Emergence of Maps in the Memories of Blind Navigation Agents
-
Published:2023-06
Issue:2
Volume:9
Page:8-14
-
ISSN:2372-3483
-
Container-title:AI Matters
-
language:en
-
Short-container-title:AI Matters
Author:
Wijmans Erik1, Savva Manolis2, Essa Irfan3, Lee Stefan4, Morcos Ari S.5, Batra Dhruv6
Affiliation:
1. Georgia Institute of Technology & FAIR, Meta AI 2. Simon Fraser University & FAIR, Meta AI 3. Georgia Institute of Technology 4. Oregon State University 5. FAIR, Meta AI 6. FAIR, Meta AI & Georgia Institute of Technology
Abstract
Decades of research into intelligent animal navigation posits that organisms build and maintain internal spatial representations (or maps)
1
of their environment, that enables the organism to determine and follow task-appropriate paths (Epstein, Patai, Julian, & Spiers, 2017; O'keefe & Nadel, 1978; Tollman, 1948). Hamsters, wolves, chimpanzees, and bats leverage prior exploration to determine and follow shortcuts they may never have taken before (Chapuis & Scardigli, 1993; Harten, Katz, Goldshtein, Handel, & Yovel, 2020; Menzel, 1973; Peters, 1976; Toledo et al., 2020). Even blind mole rats and animals rendered situationally-blind in dark environments demonstrate shortcut behaviors (Avni, Tzvaigrach, & Eilam, 2008; Kimchi, Etienne, & Terkel, 2004; Maaswinkel & Whishaw, 1999). Ants forage for food along meandering paths but take near-optimal return trips (Müller & Wehner, 1988), though there is some controversy about whether insects like ants and bees are capable of forming maps (Cheung et al., 2014; Cruse & Wehner, 2011).
Publisher
Association for Computing Machinery (ACM)
Reference33 articles.
1. Anderson , P. , Chang , A. X. , Chaplot , D. S. , Dosovitskiy , A. , Gupta , S. , Koltun , V. , ... Zamir , A. R. ( 2018 ). On evaluation of embodied navigation agents. CoRR, abs/1807.06757. Retrieved from http://arxiv.org/abs/1807.06757 Anderson, P., Chang, A. X., Chaplot, D. S., Dosovitskiy, A., Gupta, S., Koltun, V., ... Zamir, A. R. (2018). On evaluation of embodied navigation agents. CoRR, abs/1807.06757. Retrieved from http://arxiv.org/abs/1807.06757 2. Exploration and navigation in the blind mole rat (spalax ehrenbergi): global calibration as a primer of spatial representation;Avni R.;Journal of Experimental Biology,2008 3. Building, Registrating, and Fusing Noisy Visual Maps 4. Shortcut ability in hamsters (Mesocricetus auratus): The role of environmental and kinesthetic information 5. Chattopadhyay , P. , Hoffman , J. , Mottaghi , R. , & Kembhavi , A. ( 2021 ). Robustnav: Towards benchmarking robustness in embodied navigation . In Proceedings of ieee conference on computer vision and pattern recognition (cvpr). Chattopadhyay, P., Hoffman, J., Mottaghi, R., & Kembhavi, A. (2021). Robustnav: Towards benchmarking robustness in embodied navigation. In Proceedings of ieee conference on computer vision and pattern recognition (cvpr).
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Optimal foraging strategies can be learned;New Journal of Physics;2024-01-01 2. Object Goal Navigation with Recursive Implicit Maps;2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS);2023-10-01
|
|