Structured Exploration Through Instruction Enhancement for Object Navigation
This addresses the unsolved navigation challenge of finding specific objects in new settings, though it appears incremental as it builds on existing hierarchical and instruction-based approaches.
The paper tackles the problem of object navigation in unseen environments by proposing a hierarchical learning-based method with high-level planning and low-level navigation, demonstrating its effectiveness in a dynamic domestic environment.
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.