arXiv cs.MA· Fernando Montes-Gonzalez·· 6 天前AI 评分17
e-puck 机器人进化中通信涌现与信息价值的关系研究
The value of information and the emergence of communication in evolved e-puck robots
AI 导读
两个在 PyBullet 中重建的 e-puck 机器人需找到仅经过时才能探测到的进食区，控制由带残差路径的 GRU 网络提供，可单独运行或作为 EASA 通道。当机器人获得指向食物的罗盘时，信号使用完全消失；无罗盘时小场地内三种策略表现相近，场地扩大后指称信号泛化最好。EASA 中的先天反射会约束网络并降低性能，随优先级演化被持续削弱。
正文 · 原文
Abstract:We study when communication emerges between autonomous agents and what role an innate action selection architecture plays. Two e-puck robots, reconstructed in PyBullet from their Webots model and validated against it, must find a feeding zone that can only be detected when a robot passes over it. Each robot can emit a one-bit signal whose direction is detected by the receiver. Control is provided by a GRU recurrent network with a residual path, either operating alone or as a channel within an Embedded Action Selection Architecture (EASA). Fitness measures only the time the robots spend over the food. When the robots receive a compass pointing to the food, use of the signal disappears completely. Without a compass, in a small arena, three independent runs achieved similar performance using different strategies: a referential signal, a permanent beacon, or no use of the signal. As the arena expands, the strategy based on a referential signal generalizes best. In contrast, evolving directly in the large arena does not increase the frequency of communication, but it does separate the strategies, and the referential signal clearly outperforms solitary searching. Within EASA, innate reflexes constrain the network and reduce performance. As its priorities evolve, evolution consistently weakens those reflexes. The results suggest that communication emerges in proportion to the value of the information it transmits, and that an innate scaffolding designed for isolated agents can be an impediment in a social task.
| Comments: | 21 pages, 7 figures, 5 tables. Code and data: this https URL (archived at this https URL) |
| Subjects: | Robotics (cs.RO); Multiagent Systems (cs.MA); Neural and Evolutionary Computing (cs.NE) |
| ACM classes: | I.2.9; I.2.6 |
| Cite as: | arXiv:2610.13118 [cs.RO] |
| (or arXiv:2610.13118v1 [cs.RO] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13118 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Fernando Montes-Gonzalez [view email]
[v1]
Fri, 9 Oct 2026 07:12:50 UTC (1,453 KB)
来源：arXiv cs.MA · arxiv.org