Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Statistics of latest Autoware's Whole Perception Pipeline Latency (Lidar only mode) #8752

Open
3 tasks done
cyn-liu opened this issue Sep 4, 2024 · 1 comment
Open
3 tasks done
Assignees
Labels
component:perception Advanced sensor data processing and environment understanding. (auto-assigned)

Comments

@cyn-liu
Copy link
Contributor

cyn-liu commented Sep 4, 2024

Checklist

  • I've read the contribution guidelines.
  • I've searched other issues and no duplicate issues were found.
  • I've agreed with the maintainers that I can plan this task.

Description

Counting the running time of the perception module(lidar-only mode) during real vehicle operation.

Environment:
Device: DELL precison3581
OS: Ubuntu22.04
GPU: NVIDIA RTX A1000 6GB Laptop
CPU: intel CORE i7

Purpose

In order to get a detailed of each node and the overall time consumption of the perception pipeline, and to facilitate developers in improving the performance of the perception module.

Possible approaches

We will investigate a reasonable method to calculate the running time of the perception pipeline.
@mitsudome-r @xmfcx
Do you have any suggestions for statistical tools and methods?

Definition of done

TODO

@cyn-liu cyn-liu added the component:perception Advanced sensor data processing and environment understanding. (auto-assigned) label Sep 4, 2024
@cyn-liu cyn-liu self-assigned this Sep 4, 2024
@xmfcx
Copy link
Contributor

xmfcx commented Sep 4, 2024

Pipeline timings (Recommended)

Easily learn about pipeline latency up-to a node you like by subscribing to node_name/pipeline_latency_ms topic.

CARET

https://github.com/orgs/autowarefoundation/discussions/2822

Takes more time to prepare, requires post processing to analyze timings.

End to end latency for whole system

For checking the latency of whole system.

An object spawns at a predetermined time and the time when the velocity changes is measured.

@cyn-liu I updated this post.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
component:perception Advanced sensor data processing and environment understanding. (auto-assigned)
Projects
Status: In Progress
Status: In Progress
Development

No branches or pull requests

2 participants