Originally published at: https://developer.nvidia.com/blog/accelerating-the-pony-ai-av-sensor-data-processing-pipeline/
Here’s how Pony.ai, which develops autonomous driving systems for robotaxis and trucks, uses GPU technology to develop a highly efficient data processing pipeline.
jwitsoe
1
Related topics
Topic | Replies | Views | Activity | |
---|---|---|---|---|
No image capture from camera via FPD Link for Orin nano R36.3 module | 36 | 438 | February 5, 2025 | |
Real-time GPU processing Peer 2 peer data copy, Linux kernel memory, kernels in kernel, | 35 | 8107 | June 30, 2010 | |
Using VPI in GStreamer | 51 | 5008 | March 8, 2023 | |
GPUDirect Storage: A Direct Path Between Storage and GPU Memory | 7 | 1091 | March 22, 2022 | |
/dev/video0 node not appearing when loading custom driver to capture pre-configured streaming camera data without i2c | 29 | 3600 | October 14, 2022 | |
Orin NX can't detect NVMe storage (SD Express PCIe) | 47 | 531 | April 15, 2025 | |
Welcome to the Jetson Projects forum! | 45 | 9837 | November 24, 2024 | |
Designing an Optimal AI Inference Pipeline for Autonomous Driving | 0 | 274 | November 30, 2022 | |
Orin in jp5.0.2 camera [vi output, imx1] process cpu occupies 100% | 23 | 2467 | December 14, 2022 | |
Batch processing using NVIDIA NIM | Docker | Self-hosted | 11 | 253 | January 29, 2025 |