Vision-based route following by an embodied insect-inspired sparse neural network

Lu Yihe, Rana Alkhoury Maroun, Barbara Webb
3/14/2023
cs.NEcs.LGcs.RO

No confident code implementation found for this paper.

Abstract

We compared the efficiency of the FlyHash model, an insect-inspired sparse neural network (Dasgupta et al., 2017), to similar but non-sparse models in an embodied navigation task. This requires a model to control steering by comparing current visual inputs to memories stored along a training route. We concluded the FlyHash model is more efficient than others, especially in terms of data encoding.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

An Efficient Insect-inspired Approach for Visual Point-goal Navigation

81% match2026

A neuromorphic model of the insect visual system for natural image processing

80% match2026

Whole-Brain Connectomic Graph Model Enables Whole-Body Locomotion Control in Fruit Fly

80% match2026

Emergence of Maps in the Memories of Blind Navigation Agents

78% match2023

Investigating Navigation Strategies in the Morris Water Maze through Deep Reinforcement Learning

78% match2023

Direct learning of home vector direction for insect-inspired robot navigation

77% match2024

Cite this paper

@article{yihe2023visionbased,
  title  = {Vision-based route following by an embodied insect-inspired sparse neural network},
  author = {Lu Yihe and Rana Alkhoury Maroun and Barbara Webb},
  year   = {2023},
  eprint = {2303.08109},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2303.08109v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2303.08109.svg)](https://codeofpaper.com/paper/2303.08109)

Discussion