Object-oriented Targets for Visual Navigation using Rich Semantic Representations
This addresses the problem of efficient and generalizable navigation for AI agents, though it appears incremental as it builds on existing semantic methods.
The paper tackles visual navigation by using rich semantic representations and object-oriented targets, enabling the agent to generalize to new targets and unseen scenes with reduced training time.
When searching for an object humans navigate through a scene using semantic information and spatial relationships. We look for an object using our knowledge of its attributes and relationships with other objects to infer the probable location. In this paper, we propose to tackle the visual navigation problem using rich semantic representations of the observed scene and object-oriented targets to train an agent. We show that both allows the agent to generalize to new targets and unseen scene in a short amount of training time.