# Robot Manipulation on Adroit (Latency Metrics)

Source: [Robot Manipulation on Adroit (Latency Metrics)](<https://www.sota2.com/research/sota/robot-manipulation-on-adroit-latency-metrics>)

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

Data updated: 2026-02-26T05:48:26.893Z

Evaluation of robot manipulation performance on the Adroit benchmark suite, measured by the time taken (latency in ms) to complete specific tasks like Hammer, Door, and Pen.

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 | Robot Manipulation |
| Dataset (including any stated split) | Adroit |
| Metric | Latency (Hammer) (ms) |
| Unit | TIME |
| Direction | Lower 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

- [Latency (Hammer) (ms)](<https://www.sota2.com/research/sota/robot-manipulation-on-adroit-latency-metrics.md?metric=Latency%20(Hammer)%20(ms)>): Lower is better; unit: TIME.

- [Latency (Door) (ms)](<https://www.sota2.com/research/sota/robot-manipulation-on-adroit-latency-metrics.md?metric=Latency%20(Door)%20(ms)>): Lower is better; unit: TIME.

- [Latency (Pen) (ms)](<https://www.sota2.com/research/sota/robot-manipulation-on-adroit-latency-metrics.md?metric=Latency%20(Pen)%20(ms)>): Lower is better; unit: TIME.

## Recorded results

| Method | Latency (Hammer) (ms) | Result date | Report paper |
| --- | --- | --- | --- |
| KAN-We-Flow | 9.5 | Not recorded | 69818138a8b01e76cc8e238b |
| FlowPolicy | 15.3 | Not recorded | 69818138a8b01e76cc8e238b |
| Simple DP3 | 103.1 | Not recorded | 69818138a8b01e76cc8e238b |
| DP3 | 129.5 | Not recorded | 69818138a8b01e76cc8e238b |

### KAN-We-Flow

Latency (Hammer) (ms): 9.5. Result ID: 6999cb7d5698665ec4490863.

[Reporting paper](<https://www.sota2.com/research/paper/69818138a8b01e76cc8e238b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69818138a8b01e76cc8e238b.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### FlowPolicy

Latency (Hammer) (ms): 15.3. Result ID: 6999cb7d5698665ec4490862.

[Reporting paper](<https://www.sota2.com/research/paper/69818138a8b01e76cc8e238b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa76381e209131cea6beff.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### Simple DP3

Latency (Hammer) (ms): 103.1. Result ID: 6999cb7d5698665ec4490861.

[Reporting paper](<https://www.sota2.com/research/paper/69818138a8b01e76cc8e238b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c76.md>)

[Implementation](<https://github.com/YanjieZe/3D-Diffusion-Policy>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DP3

Latency (Hammer) (ms): 129.5. Result ID: 6999cb7d5698665ec4490860.

[Reporting paper](<https://www.sota2.com/research/paper/69818138a8b01e76cc8e238b.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa74f31e209131cea64c76.md>)

[Implementation](<https://github.com/YanjieZe/3D-Diffusion-Policy>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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