PTL : Liya Yu (13 April 2021)
Blueprint species:
Use Case Attributes | Description | Informational | ||||
Type | New |
| ||||
Blueprint Family | Integrated Edge Cloud (IEC)The AI Edge |
| ||||
Use CaseSafety and security, driving assistant | Autonomousdrivingtaxi |
| ||||
Blueprint proposed Name | IEC Type 3: Autonomous vehicles as the edgeRoboTaxi |
| ||||
Initial POD Cost (capex) N | /A Leverage Unicycle POD - less than $150k |
| ||||
Scale & Type One per vehicle | Up to 4 servers, x86/Arm server or deep edge class With nVIDIA Tesla P4/T4 GPUs |
| ||||
Applications | Video Processing for AutoDriving (especially training deep learning models)
| Autonomousdrivingtaxi |
| |||
Power and memory restrictionsAutonoumous vehicles are power and memory constrained. | Less than 10Kw |
| ||||
Infrastructure orchestrationNeed Geolocation correlation with deep learning model (the trained ones in binary format) | Docker 1.13.1 or above K8s 1.12.5 or above- Container Orchestration OS – CentOS 7.0 or above |
| ||||
SDN | Calico and K8s, and Containers serving as client/server (a database to collect raw videos/video streams) and server/client (a database for trained models in binary format)container networking,or OVS-DPDK |
| ||||
Workload Type | Containers (Tensoflow, Keras containers)VMs |
| Dataplane | VPP w/ Direct GPU (e.g. GPUnet) | Additional Details | Different bus connection: Ethernet, CANbus, etc. There are mainly 4 pieces:
|
| PaaS | OTE Stack + Baetyl + OpenNESS | |||||
Additional Details | N/A |
|
| View file | ||||
|---|---|---|---|---|
|
As per the Akraino Community process and directed by TSC, any person wishing to be PTL shall self nominate themselves by putting a Y in the column. A blueprint which has only one nominee for Project Technical Lead (PTL) will be the elected lead. If there are two or more, an election will take place.
Self Nominations begin on 25 March 2021 and will conclude on 1 April 2021
Committer | Committer Company | Committer Contact Info | Committer Bio | Committer Picture | Self Nominate for PTL (Y/N |
) | |||||
| Hechun Zhang | Baidu | Seasoned MEC and 5G Solution Architect of Baidu, with impressive 9 years experience in the ICT industry. Project Manager of ODCC Edge Computing Group. |
| ||
| Zhenhua Xu | Baidu | xuzhenhua02@baidu.com | |||
| Liya Yu | Baidu | yuliya@baidu.com | Y | ||
| Zhuming Zhang(Simmy Zhang) | Yishi | 17555827@qq.com | |||
| Zhongwang Hao(haozw) | Yishi | zw.hao@msn.cn | |||
| Yipan Deng | Intel | yipan.deng@intel.com | |||
| Haitao Wang | Intel | hai.tao.wang@intel.com | |||
| Xiaopeng Tong | Intel | xiaopeng.tong@intel.com |
| Tina Tsou | Arm | tina.tsou@arm.com | |||
| Dechao Kong | Baidu | kongdechao@baidu.com | |||
| Wenhui Zhang | PSU | N |
Proposed PTL:
Ken YiHechun Zhang
Contributors:
@soshun@soshun.arai@arm.com
Committers: