Structured Exploration Through Instruction Enhancement for Object Navigation

TL;DR

This paper introduces a hierarchical learning approach for object navigation that enhances instructions and utilizes a goal assessment module, improving navigation efficiency in unseen environments.

Contribution

It presents a novel hierarchical framework with instruction enhancement and a goal assessment module for improved object navigation in unseen environments.

Findings

Effective high-level planning with memory on a floorplan level

Enhanced instructions improve navigation success

Demonstrated effectiveness in dynamic domestic environments

Abstract

Finding an object of a specific class in an unseen environment remains an unsolved navigation problem. Hence, we propose a hierarchical learning-based method for object navigation. The top-level is capable of high-level planning, and building a memory on a floorplan-level (e.g., which room makes the most sense for the agent to visit next, where has the agent already been?). While the lower-level is tasked with efficiently navigating between rooms and looking for objects in them. Instructions can be provided to the agent using a simple synthetic language. The top-level intelligently enhances the instructions in order to make the overall task more tractable. Language grounding, mapping instructions to visual observations, is performed by utilizing an additional separate supervised trained goal assessment module. We demonstrate the effectiveness of our method on a dynamic configurable domestic environment.