i-Dris integrates 5G mmWave base stationreconfigurable intelligent surface (RIS) for improving signal coverage/throughput. We design multi-time scaled temporal reinforcement learning for RIS deployment equipped on auto-guided vehicle, which determines future actions from both historicalcurrent rates observed from the edge server. Under blockagesnon-line-of-sight, i-Dris can achieve 800~900 Mbps rate (1.2~3.6x more compared to non-RIS). i-Dris only requires 10-min of deployment time (1 hr for other methods). Compared to existing prototypes in academia/industry, i-Dris does not need fiber, huge human resources, re-measurementoffline training. It learns from historical data guaranteering robustness to changing environments.

i-Dris integrates Nokis 5G mmWave BS, AGV-RIS for auto-deploymentedge server for monitoring performance. By reflecting mmWave signals from RIS, we improve 20~40 dB SNR from blockagesNLOS20 dB SNR from human blockageshand-held device behaviors achieving optimal rate of 800~900 Mbps. Multi-RIS can also sustain 600 Mbps under multi-reflection, which auto-adjusts its deployment with 10 min compared to 1 hr from existing solutions. We design multi-time scaled temporal reinforcement learning resolving time-variant channel fading. Different time scales are decided for obtaining future actions. Compared to existing prototypes in academia/industry, i-Dris does not need fiber, human resources, re-measurementoffline training.

i-Dris has addressed arising mmWave issues such as deployment expenditure, high maintenance cost, human resources,lowered signal quality due to blockagesNLOS from buildingspeople. i-Dris system can provide high throughput performance under cost-effectiveefficient AGV-RIS deployment through plug-and-play manner. i-Dris benefits operators, manufactoryindustry with economical advantages based on its compatibility to existing protocolsfuture extension to intelligent services, private networksmulti-spectrum sensing/accessing in smart warehouse, O-RANnext-generation Wi-Fi. i-Dris has gained Taiwanese technology transfer with 10 million royalty. Related projects are funded by MoEAMoST with 8 patents.