Goal-oriented Semantic Communication for Robot Arm Reconstruction in Digital Twin: Feature and Temporal Selections

TL;DR

This paper addresses the high communication burden of real-time robot-arm DT reconstruction by proposing a goal-oriented semantic communication framework that combines feature selection with temporal (time-domain) transmission control. The FS module identifies phase-specific, semantically relevant data, while the PPDQN module learns when to transmit to minimize load under reconstruction-error constraints, formulated as a C-POMDP with a Lagrangian-PID approach. The approach yields substantial load reductions (up to 80% in simulations and 74% in experiments) with comparable reconstruction accuracy across pick-and-place, pick-and-toss, and push-and-pull tasks. The work demonstrates practical impact for industrial DT systems by enabling lighter, more reliable wireless communication without compromising real-time fidelity, validated on PyBullet simulations and Franka Research 3 experiments.

Abstract

As one of the most promising technologies in industry, the Digital Twin (DT) facilitates real-time monitoring and predictive analysis for real-world systems by precisely reconstructing virtual replicas of physical entities. However, this reconstruction faces unprecedented challenges due to the everincreasing communication overhead, especially for digital robot arm reconstruction. To this end, we propose a novel goal-oriented semantic communication (GSC) framework to extract the GSC information for the robot arm reconstruction task in the DT, with the aim of minimising the communication load under the strict and relaxed reconstruction error constraints. Unlike the traditional reconstruction framework that periodically transmits a reconstruction message for real-time DT reconstruction, our framework implements a feature selection (FS) algorithm to extract the semantic information from the reconstruction message, and a deep reinforcement learning-based temporal selection algorithm to selectively transmit the semantic information over time. We validate our proposed GSC framework through both Pybullet simulations and lab experiments based on the Franka Research 3 robot arm. For a range of distinct robotic tasks, simulation results show that our framework can reduce the communication load by at least 59.5% under strict reconstruction error constraints and 80% under relaxed reconstruction error constraints, compared with traditional communication framework. Also, experimental results confirm the effectiveness of our framework, where the communication load is reduced by 53% in strict constraint case and 74% in relaxed constraint case. The demo is available at: https://youtu.be/2OdeHKxcgnk.

Figures (8)

• Figure 1: Traditional framework for robot arm reconstruction.
• Figure 2: Our proposed GSC framework for robot arm reconstruction.
• Figure 3: Phases of different robot tasks.
• Figure 4: Real-world testbed setup.
• Figure 5: Performance comparison for pick-and-place task between baselines and the proposed GSC framework in simulations.