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

2023/03/14 by Lu Yihe, Yihe, Lu, Rana Alkhoury Maroun +3
Biochemistry, Genetics and Molecular Biology · Neuroscience · #Animal Vocal Communication and Behavior #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE) #Neurobiology and Insect Physiology Research #Robotics (cs.RO) #Visual perception and processing mechanisms

paper · pdf · doi:10.48550/arxiv.2303.08109

openalex publication_date 2023/03/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

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.

Related

• Reinforcement Learning as a Robotics-Inspired Framework for Insect Navigation: From Spatial Representations to Neural Implementation
• Visual Memory for Robust Path Following
• Learning to Navigate: Exploiting Deep Networks to Inform Sample-Based Planning During Vision-Based Navigation
• Emergence of Maps in the Memories of Blind Navigation Agents
• Almost there: Learning to navigate approximately with a grid map