Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Ambroise Vincent
- Xinyu Wang
Authors
lidar_apollo_segmentation_tvm
Design
Usage
Neural network
This package will not run without a neural network for its inference. The network is provided by ansible script during the installation of Autoware or can be downloaded manually according to Manual Downloading. This package uses ‘get_neural_network’ function from tvm_utility package to create and provide proper dependency. See its design page for more information on how to handle user-compiled networks.
Backend
The backend used for the inference can be selected by setting the lidar_apollo_segmentation_tvm_BACKEND cmake variable.
The current available options are llvm for a CPU backend, and vulkan for a GPU backend.
It defaults to llvm.
Convolutional Neural Networks (CNN) Segmentation
See the original design by Apollo. The paragraph of interest goes up to, but excluding, the “MinBox Builder” paragraph. This package instead relies on further processing by a dedicated shape estimator.
Note: the parameters described in the original design have been modified and are out of date.
Inputs / Outputs / API
The package exports a boolean lidar_apollo_segmentation_tvm_BUILT cmake variable.
Reference
Lidar segmentation is based off a core algorithm by Apollo, with modifications from [TIER IV] (https://github.com/tier4/lidar_instance_segmentation_tvm) for the TVM backend.
Package Dependencies
System Dependencies
| Name |
|---|
| libpcl-all-dev |
Dependant Packages
| Name | Deps |
|---|---|
| lidar_apollo_segmentation_tvm_nodes |
Launch files
Messages
Services
Plugins
Recent questions tagged lidar_apollo_segmentation_tvm at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Ambroise Vincent
- Xinyu Wang
Authors
lidar_apollo_segmentation_tvm
Design
Usage
Neural network
This package will not run without a neural network for its inference. The network is provided by ansible script during the installation of Autoware or can be downloaded manually according to Manual Downloading. This package uses ‘get_neural_network’ function from tvm_utility package to create and provide proper dependency. See its design page for more information on how to handle user-compiled networks.
Backend
The backend used for the inference can be selected by setting the lidar_apollo_segmentation_tvm_BACKEND cmake variable.
The current available options are llvm for a CPU backend, and vulkan for a GPU backend.
It defaults to llvm.
Convolutional Neural Networks (CNN) Segmentation
See the original design by Apollo. The paragraph of interest goes up to, but excluding, the “MinBox Builder” paragraph. This package instead relies on further processing by a dedicated shape estimator.
Note: the parameters described in the original design have been modified and are out of date.
Inputs / Outputs / API
The package exports a boolean lidar_apollo_segmentation_tvm_BUILT cmake variable.
Reference
Lidar segmentation is based off a core algorithm by Apollo, with modifications from [TIER IV] (https://github.com/tier4/lidar_instance_segmentation_tvm) for the TVM backend.
Package Dependencies
System Dependencies
| Name |
|---|
| libpcl-all-dev |
Dependant Packages
| Name | Deps |
|---|---|
| lidar_apollo_segmentation_tvm_nodes |
Launch files
Messages
Services
Plugins
Recent questions tagged lidar_apollo_segmentation_tvm at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Ambroise Vincent
- Xinyu Wang
Authors
lidar_apollo_segmentation_tvm
Design
Usage
Neural network
This package will not run without a neural network for its inference. The network is provided by ansible script during the installation of Autoware or can be downloaded manually according to Manual Downloading. This package uses ‘get_neural_network’ function from tvm_utility package to create and provide proper dependency. See its design page for more information on how to handle user-compiled networks.
Backend
The backend used for the inference can be selected by setting the lidar_apollo_segmentation_tvm_BACKEND cmake variable.
The current available options are llvm for a CPU backend, and vulkan for a GPU backend.
It defaults to llvm.
Convolutional Neural Networks (CNN) Segmentation
See the original design by Apollo. The paragraph of interest goes up to, but excluding, the “MinBox Builder” paragraph. This package instead relies on further processing by a dedicated shape estimator.
Note: the parameters described in the original design have been modified and are out of date.
Inputs / Outputs / API
The package exports a boolean lidar_apollo_segmentation_tvm_BUILT cmake variable.
Reference
Lidar segmentation is based off a core algorithm by Apollo, with modifications from [TIER IV] (https://github.com/tier4/lidar_instance_segmentation_tvm) for the TVM backend.
Package Dependencies
System Dependencies
| Name |
|---|
| libpcl-all-dev |
Dependant Packages
| Name | Deps |
|---|---|
| lidar_apollo_segmentation_tvm_nodes |
Launch files
Messages
Services
Plugins
Recent questions tagged lidar_apollo_segmentation_tvm at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Ambroise Vincent
- Xinyu Wang
Authors
lidar_apollo_segmentation_tvm
Design
Usage
Neural network
This package will not run without a neural network for its inference. The network is provided by ansible script during the installation of Autoware or can be downloaded manually according to Manual Downloading. This package uses ‘get_neural_network’ function from tvm_utility package to create and provide proper dependency. See its design page for more information on how to handle user-compiled networks.
Backend
The backend used for the inference can be selected by setting the lidar_apollo_segmentation_tvm_BACKEND cmake variable.
The current available options are llvm for a CPU backend, and vulkan for a GPU backend.
It defaults to llvm.
Convolutional Neural Networks (CNN) Segmentation
See the original design by Apollo. The paragraph of interest goes up to, but excluding, the “MinBox Builder” paragraph. This package instead relies on further processing by a dedicated shape estimator.
Note: the parameters described in the original design have been modified and are out of date.
Inputs / Outputs / API
The package exports a boolean lidar_apollo_segmentation_tvm_BUILT cmake variable.
Reference
Lidar segmentation is based off a core algorithm by Apollo, with modifications from [TIER IV] (https://github.com/tier4/lidar_instance_segmentation_tvm) for the TVM backend.
Package Dependencies
System Dependencies
| Name |
|---|
| libpcl-all-dev |
Dependant Packages
| Name | Deps |
|---|---|
| lidar_apollo_segmentation_tvm_nodes |
Launch files
Messages
Services
Plugins
Recent questions tagged lidar_apollo_segmentation_tvm at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Ambroise Vincent
- Xinyu Wang
Authors
lidar_apollo_segmentation_tvm
Design
Usage
Neural network
This package will not run without a neural network for its inference. The network is provided by ansible script during the installation of Autoware or can be downloaded manually according to Manual Downloading. This package uses ‘get_neural_network’ function from tvm_utility package to create and provide proper dependency. See its design page for more information on how to handle user-compiled networks.
Backend
The backend used for the inference can be selected by setting the lidar_apollo_segmentation_tvm_BACKEND cmake variable.
The current available options are llvm for a CPU backend, and vulkan for a GPU backend.
It defaults to llvm.
Convolutional Neural Networks (CNN) Segmentation
See the original design by Apollo. The paragraph of interest goes up to, but excluding, the “MinBox Builder” paragraph. This package instead relies on further processing by a dedicated shape estimator.
Note: the parameters described in the original design have been modified and are out of date.
Inputs / Outputs / API
The package exports a boolean lidar_apollo_segmentation_tvm_BUILT cmake variable.
Reference
Lidar segmentation is based off a core algorithm by Apollo, with modifications from [TIER IV] (https://github.com/tier4/lidar_instance_segmentation_tvm) for the TVM backend.
Package Dependencies
System Dependencies
| Name |
|---|
| libpcl-all-dev |
Dependant Packages
| Name | Deps |
|---|---|
| lidar_apollo_segmentation_tvm_nodes |
Launch files
Messages
Services
Plugins
Recent questions tagged lidar_apollo_segmentation_tvm at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Ambroise Vincent
- Xinyu Wang
Authors
lidar_apollo_segmentation_tvm
Design
Usage
Neural network
This package will not run without a neural network for its inference. The network is provided by ansible script during the installation of Autoware or can be downloaded manually according to Manual Downloading. This package uses ‘get_neural_network’ function from tvm_utility package to create and provide proper dependency. See its design page for more information on how to handle user-compiled networks.
Backend
The backend used for the inference can be selected by setting the lidar_apollo_segmentation_tvm_BACKEND cmake variable.
The current available options are llvm for a CPU backend, and vulkan for a GPU backend.
It defaults to llvm.
Convolutional Neural Networks (CNN) Segmentation
See the original design by Apollo. The paragraph of interest goes up to, but excluding, the “MinBox Builder” paragraph. This package instead relies on further processing by a dedicated shape estimator.
Note: the parameters described in the original design have been modified and are out of date.
Inputs / Outputs / API
The package exports a boolean lidar_apollo_segmentation_tvm_BUILT cmake variable.
Reference
Lidar segmentation is based off a core algorithm by Apollo, with modifications from [TIER IV] (https://github.com/tier4/lidar_instance_segmentation_tvm) for the TVM backend.
Package Dependencies
System Dependencies
| Name |
|---|
| libpcl-all-dev |
Dependant Packages
| Name | Deps |
|---|---|
| lidar_apollo_segmentation_tvm_nodes |
Launch files
Messages
Services
Plugins
Recent questions tagged lidar_apollo_segmentation_tvm at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Ambroise Vincent
- Xinyu Wang
Authors
lidar_apollo_segmentation_tvm
Design
Usage
Neural network
This package will not run without a neural network for its inference. The network is provided by ansible script during the installation of Autoware or can be downloaded manually according to Manual Downloading. This package uses ‘get_neural_network’ function from tvm_utility package to create and provide proper dependency. See its design page for more information on how to handle user-compiled networks.
Backend
The backend used for the inference can be selected by setting the lidar_apollo_segmentation_tvm_BACKEND cmake variable.
The current available options are llvm for a CPU backend, and vulkan for a GPU backend.
It defaults to llvm.
Convolutional Neural Networks (CNN) Segmentation
See the original design by Apollo. The paragraph of interest goes up to, but excluding, the “MinBox Builder” paragraph. This package instead relies on further processing by a dedicated shape estimator.
Note: the parameters described in the original design have been modified and are out of date.
Inputs / Outputs / API
The package exports a boolean lidar_apollo_segmentation_tvm_BUILT cmake variable.
Reference
Lidar segmentation is based off a core algorithm by Apollo, with modifications from [TIER IV] (https://github.com/tier4/lidar_instance_segmentation_tvm) for the TVM backend.
Package Dependencies
System Dependencies
| Name |
|---|
| libpcl-all-dev |
Dependant Packages
| Name | Deps |
|---|---|
| lidar_apollo_segmentation_tvm_nodes |
Launch files
Messages
Services
Plugins
Recent questions tagged lidar_apollo_segmentation_tvm at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Ambroise Vincent
- Xinyu Wang
Authors
lidar_apollo_segmentation_tvm
Design
Usage
Neural network
This package will not run without a neural network for its inference. The network is provided by ansible script during the installation of Autoware or can be downloaded manually according to Manual Downloading. This package uses ‘get_neural_network’ function from tvm_utility package to create and provide proper dependency. See its design page for more information on how to handle user-compiled networks.
Backend
The backend used for the inference can be selected by setting the lidar_apollo_segmentation_tvm_BACKEND cmake variable.
The current available options are llvm for a CPU backend, and vulkan for a GPU backend.
It defaults to llvm.
Convolutional Neural Networks (CNN) Segmentation
See the original design by Apollo. The paragraph of interest goes up to, but excluding, the “MinBox Builder” paragraph. This package instead relies on further processing by a dedicated shape estimator.
Note: the parameters described in the original design have been modified and are out of date.
Inputs / Outputs / API
The package exports a boolean lidar_apollo_segmentation_tvm_BUILT cmake variable.
Reference
Lidar segmentation is based off a core algorithm by Apollo, with modifications from [TIER IV] (https://github.com/tier4/lidar_instance_segmentation_tvm) for the TVM backend.
Package Dependencies
System Dependencies
| Name |
|---|
| libpcl-all-dev |
Dependant Packages
| Name | Deps |
|---|---|
| lidar_apollo_segmentation_tvm_nodes |
Launch files
Messages
Services
Plugins
Recent questions tagged lidar_apollo_segmentation_tvm at Robotics Stack Exchange
Package Summary
| Tags | No category tags. |
| Version | 0.1.0 |
| License | Apache 2.0 |
| Build type | AMENT_CMAKE |
| Use | RECOMMENDED |
Repository Summary
| Description | |
| Checkout URI | https://github.com/ieiauto/autodrrt.git |
| VCS Type | git |
| VCS Version | main |
| Last Updated | 2025-09-29 |
| Dev Status | UNKNOWN |
| Released | UNRELEASED |
| Tags | No category tags. |
| Contributing |
Help Wanted (-)
Good First Issues (-) Pull Requests to Review (-) |
Package Description
Additional Links
Maintainers
- Ambroise Vincent
- Xinyu Wang
Authors
lidar_apollo_segmentation_tvm
Design
Usage
Neural network
This package will not run without a neural network for its inference. The network is provided by ansible script during the installation of Autoware or can be downloaded manually according to Manual Downloading. This package uses ‘get_neural_network’ function from tvm_utility package to create and provide proper dependency. See its design page for more information on how to handle user-compiled networks.
Backend
The backend used for the inference can be selected by setting the lidar_apollo_segmentation_tvm_BACKEND cmake variable.
The current available options are llvm for a CPU backend, and vulkan for a GPU backend.
It defaults to llvm.
Convolutional Neural Networks (CNN) Segmentation
See the original design by Apollo. The paragraph of interest goes up to, but excluding, the “MinBox Builder” paragraph. This package instead relies on further processing by a dedicated shape estimator.
Note: the parameters described in the original design have been modified and are out of date.
Inputs / Outputs / API
The package exports a boolean lidar_apollo_segmentation_tvm_BUILT cmake variable.
Reference
Lidar segmentation is based off a core algorithm by Apollo, with modifications from [TIER IV] (https://github.com/tier4/lidar_instance_segmentation_tvm) for the TVM backend.
Package Dependencies
System Dependencies
| Name |
|---|
| libpcl-all-dev |
Dependant Packages
| Name | Deps |
|---|---|
| lidar_apollo_segmentation_tvm_nodes |