Summary of Feudal Networks For Visual Navigation, by Faith Johnson et al.
Feudal Networks for Visual Navigation
by Faith Johnson, Bryan Bo Cao, Ashwin Ashok, Shubham Jain, Kristin Dana
First submitted to arxiv on: 19 Feb 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Machine Learning (cs.LG); Robotics (cs.RO)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The researchers introduce a new approach to visual navigation using feudal learning, which employs a hierarchical structure of agents operating at different spatial and temporal scales. This framework consists of a worker agent, a mid-level manager, and a high-level manager. The high-level manager learns a memory proxy map in a self-supervised manner to record prior observations in a learned latent space, avoiding the use of graphs and odometry. The mid-level manager develops a waypoint network that outputs intermediate subgoals imitating human waypoint selection during local navigation. This framework achieves near state-of-the-art (SOTA) performance while providing a novel no-RL, no-graph, no-odometry approach to the image goal navigation task. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re lost in a new city and need to find your way back to your hotel. Humans can navigate without maps by following landmarks and remembering the path they took. This paper introduces a new way for machines to do the same thing, using “feudal learning” which is like having different levels of bosses working together to help you get where you want to go. One level makes a mental map of what it’s seen before, another level helps decide on short-term goals, and the top level figures out how to get to those goals. This approach is better than previous ones because it doesn’t need to know exactly where it’s going or keep track of its location (like with GPS). It just uses what it sees and remembers to find its way. |
Keywords
* Artificial intelligence * Latent space * Self supervised
