ForagerSim: Evaluating Embodied Map-Based Reasoning in Large-Scale Dynamic Worlds

原文：ForagerSim: Evaluating Embodied Map-Based Reasoning in Large-Scale Dynamic Worlds

作者：Tomáš Musil, Martin Kotík, Michal Vavrečka, Karla Štěpánová, Sebastian Scherer, Martin Saska

来源：arXiv cs.RO（机器人）

正文

Computer Science > Robotics

arXiv:2610.26395v1 (cs)

[Submitted on 19 Oct 2026]

Title:ForagerSim: Evaluating Embodied Map-Based Reasoning in Large-Scale Dynamic Worlds

Authors:Tomáš Musil, Martin Kotík, Michal Vavrečka, Karla Štěpánová, Sebastian Scherer, Martin Saska

View a PDF of the paper titled ForagerSim: Evaluating Embodied Map-Based Reasoning in Large-Scale Dynamic Worlds, by Tom'a\v{s} Musil and 5 other authors

View PDF

HTML (experimental)

Abstract:Animals build cognitive maps of vast environments, use them to perform map-based navigation, and might even be reusing the same circuitry used in spatial reasoning for creating and using maps of arbitrary task-spaces. In contrast, current embodied AI systems either rely on hand-engineered mapping pipelines, which break in the presence of unmodeled dynamics and are restricted to metric space, or on learned policies that rarely form map-like representations at all. Developing architectures that could learn to build and use map-like representations as flexibly as animals is, however, difficult because few embodied AI benchmarks actually require map-based reasoning. To address this, we present ForagerSim — an interdisciplinary research platform and simulation environment focused on embodied tasks that require map-based reasoning, with scenarios ranging from mobile-robot search and rescue to animal foraging in both complex mazes and vast, potentially infinite open areas. ForagerSim is highly modular and allows modifying independent axes of difficulty related to perception (abstract 2D sensing to full RGB or LiDAR), scale (room-scale to multi-km scale), topology (open-fields to complex mazes), dynamics (smoke, debris, sensorimotor failures and others) and tasks (from simple 2D coverage to foraging-inspired well-alternation tasks). We compare reinforcement learning baselines with a simple engineered robotics stack and a human player on 8 example worlds which show how different difficulty axes affect existing methods. Our results show that, when sensing is simplified to 2D, learned policies can perform multi-object search and well-alternation tasks surprisingly well in simple topologies, but they fall short of human performance in larger or more complex-topology environments where map-based baselines perform well, suggesting that map-based reasoning is the bottleneck in these scenarios.

Comments:

Code and data: this https URL

Subjects:

Robotics (cs.RO); Machine Learning (cs.LG)

Cite as:

arXiv:2610.26395 [cs.RO]

(or

arXiv:2610.26395v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2610.26395

Focus to learn more

arXiv-issued DOI via DataCite

主题

机器人 · 机器学习

由「前沿雷达」于 2026-10-19 采集。正文取自原文页面，已保留出处链接。标题与正文版权归原作者所有。