Learning Dynamic Cognitive Map with Autonomous Navigation
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913635816701952 |
|---|---|
| author | de Tinguy, Daria Verbelen, Tim Dhoedt, Bart |
| author_facet | de Tinguy, Daria Verbelen, Tim Dhoedt, Bart |
| contents | Inspired by animal navigation strategies, we introduce a novel computational model to navigate and map a space rooted in biologically inspired principles. Animals exhibit extraordinary navigation prowess, harnessing memory, imagination, and strategic decision-making to traverse complex and aliased environments adeptly. Our model aims to replicate these capabilities by incorporating a dynamically expanding cognitive map over predicted poses within an Active Inference framework, enhancing our agent's generative model plasticity to novelty and environmental changes. Through structure learning and active inference navigation, our model demonstrates efficient exploration and exploitation, dynamically expanding its model capacity in response to anticipated novel un-visited locations and updating the map given new evidence contradicting previous beliefs. Comparative analyses in mini-grid environments with the Clone-Structured Cognitive Graph model (CSCG), which shares similar objectives, highlight our model's ability to rapidly learn environmental structures within a single episode, with minimal navigation overlap. Our model achieves this without prior knowledge of observation and world dimensions, underscoring its robustness and efficacy in navigating intricate environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_08447 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Learning Dynamic Cognitive Map with Autonomous Navigation de Tinguy, Daria Verbelen, Tim Dhoedt, Bart Robotics Artificial Intelligence Machine Learning Inspired by animal navigation strategies, we introduce a novel computational model to navigate and map a space rooted in biologically inspired principles. Animals exhibit extraordinary navigation prowess, harnessing memory, imagination, and strategic decision-making to traverse complex and aliased environments adeptly. Our model aims to replicate these capabilities by incorporating a dynamically expanding cognitive map over predicted poses within an Active Inference framework, enhancing our agent's generative model plasticity to novelty and environmental changes. Through structure learning and active inference navigation, our model demonstrates efficient exploration and exploitation, dynamically expanding its model capacity in response to anticipated novel un-visited locations and updating the map given new evidence contradicting previous beliefs. Comparative analyses in mini-grid environments with the Clone-Structured Cognitive Graph model (CSCG), which shares similar objectives, highlight our model's ability to rapidly learn environmental structures within a single episode, with minimal navigation overlap. Our model achieves this without prior knowledge of observation and world dimensions, underscoring its robustness and efficacy in navigating intricate environments. |
| title | Learning Dynamic Cognitive Map with Autonomous Navigation |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2411.08447 |