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

feat(autoware_lidar_bevfusion): implementation of bevusion using tensorrt #10024

Draft
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

knzo25
Copy link
Contributor

@knzo25 knzo25 commented Jan 27, 2025

Description

This PR introduces BEVFusion to autoware using TensorRT.
However, it requires TensorRT10, which is being updated here
As such, this PR will remain as a draft until the previous PR gets merged.

In addition, the following dependencies are needed:

  • cuda-nvrtc-dev-12-4
  • spconv

A PR will be send to add nvrtc to autoware.
For spconv, two alternatives were talked with the AWF:

The onnx files will be provided after during the review of this PR of at the point of merging
I would like to ask reviewers to let the "integration" into the pipeline/launchers to a posterior PR 🙏

Related links

Parent Issue:

  • Link

How was this PR tested?

Notes for reviewers

None.

Interface changes

None.

Effects on system behavior

None.

@knzo25 knzo25 requested a review from scepter914 January 27, 2025 05:14
@knzo25 knzo25 self-assigned this Jan 27, 2025
@github-actions github-actions bot added component:perception Advanced sensor data processing and environment understanding. (auto-assigned) component:sensing Data acquisition from sensors, drivers, preprocessing. (auto-assigned) labels Jan 27, 2025
Copy link

Thank you for contributing to the Autoware project!

🚧 If your pull request is in progress, switch it to draft mode.

Please ensure:

@xmfcx
Copy link
Contributor

xmfcx commented Jan 27, 2025

@knzo25
Copy link
Contributor Author

knzo25 commented Jan 27, 2025

@xmfcx
Although both use viewtransform, they are different papers and modalities
https://arxiv.org/pdf/2112.11790
https://arxiv.org/pdf/2205.13542

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) component:sensing Data acquisition from sensors, drivers, preprocessing. (auto-assigned)
Projects
Status: To Triage
Development

Successfully merging this pull request may close these issues.

2 participants