Fundamental Visual Navigation Algorithms: Indirect Sequential, Biased Diffusive, & Direct Pathing
- URL: http://arxiv.org/abs/2407.13535v1
- Date: Thu, 18 Jul 2024 14:07:44 GMT
- Title: Fundamental Visual Navigation Algorithms: Indirect Sequential, Biased Diffusive, & Direct Pathing
- Authors: Patrick Govoni, Pawel Romanczuk,
- Abstract summary: We study embodied neural networks to explore information processing algorithms an organism may use for visual spatial navigation.
Surprisingly, three distinct classes of algorithms emerged, each with its own set of rules and tradeoffs, and each appear to be highly relevant to observable biological navigation behaviors.
- Score: 1.3812010983144802
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Effective foraging in a predictable local environment requires coordinating movement with observable spatial context - in a word, navigation. Distinct from search, navigating to specific areas known to be valuable entails its own particularities. How space is understood through vision and parsed for navigation is often examined experimentally, with limited ability to manipulate sensory inputs and probe into the algorithmic level of decision-making. As a generalizable, minimal alternative to empirical means, we evolve and study embodied neural networks to explore information processing algorithms an organism may use for visual spatial navigation. Surprisingly, three distinct classes of algorithms emerged, each with its own set of rules and tradeoffs, and each appear to be highly relevant to observable biological navigation behaviors.
Related papers
- Learning Where to Look: Self-supervised Viewpoint Selection for Active Localization using Geometrical Information [68.10033984296247]
This paper explores the domain of active localization, emphasizing the importance of viewpoint selection to enhance localization accuracy.
Our contributions involve using a data-driven approach with a simple architecture designed for real-time operation, a self-supervised data training method, and the capability to consistently integrate our map into a planning framework tailored for real-world robotics applications.
arXiv Detail & Related papers (2024-07-22T12:32:09Z) - A Role of Environmental Complexity on Representation Learning in Deep Reinforcement Learning Agents [3.7314353481448337]
We developed a simulated navigation environment to train deep reinforcement learning agents.
We modulated the frequency of exposure to a shortcut and navigation cue, leading to the development of artificial agents with differing abilities.
We examined the encoded representations in artificial neural networks driving these agents, revealing intricate dynamics in representation learning.
arXiv Detail & Related papers (2024-07-03T18:27:26Z) - Automated mapping of virtual environments with visual predictive coding [0.9591674293850556]
We introduce a framework in which an agent navigates a virtual environment while engaging in visual predictive coding.
While learning a next image prediction task, the agent automatically constructs an internal representation of the environment that quantitatively reflects distances.
The internal map enables the agent to pinpoint its location relative to landmarks using only visual information.
arXiv Detail & Related papers (2023-08-20T22:29:16Z) - Learning Navigational Visual Representations with Semantic Map
Supervision [85.91625020847358]
We propose a navigational-specific visual representation learning method by contrasting the agent's egocentric views and semantic maps.
Ego$2$-Map learning transfers the compact and rich information from a map, such as objects, structure and transition, to the agent's egocentric representations for navigation.
arXiv Detail & Related papers (2023-07-23T14:01:05Z) - Visual-Language Navigation Pretraining via Prompt-based Environmental
Self-exploration [83.96729205383501]
We introduce prompt-based learning to achieve fast adaptation for language embeddings.
Our model can adapt to diverse vision-language navigation tasks, including VLN and REVERIE.
arXiv Detail & Related papers (2022-03-08T11:01:24Z) - Map Induction: Compositional spatial submap learning for efficient
exploration in novel environments [25.00757828975447]
We show that humans explore new environments efficiently by inferring the structure of unobserved spaces.
Using a new behavioral Map Induction Task, we demonstrate that this computational framework explains human exploration behavior better than non-inductive models.
arXiv Detail & Related papers (2021-10-23T21:23:04Z) - Deep Learning for Embodied Vision Navigation: A Survey [108.13766213265069]
"Embodied visual navigation" problem requires an agent to navigate in a 3D environment mainly rely on its first-person observation.
This paper attempts to establish an outline of the current works in the field of embodied visual navigation by providing a comprehensive literature survey.
arXiv Detail & Related papers (2021-07-07T12:09:04Z) - Objective discovery of dominant dynamical processes with intelligible
machine learning [0.0]
We present a formal definition in which the identification of dynamical regimes is formulated as an optimization problem.
We propose an unsupervised learning framework which eliminates the need for a priori knowledge and ad hoc definitions.
Our method is a step towards unbiased data exploration that allows serendipitous discovery within dynamical systems.
arXiv Detail & Related papers (2021-06-21T20:57:23Z) - Structured Scene Memory for Vision-Language Navigation [155.63025602722712]
We propose a crucial architecture for vision-language navigation (VLN)
It is compartmentalized enough to accurately memorize the percepts during navigation.
It also serves as a structured scene representation, which captures and disentangles visual and geometric cues in the environment.
arXiv Detail & Related papers (2021-03-05T03:41:00Z) - Neural Topological SLAM for Visual Navigation [112.73876869904]
We design topological representations for space that leverage semantics and afford approximate geometric reasoning.
We describe supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation.
arXiv Detail & Related papers (2020-05-25T17:56:29Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.