Evaluating the Transfer of Co-Evolved Communication from 2D to 3D Simulation
Summary
该论文研究两个机器人智能体在二维离散环境中共同演化出的通信机制,在迁移到基于物理的三维模拟器后是否仍能保持其功能作用。结果显示通信信号主要作为辅助解堵机制而非导航引导,且更长的评估时长能持续提升性能。
View Cached Full Text
Cached at: 10/10/26, 02:24 AM
Paper page - Evaluating the Transfer of Co-Evolved Communication from 2D to 3D Simulation
Source: https://huggingface.co/papers/2610.09280 This paper investigates whether a communication mechanism co-evolved between two robotic agents in a discrete 2D environment preserves its functional role after transfer to a 3D physics-based simulator. We analyze the effects of episode duration, social cues, and role asymmetry across multiple independent evolutionary runs.
Results show that performance continues to improve with longer evaluation horizons, suggesting that short episodes may underestimate learned behaviors. In both simulators, the communication signal acts primarily as a jam-assistance mechanism rather than a navigation guide, although the effect is stronger in the original 2D environment.
These findings contribute to understanding how emergent communication and cooperative behaviors transfer across simulation fidelities, an important challenge in evolutionary robotics and sim-to-sim transfer.
Similar Articles
Behavioral Persistence and Incomplete Functional Transfer of Co-evolved Communication in Evolutionary Robotics
本文评估了将协同演化的通信协议从二维仿真直接迁移到三维物理机器人环境(无重训练)的效果,发现迁移仅部分且不对称,表明涌现通信的成功迁移不仅依赖信号过程本身,还依赖其演化时的生态与导航条件。
The value of information and the emergence of communication in evolved e-puck robots
该论文研究了在PyBullet中重建的两只e-puck机器人之间通信行为的涌现条件,发现通信的出现与其所传递信息的价值成正比,而为孤立智能体设计的先天反射架构在社交任务中反而可能成为阻碍。
CoDA: Co-Evolution of Data Engines and Action Policies
CoDA 提出一种仿真数据引擎与机器人动作策略协同演进的框架,通过共享失败与学习进展记忆、视觉语言诊断以及 Text2potential 分阶段势能奖励,将机器人操作任务的分布外成功率从 5.3% 提升至 27.6%,并在 LIBERO-Pro 上取得显著改善。
Words to World: Benchmarking LLMs in Interactive Physical Environments
该论文提出了一个用于评估大语言模型在闭环物理交互中表现的基准,模型需通过连接机械臂、摄像头和传感器的系统在真实环境中执行任务并根据物理反馈调整行动。实验揭示了LLM在物理行动中的常见失败模式,如幻觉状态变化、糟糕的异常恢复和不稳定的长程规划。
Structured interactions improve distributed coordination beyond model scaling in a real-world multi-robot system
This paper investigates whether restructuring communication among robots yields larger gains than increasing onboard model size in a multi-robot transport-and-mapping task. Results show that switching to modular hierarchical interactions improves normalized performance by 47 points, while doubling neural network hidden size yields at most 9 points.