

Embodied agents, trained to explore and navigate indoor photorealistic e...

Emergence of Maps in the Memories of Blind Navigation Agents

Animal navigation research posits that organisms build and maintain inte...

Please sign up or login with your details

Forgot password? Click here to reset