[论文解读] Sampling, Communication, and Prediction Co-Design for Synchronizing the Real-World Device and Digital Model in Metaverse

Zhen Meng, Changyang She+2 more|arXiv (Cornell University)|Jul 31, 2022

Virtual Reality Applications and Impacts被引用 4

一句话总结

本文提出了一种协同设计框架，整合采样、通信与预测，以在保持现实世界机械臂与其元宇宙中数字孪生体之间紧密同步的同时，最小化通信负载。采用知识增强的约束深度强化学习算法（KC-TD3），该框架动态优化采样率与预测时域，在严格误差约束下将平均通信负载减少高达87%，并在稳定性与尾部误差性能方面优于静态基准。

ABSTRACT

The metaverse has the potential to revolutionize the next generation of the Internet by supporting highly interactive services with the help of Mixed Reality (MR) technologies; still, to provide a satisfactory experience for users, the synchronization between the physical world and its digital models is crucial. This work proposes a sampling, communication and prediction co-design framework to minimize the communication load subject to a constraint on tracking the Mean Squared Error (MSE) between a real-world device and its digital model in the metaverse. To optimize the sampling rate and the prediction horizon, we exploit expert knowledge and develop a constrained Deep Reinforcement Learning (DRL) algorithm, named Knowledge-assisted Constrained Twin-Delayed Deep Deterministic (KC-TD3) policy gradient algorithm. We validate our framework on a prototype composed of a real-world robotic arm and its digital model. Compared with existing approaches: (1) When the tracking error constraint is stringent (MSE=0.002 degrees), our policy degenerates into the policy in the sampling-communication co-design framework. (2) When the tracking error constraint is mild (MSE=0.007 degrees), our policy degenerates into the policy in the prediction-communication co-design framework. (3) Our framework achieves a better trade-off between the average MSE and the average communication load compared with a communication system without sampling and prediction. For example, the average communication load can be reduced up to 87% when the track error constraint is 0.002 degrees. (4) Our policy outperforms the benchmark with the static sampling rate and prediction horizon optimized by exhaustive search, in terms of the tail probability of the tracking error. Furthermore, with the assistance of expert knowledge, the proposed algorithm KC-TD3 achieves better convergence time, stability, and final policy performance.

研究动机与目标

• 解决在元宇宙中以最小通信开销同步现实世界设备与数字模型的挑战。
• 在存在延迟和丢包等网络约束的情况下，仍保持低跟踪误差（MSE）。
• 协同优化采样率、通信与预测时域，以提升效率与可靠性。
• 开发一种基于强化学习的策略，可动态适应系统动态与约束条件。
• 在真实机械臂与数字孪生原型系统上，在真实网络条件下验证该框架。

提出的方法

• 提出一种协同设计框架，联合优化采样、通信与预测，实现实时同步。
• 引入一种约束深度强化学习（DRL）算法KC-TD3，通过整合专家知识引导探索并强制执行MSE约束。
• 采用马尔可夫决策过程建模，其中状态包含历史轨迹、预测状态与系统参数，以支持长时域决策。
• 采用基于去相关时间的观测时域，以确保马尔可夫性，实现稳定学习。
• 设计奖励函数，对高通信负载与跟踪误差施加惩罚，通过基于惩罚的方法强制执行约束。
• 在具有可变丢包率与MSE约束的真实机械臂与数字孪生系统上验证该框架。

Figure 1: Proposed co-design framework to synchronize a real-world device and its digital model in the metaverse.

实验结果

研究问题

• RQ1 采样、通信与预测的协同设计框架是否能显著降低通信负载，同时在元宇宙同步中保持低跟踪误差？
• RQ2 与通过穷举搜索优化的静态策略相比，所提出的KC-TD3算法在收敛性、稳定性与跟踪误差分布方面表现如何？
• RQ3 在何种条件下，该框架退化为纯采样-通信协同设计或预测-通信协同设计？
• RQ4 专家知识在多大程度上提升了DRL智能体的收敛速度与最终策略性能？
• RQ5 在真实通信信道中，不同丢包概率下系统性能如何？

主要发现

• 当平均跟踪误差约束为0.002°时，所提出的KC-TD3算法将平均通信负载减少高达87%，显著优于基线系统。
• 在严格的MSE约束（0.002°）下，策略收敛至类似纯采样-通信协同设计的行为，验证了其自适应能力。
• 在较宽松的约束（0.007°）下，策略转向预测-通信协同设计，表明其在允许条件下能有效利用预测能力。
• KC-TD3在跟踪误差的尾部概率性能方面优于基于穷举搜索的静态策略，表明其同步更加一致且可靠。
• 引入专家知识后，KC-TD3收敛更快，表现更稳定，且最终策略性能优于无约束DRL基线模型。
• 即使在10%丢包率下，KC-TD3相比基线系统仍将归一化通信负载减少高达75%，同时保持平均跟踪误差为0.002°。

Figure 2: The timing sequence of the proposed co-design framework (The senor belongs to the real world device for data generation and the transmitter belongs to a local server. The receiver and functions for construction and predication are deployed at the cloud server that operates the metaverse).