NVIDIA-ISAAC-ROS · hemalshahNV · Sep 2, 2022 · Sep 2, 2022
diff --git a/README.md b/README.md
@@ -61,16 +61,18 @@ The following are the benchmark performance results of the prepared pipelines in
   - [Updates](#updates)
 
 ## Latest Update
-Update 2022-06-30: Added format string parameter in Triton/TensorRT, switched to NITROS implementation, removed parameters in DNN Image Encoder
+Update 2022-08-31: Update to be compatible with JetPack 5.0.2
 
 
 ## Supported Platforms
 This package is designed and tested to be compatible with ROS2 Humble running on [Jetson](https://developer.nvidia.com/embedded-computing) or an x86_64 system with an NVIDIA GPU.
 
+> **Note**: Versions of ROS2 earlier than Humble are **not** supported. This package depends on specific ROS2 implementation features that were only introduced beginning with the Humble release.
+
 
 | Platform | Hardware                                                                                                                                                                                                | Software                                                                                                             | Notes                                                                                                                                                                                   |
 | -------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Jetson   | [Jetson Orin](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/)<br/>[Jetson Xavier](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-agx-xavier/) | [JetPack 5.0.1 DP](https://developer.nvidia.com/embedded/jetpack)                                                    | For best performance, ensure that [power settings](https://docs.nvidia.com/jetson/archives/r34.1/DeveloperGuide/text/SD/PlatformPowerAndPerformance.html) are configured appropriately. |
+| Jetson   | [Jetson Orin](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-orin/)<br/>[Jetson Xavier](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/jetson-agx-xavier/) | [JetPack 5.0.2](https://developer.nvidia.com/embedded/jetpack)                                                       | For best performance, ensure that [power settings](https://docs.nvidia.com/jetson/archives/r34.1/DeveloperGuide/text/SD/PlatformPowerAndPerformance.html) are configured appropriately. |
 | x86_64   | NVIDIA GPU                                                                                                                                                                                              | [Ubuntu 20.04+](https://releases.ubuntu.com/20.04/) <br> [CUDA 11.6.1+](https://developer.nvidia.com/cuda-downloads) |
 
 
@@ -81,6 +83,7 @@ To simplify development, we strongly recommend leveraging the Isaac ROS Dev Dock
 
 
 ## Quickstart with Triton
+
 > **Note**: The quickstart helps with getting raw inference (tensor) results from the two nodes. To use the packages in a useful context and get meaningful results from the package, please refer [here](#use-different-models).
 1. Set up your development environment by following the instructions [here](https://github.com/NVIDIA-ISAAC-ROS/isaac_ros_common/blob/main/docs/dev-env-setup.md).
 2. Clone this repository and its dependencies under `~/workspaces/isaac_ros-dev/src`.
@@ -390,6 +393,7 @@ For solutions to problems with using DNN models, please check [here](docs/troubl
 ## Updates
 | Date       | Changes                                                                                                                      |
 | ---------- | ---------------------------------------------------------------------------------------------------------------------------- |
+| 2022-08-31 | Update to be compatible with JetPack 5.0.2                                                                                   |
 | 2022-06-30 | Added format string parameter in Triton/TensorRT, switched to NITROS implementation, removed parameters in DNN Image Encoder |
 | 2021-11-03 | Split DOPE and U-Net into separate repositories                                                                              |
 | 2021-10-20 | Initial release                                                                                                              |
diff --git a/isaac_ros_dnn_encoders/package.xml b/isaac_ros_dnn_encoders/package.xml
@@ -13,7 +13,7 @@ license agreement from NVIDIA CORPORATION is strictly prohibited.
 <?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
 <package format="3">
   <name>isaac_ros_dnn_encoders</name>
-  <version>0.9.0</version>
+  <version>0.11.0</version>
   <description>Encoders for preprocessing before running deep learning inference</description>
   <maintainer email="hemals@nvidia.com">Hemal Shah</maintainer>
   <license>NVIDIA Isaac ROS Software License</license>
@@ -25,6 +25,8 @@ license agreement from NVIDIA CORPORATION is strictly prohibited.
   <depend>rclcpp</depend>
   <depend>rclcpp_components</depend>
   <depend>isaac_ros_nitros</depend>
+  <depend>isaac_ros_nitros_image_type</depend>
+  <depend>isaac_ros_nitros_tensor_list_type</depend>
 
   <test_depend>ament_lint_auto</test_depend>
   <test_depend>ament_lint_common</test_depend>

diff --git a/isaac_ros_dnn_encoders/src/dnn_image_encoder_node.cpp b/isaac_ros_dnn_encoders/src/dnn_image_encoder_node.cpp
@@ -15,7 +15,8 @@
 #include <unordered_map>
 #include <vector>
 
-#include "isaac_ros_nitros/types/nitros_image.hpp"
+#include "isaac_ros_nitros_image_type/nitros_image.hpp"
+#include "isaac_ros_nitros_tensor_list_type/nitros_tensor_list.hpp"
 
 namespace nvidia
 {
@@ -113,6 +114,9 @@ DnnImageEncoderNode::DnnImageEncoderNode(const rclcpp::NodeOptions options)
             "this needs to be set per the model input requirements.");
   }
 
+  registerSupportedType<nvidia::isaac_ros::nitros::NitrosImage>();
+  registerSupportedType<nvidia::isaac_ros::nitros::NitrosTensorList>();
+
   startNitrosNode();
 }
 

diff --git a/isaac_ros_dnn_inference_test/package.xml b/isaac_ros_dnn_inference_test/package.xml
@@ -13,7 +13,7 @@ license agreement from NVIDIA CORPORATION is strictly prohibited.
 <?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
 <package format="3">
   <name>isaac_ros_dnn_inference_test</name>
-  <version>0.1.0</version>
+  <version>0.11.0</version>
   <description>DNN Inference support for Isaac ROS</description>
 
   <maintainer email="hemals@nvidia.com">Hemal Shah</maintainer>

diff --git a/isaac_ros_tensor_rt/package.xml b/isaac_ros_tensor_rt/package.xml
@@ -13,7 +13,7 @@ license agreement from NVIDIA CORPORATION is strictly prohibited.
 <?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
 <package format="3">
   <name>isaac_ros_tensor_rt</name>
-  <version>0.1.0</version>
+  <version>0.11.0</version>
   <description>DNN Inference support for Isaac ROS</description>
 
   <maintainer email="cyc@nvidia.com">CY Chen</maintainer>
@@ -30,6 +30,7 @@ license agreement from NVIDIA CORPORATION is strictly prohibited.
   <depend>rclcpp</depend>
   <depend>rclcpp_components</depend>
   <depend>isaac_ros_nitros</depend>
+  <depend>isaac_ros_nitros_tensor_list_type</depend>
 
   <test_depend>ament_lint_auto</test_depend>
   <test_depend>ament_lint_common</test_depend>

diff --git a/isaac_ros_tensor_rt/src/tensor_rt_node.cpp b/isaac_ros_tensor_rt/src/tensor_rt_node.cpp
@@ -14,6 +14,8 @@
 #include <string>
 #include <vector>
 
+#include "isaac_ros_nitros_tensor_list_type/nitros_tensor_list.hpp"
+
 #include "rclcpp/rclcpp.hpp"
 #include "rclcpp_components/register_node_macro.hpp"
 
@@ -155,6 +157,8 @@ TensorRTNode::TensorRTNode(const rclcpp::NodeOptions & options)
       output_tensor_formats_[0].c_str());
   }
 
+  registerSupportedType<nvidia::isaac_ros::nitros::NitrosTensorList>();
+
   startNitrosNode();
 }
 

diff --git a/isaac_ros_triton/package.xml b/isaac_ros_triton/package.xml
@@ -13,7 +13,7 @@ license agreement from NVIDIA CORPORATION is strictly prohibited.
 <?xml-model href="http://download.ros.org/schema/package_format3.xsd" schematypens="http://www.w3.org/2001/XMLSchema"?>
 <package format="3">
   <name>isaac_ros_triton</name>
-  <version>0.10.0</version>
+  <version>0.11.0</version>
   <description>DNN Inference support for Isaac ROS</description>
 
   <maintainer email="cyc@nvidia.com">CY Chen</maintainer>
@@ -27,6 +27,7 @@ license agreement from NVIDIA CORPORATION is strictly prohibited.
   <depend>rclcpp</depend>
   <depend>rclcpp_components</depend>
   <depend>isaac_ros_nitros</depend>
+  <depend>isaac_ros_nitros_tensor_list_type</depend>
 
   <test_depend>ament_lint_auto</test_depend>
   <test_depend>ament_lint_common</test_depend>

diff --git a/isaac_ros_triton/src/triton_node.cpp b/isaac_ros_triton/src/triton_node.cpp
@@ -17,6 +17,8 @@
 #include <string>
 #include <utility>
 
+#include "isaac_ros_nitros_tensor_list_type/nitros_tensor_list.hpp"
+
 #include "rclcpp/rclcpp.hpp"
 #include "rclcpp_components/register_node_macro.hpp"
 
@@ -153,6 +155,8 @@ TritonNode::TritonNode(const rclcpp::NodeOptions & options)
       output_tensor_formats_[0].c_str());
   }
 
+  registerSupportedType<nvidia::isaac_ros::nitros::NitrosTensorList>();
+
   startNitrosNode();
 }