Last-Mile Embodied Visual Navigation

Justin Wasserman, Karmesh Yadav, Girish Chowdhary, Abhinav Gupta, Unnat Jain

Research output: Contribution to journalConference articlepeer-review


Realistic long-horizon tasks like image-goal navigation involve exploratory and exploitative phases. Assigned with an image of the goal, an embodied agent must explore to discover the goal, i.e., search efficiently using learned priors. Once the goal is discovered, the agent must accurately calibrate the last-mile of navigation to the goal. As with any robust system, switches between exploratory goal discovery and exploitative last-mile navigation enable better recovery from errors. Following these intuitive guide rails, we propose SLING to improve the performance of existing image-goal navigation systems. Entirely complementing prior methods, we focus on last-mile navigation and leverage the underlying geometric structure of the problem with neural descriptors. With simple but effective switches, we can easily connect SLING with heuristic, reinforcement learning, and neural modular policies. On a standardized image-goal navigation benchmark [1], we improve performance across policies, scenes, and episode complexity, raising the state-of-the-art from 45% to 55% success rate. Beyond photorealistic simulation, we conduct real-robot experiments in three physical scenes and find these improvements to transfer well to real environments. Code and results:

Original languageEnglish (US)
Pages (from-to)666-678
Number of pages13
JournalProceedings of Machine Learning Research
StatePublished - 2023
Event6th Conference on Robot Learning, CoRL 2022 - Auckland, New Zealand
Duration: Dec 14 2022Dec 18 2022


  • AI Habitat
  • Embodied AI
  • Perspective-n-Point
  • Robot Learning
  • Sim-to-Real
  • Visual Navigation

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability


Dive into the research topics of 'Last-Mile Embodied Visual Navigation'. Together they form a unique fingerprint.

Cite this