Goal oriented communication speeds up physical AI robot tasks
Goal-Oriented Communications for Physical AI: Design and Testbed
Robotics
Summary
Robots that interact with the physical world need to process lots of video data quickly, but current networks struggle with this volume and delay. The authors created a test system that sends only the most important information from a robot’s camera over a 5G network to speed up decision making. By using different ways to summarize video data, their method reduces how long tasks take by up to half and improves the chances of success. This shows that sending just task-relevant details can make robot systems more efficient in real settings.
What this means in practice
- •For robotics system developers: Build robot systems that send only task-relevant scene data to reduce communication delay and improve task completion success over 5G or future networks.
- •For industrial automation engineers: Implement efficient communication strategies in automated production lines to speed up robot responses by transmitting semantic representations instead of raw videos.
Authors
Shutong Chen, Wenkai Zhang, Adnan Aijaz, Miao Guo, Yansha Deng
Abstract
Physical AI relies on frequently-updated, latency-sensitive video stream to perceive, reason, and interact with the physical world, resulting in strict latency requirements with much higher data volumes that existing 5G networks cannot support. Goal-oriented communication (GoC) offers as a promising approach to solve this challenge by transmitting only task-relevant semantic representations. However, existing GoC frameworks were mainly evaluated in the simulations while their effectiveness has never been validated in a practical deployment of physical AI application. In this work, we develop an end-to-end GoC testbed for Physical AI, which connects a PiPER robot arm equipped with an RGB-D camera and a 5G modem to an NVIDIA Jetson AGX Orin edge server through a 5G OpenAirInterface network. We propose and implement three GoC frameworks that transmit 3D bounding boxes, 2D scene graphs, and 3D scene graphs, as three types of semantic representations, respectively. They share the common functional modules designed for closed-loop Physical AI applications, including semantic extraction, full stack 5G transmission, language model inference, digital twin validation, and robotic control. Extensive experiments on our testbed show that our GoC frameworks reduce the task completion time by up to 52.6% and improve task success probability by up to 45%, compared to the traditional framework that periodically transmits the raw image data. These results validate the practical effectiveness of our GoC framework and pave the way for efficient and reliable Physical AI applications over future 6G networks. Project website: https://sites.google.com/view/goc-physical-ai-testbed.