| Raymobtime is a methodology for generating realistic wireless communication datasets using ray-tracing combined with 3D dynamic scenarios. The framework ensures physical consistency across time, frequency, and space, enabling high-fidelity modeling of mobility and channel evolution. To enrich the datasets for machine learning, sensing, and multimodal research, we incorporate: LiDAR simulations (via Blensor), RGB camera rendering (via Blender), Position and mobility metadata, Ray-tracing (computed with Remcom Wireless InSite), Vehicle and pedestrian mobility (modeled by SUMO) and Realistic urban maps from CadMapper and OpenStreetMap. Raymobtime datasets have been used in research on beam selection, beam tracking, blockage prediction, V2V modeling, and multimodal AI for next-generation mmWave/THz communications. For technical details, please refer to our publications. |
| Dataset Name | Scenario Description | Modality | Dataset Structure | Suggested Application(s) | Link/legacy name |
|---|---|---|---|---|---|
| Scenario 1 | Rosslyn · 60 GHz · 10 Mobile RX | Ray-tracing | 100 ms scenes · 30 s episodes · 116 episodes × 50 scenes · 41K channels | Beam selection · Mobility modeling | s000 |
| Scenario 2 | Rosslyn · 2.8 & 5 GHz · 10 Fixed RX | Ray-tracing | 5 ms scenes · 37 s episodes · 200 episodes × 10 scenes · 20K channels | Beam selection · Link prediction | s001 |
| Scenario 3 | Rosslyn · 2.8 & 60 GHz · 10 Fixed RX | Ray-tracing | 1 s scenes · 3 s episodes · 1800 episodes × 1 scene · 18K channels | Beam selection · LOS/NLOS analysis | s002 |
| Scenario 4 | Rosslyn · 2.8 & 5 GHz · 10 Fixed RX | Ray-tracing | 1 ms scenes · 35 s episodes · 200 episodes × 10 scenes · 20K channels | Beam selection | s003 |
| Scenario 5 | Rosslyn · 60 GHz · 10 Mobile RX | Ray-tracing | 1 s scenes · 30 s episodes · 5000 episodes × 1 scene · 35K channels | Beam tracking (short steps) | s004 |
| Scenario 6 | Rosslyn · 2.8 & 5 GHz · 10 Fixed RX | Ray-tracing | 10 ms scenes · 35 s episodes · 125 episodes × 80 scenes · 100K channels | Link prediction · Beam selection | s005 |
| Scenario 7 | Rosslyn · 28 & 60 GHz · 10 Fixed RX | Ray-tracing | 1 ms scenes · 35 s episodes · 200 episodes × 10 scenes · 20K channels | Multi-band modeling | s006 |
| Scenario 8 | Rosslyn · 60 GHz · 10 Mobile RX | Ray-tracing | 0.5 s scenes · 5 s episodes · 100 episodes × 50 scenes · 30K channels | Beam tracking · Mobility | s010 |
| Scenario 9 | Rosslyn · 60 GHz · 10 Mobile RX | Ray-tracing | 0.5 s scenes · 6 s episodes · 76 episodes × 20 scenes · 13K channels | Beam tracking | s011 |
| Scenario 10 | Rosslyn · 60 GHz · 10 Fixed RX | Ray-tracing | 0.5 s scenes · 6 s episodes · 105 episodes × 20 scenes · 21K channels | Beam selection | s012 |
| Scenario 11 | Beijing · 2.8 & 60 GHz · 10 Mobile RX | Ray-tracing + LiDAR + Camera | 1 s scenes · 5 s episodes · 50 episodes × 40 scenes · 15K channels | Multimodal ML · Beam tracking | s007 |
| Scenario 12 | Rosslyn · 60 GHz · 10 Mobile RX | Ray-tracing + LiDAR + Camera | 0.1 s scenes · 30 s episodes · 2086 episodes × 1 scene · 11K channels | Multimodal ML · Beam selection | s008 |
| Scenario 13 | Rosslyn · 60 GHz · 10 Mobile RX | Ray-tracing + LiDAR + Camera | 0.1 s scenes · 30 s episodes · 2000 episodes × 1 scene · 10K channels | Multimodal ML · Beam selection | s009 |
| Scenario 14 | Rosslyn · 5m Antenna · 20% NLOS · 60 GHz · 5 RX | Ray-tracing (Beam Tracking) | 80 ms scenes · 30 s episodes · 145 episodes × 40 scenes · 28997 channels | Beam tracking · Multimodal ML | t003 |
| Scenario 15 | Rosslyn · 10m Antenna · 50% NLOS · 60 GHz · 5 RX | Ray-tracing (Beam Tracking) | 80 ms scenes · 30 s episodes · 145 episodes × 40 scenes · 28288 channels | Beam tracking · Multimodal ML | t004 |
| Scenario 16 | Marseille · 25m Antenna · 10% NLOS · 60 GHz · 5 RX | Ray-tracing (Beam Tracking) | 80 ms scenes · episodes missing · 145 episodes × 40 scenes | Beam tracking · Multimodal ML | t005 |
| Scenario 17 | Rosslyn · 25m Antenna · 10% NLOS · 60 GHz · 5 RX | Ray-tracing (Beam Tracking) | 80 ms scenes · episodes missing · 145 episodes × 40 scenes | Beam tracking · Multimodal ML | t006 |
| Scenario 18 | Rosslyn Indoor · 60 GHz · 2 TX + 5 RX | Indoor Ray-tracing | 100 ms scenes · 30 s episodes · 20 episodes × 50 scenes | Indoor communications · Beam selection | Ip001 |
| Scenario 19 | Indoor dataset (details missing) | Indoor Ray-tracing | — | Indoor propagation | ir002 |
| Scenario 20 | Rosslyn · 60 GHz · 2 TX · 5 RX | Ray-tracing (V2V) | 100 ms scenes · 30 s episodes · 20 episodes × 50 scenes · 8.5K channels | V2V modeling · Beam selection | v001 |
| Scenario 21 | Rosslyn · 60 GHz · 1 TX · 5 RX | Ray-tracing (V2V) | 0.1 s scenes · 0.1 s episodes · 2500 episodes × 1 scene · 12.5K channels | V2V short-range · Beam tracking | v002 |