mlsanityData to 7 Oct 2026

Structured Exploration Through Instruction Enhancement for Object Navigation

arXiv 2211.08467 ↗First posted 15 Nov 2022cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 19 of its 22 references that are in the map. First posted on arXiv 15 Nov 2022.

Builds on

19 of 22 references.

References · 19

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2019Habitat: A Platform for Embodied AI Researchcited by 1,163
  4. 2021Habitat 2.0: Training Home Assistants to Rearrange their Habitatcited by 501
  5. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 421
  6. 2016Reinforcement Learning with Unsupervised Auxiliary Taskscited by 400
  7. 2019DD-PPO: Learning Near-Perfect PointGoal Navigators from 2.5 Billion Framescited by 352
  8. 2017Cognitive Mapping and Planning for Visual Navigationcited by 209
  9. 2019Language as an Abstraction for Hierarchical Deep Reinforcement Learningcited by 138
  10. 2017Grounded Language Learning in a Simulated 3D Worldcited by 100
  11. 2017Mapping Instructions and Visual Observations to Actions with Reinforcement Learningcited by 80
  12. 2019Why Does Hierarchy (Sometimes) Work So Well in Reinforcement Learning?cited by 66
7 more
  1. 2020AllenAct: A Framework for Embodied AI Researchcited by 54
  2. 2020Auxiliary Tasks Speed Up Learning PointGoal Navigationcited by 52
  3. 2020Seeing the Un-Scene: Learning Amodal Semantic Maps for Room Navigationcited by 34
  4. 2021Differentiable SLAM-net: Learning Particle SLAM for Visual Navigationcited by 34
  5. 2020Ask Your Humans: Using Human Instructions to Improve Generalization in Reinforcement Learningcited by 32
  6. 2019Hierarchical Decision Making by Generating and Following Natural Language Instructionscited by 30
  7. 2019Benchmarking Classic and Learned Navigation in Complex 3D Environmentscited by 24

Built on by

Not cited yet.