# 3D Occupancy Mapping on Room, Soulcity, and Gascola

Source: [3D Occupancy Mapping on Room, Soulcity, and Gascola](<https://www.sota2.com/research/sota/3d-occupancy-mapping-on-room-soulcity-and-gascola>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-01T06:53:11.073Z

Evaluation of 3D Occupancy Mapping performance on the combined Room, Soulcity, and Gascola datasets, focusing on map construction/query throughput and power consumption.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | 3D Occupancy Mapping |
| Dataset (including any stated split) | Room, Soulcity, and Gascola |
| Metric | Map Construction Throughput (fps) |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [Map Construction Throughput (fps)](<https://www.sota2.com/research/sota/3d-occupancy-mapping-on-room-soulcity-and-gascola.md?metric=Map%20Construction%20Throughput%20(fps)>): Higher is better; unit: SCALAR.

- [Map Query Throughput (K cps)](<https://www.sota2.com/research/sota/3d-occupancy-mapping-on-room-soulcity-and-gascola.md?metric=Map%20Query%20Throughput%20(K%20cps)>): Higher is better; unit: SCALAR.

- [Average Map Construction Power (W/mW)](<https://www.sota2.com/research/sota/3d-occupancy-mapping-on-room-soulcity-and-gascola.md?metric=Average%20Map%20Construction%20Power%20(W%2FmW)>): Lower is better; unit: OTHER.

- [Average Map Query Power (W/mW)](<https://www.sota2.com/research/sota/3d-occupancy-mapping-on-room-soulcity-and-gascola.md?metric=Average%20Map%20Query%20Power%20(W%2FmW)>): Lower is better; unit: OTHER.

## Recorded results

| Method | Map Construction Throughput (fps) | Result date | Report paper |
| --- | --- | --- | --- |
| Gleanmer | 88 | Not recorded | 69cca6750636e5bf4afcbab2 |
| OMU | 61 | Not recorded | 69cca6750636e5bf4afcbab2 |
| NVIDIA Jetson TX2 | 44 | Not recorded | 69cca6750636e5bf4afcbab2 |
| NVIDIA Jetson TX2 | 32 | Not recorded | 69cca6750636e5bf4afcbab2 |

### Gleanmer

Map Construction Throughput (fps): 88. Result ID: 69ccc0d347f34ce924b5e85e.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6750636e5bf4afcbab2.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69cca6750636e5bf4afcbab2.md>)

Recorded evaluation configuration: {"Technology":"16 nm","Compute Platform":"ASIC","Mapping Framework":"GMMap \[7\]","Chip Area":"4 mm²","Core Area":"2.6 mm²","Supply Voltage":"0.85 V (construction) 0.95 V (query)","Operating Frequency":"125 MHz (construction) 250 MHz (query)","On-chip Memory":"622 KB"}. This record does not assert independent reproduction.

### OMU

Map Construction Throughput (fps): 61. Result ID: 69ccc0d347f34ce924b5e85d.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6750636e5bf4afcbab2.md>)

Recorded evaluation configuration: {"Technology":"12 nm","Compute Platform":"ASIC","Mapping Framework":"OctoMap \[2\]","Core Area":"2.5 mm²","Supply Voltage":"0.8 V","Operating Frequency":"1 GHz","On-chip Memory":"2 MB"}. This record does not assert independent reproduction.

### NVIDIA Jetson TX2

Map Construction Throughput (fps): 44. Result ID: 69ccc0d347f34ce924b5e85c.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6750636e5bf4afcbab2.md>)

Recorded evaluation configuration: {"Technology":"16 nm","Compute Platform":"ARM Cortex A57 CPU & 256-Core GPU","Mapping Framework":"GMMap \[7\]","Supply Voltage":"20 V","Operating Frequency":"CPU: 0.4 - 2 GHz; GPU: 0.9 – 1.3 GHz"}. This record does not assert independent reproduction.

### NVIDIA Jetson TX2

Map Construction Throughput (fps): 32. Result ID: 69ccc0d347f34ce924b5e85b.

[Reporting paper](<https://www.sota2.com/research/paper/69cca6750636e5bf4afcbab2.md>)

Recorded evaluation configuration: {"Technology":"16 nm","Compute Platform":"ARM Cortex A57 CPU","Mapping Framework":"GMMap \[7\]","Supply Voltage":"20 V","Operating Frequency":"CPU: 0.4 - 2 GHz"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
