Visuospatial navigation without distance, prediction, or maps

• URL: http://arxiv.org/abs/2407.13535v2
• Date: Wed, 6 Nov 2024 21:56:53 GMT
• Title: Visuospatial navigation without distance, prediction, or maps
• Authors: Patrick Govoni, Pawel Romanczuk,
• Abstract summary: We show the sufficiency of a minimal feedforward framework in a classic visual navigation task. While visual distance enables direct trajectories to the goal, two distinct algorithms develop to robustly navigate using visual angles alone. Each of the three confers unique contextual tradeoffs as well as aligns with movement behavior observed in rodents, insects, fish, and sperm cells.
• Score: 1.3812010983144802
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Navigation is controlled by at least two partially dissociable, concurrently developed systems in the brain. The cognitive map informs an organism of its location, bearing, and distances between environmental features, enabling shortcuts. Response-based navigation, on the other hand, the process of combining percept-action pairs into routes, is regarded as inaccurate and inflexible, ultimately subserving map-based representation. As such, navigation models tend to assume the primacy of maps, top-down constructed via predictive control and distance perception, while neglecting response-based strategies. Here we show the sufficiency of a minimal feedforward framework in a classic visual navigation task. Our agents, directly translating visual perception to movement, navigate to a hidden goal in an open field, an environment often assumed to require a map-based representation. While visual distance enables direct trajectories to the goal, two distinct algorithms develop to robustly navigate using visual angles alone. Each of the three confers unique contextual tradeoffs as well as aligns with movement behavior observed in rodents, insects, fish, and sperm cells, suggesting the widespread significance of response-based strategies. We advocate further study of navigation from the bottom-up without assuming online access to computationally expensive top-down representations, which may better explain behavior under energetic or attentional constraints.

Related papers

• Hierarchical end-to-end autonomous navigation through few-shot waypoint detection [0.0]
  Human navigation is facilitated through the association of actions with landmarks. Current autonomous navigation schemes rely on accurate positioning devices and algorithms as well as extensive streams of sensory data collected from the environment. We propose a hierarchical end-to-end meta-learning scheme that enables a mobile robot to navigate in a previously unknown environment.
  arXiv  Detail & Related papers  (2024-09-23T00:03:39Z)
• 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)
• Emergence of Maps in the Memories of Blind Navigation Agents [68.41901534985575]
  Animal navigation research posits that organisms build and maintain internal spatial representations, or maps, of their environment. We ask if machines -- specifically, artificial intelligence (AI) navigation agents -- also build implicit (or'mental') maps. Unlike animal navigation, we can judiciously design the agent's perceptual system and control the learning paradigm to nullify alternative navigation mechanisms.
  arXiv  Detail & Related papers  (2023-01-30T20:09:39Z)
• ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hints [94.60414567852536]
  Long-range navigation requires both planning and reasoning about local traversability. We propose a learning-based approach that integrates learning and planning. ViKiNG can leverage its image-based learned controller and goal-directed to navigate to goals up to 3 kilometers away.
  arXiv  Detail & Related papers  (2022-02-23T02:14:23Z)
• Lifelong Topological Visual Navigation [16.41858724205884]
  We propose a learning-based visual navigation method with graph update strategies that improve lifelong navigation performance over time. We take inspiration from sampling-based planning algorithms to build image-based topological graphs, resulting in sparser graphs yet with higher navigation performance compared to baseline methods. Unlike controllers that learn from fixed training environments, we show that our model can be finetuned using a relatively small dataset from the real-world environment where the robot is deployed.
  arXiv  Detail & Related papers  (2021-10-16T06:16:14Z)
• Augmented reality navigation system for visual prosthesis [67.09251544230744]
  We propose an augmented reality navigation system for visual prosthesis that incorporates a software of reactive navigation and path planning. It consists on four steps: locating the subject on a map, planning the subject trajectory, showing it to the subject and re-planning without obstacles. Results show how our augmented navigation system help navigation performance by reducing the time and distance to reach the goals, even significantly reducing the number of obstacles collisions.
  arXiv  Detail & Related papers  (2021-09-30T09:41:40Z)
• Pushing it out of the Way: Interactive Visual Navigation [62.296686176988125]
  We study the problem of interactive navigation where agents learn to change the environment to navigate more efficiently to their goals. We introduce the Neural Interaction Engine (NIE) to explicitly predict the change in the environment caused by the agent's actions. By modeling the changes while planning, we find that agents exhibit significant improvements in their navigational capabilities.
  arXiv  Detail & Related papers  (2021-04-28T22:46:41Z)
• Occupancy Anticipation for Efficient Exploration and Navigation [97.17517060585875]
  We propose occupancy anticipation, where the agent uses its egocentric RGB-D observations to infer the occupancy state beyond the visible regions. By exploiting context in both the egocentric views and top-down maps our model successfully anticipates a broader map of the environment. Our approach is the winning entry in the 2020 Habitat PointNav Challenge.
  arXiv  Detail & Related papers  (2020-08-21T03:16:51Z)

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.