PTL : Liya Yu (13 April 2021)


Blueprint species:

Use Case Attributes

Description

Informational

Type

New

 

Blueprint Family

The AI Edge

 

Use Case

Autonomous driving taxi

 

Blueprint proposed Name

RoboTaxi

 

Initial POD Cost (capex)

Leverage Unicycle POD - less than $150k

 

Scale & Type

Up to 4 servers, x86/Arm server or deep edge class

With nVIDIA Tesla P4/T4 GPUs

 

Applications

Autonomous driving taxi

 

Power and memory restrictions

Less than 10Kw

 

Infrastructure orchestration

Docker 1.13.1 or above

K8s 1.12.5 or above- Container Orchestration

OS – CentOS 7.0 or above

 

SDN

Calico container networking, or OVS-DPDK

 

Workload Type

Containers

 

PaaSOTE Stack + Baetyl + OpenNESS

Additional Details

N/A

 


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

zhanghechun@baidu.com

zhanghechun@gmail.com

Seasoned MEC and 5G Solution Architect of Baidu, with impressive 9 years  experience in the ICT industry.

Project Manager of ODCC Edge Computing Group.

张贺纯.jpeg



Zhenhua XuBaiduxuzhenhua02@baidu.com


Liya YuBaiduyuliya@baidu.com

Y
Zhuming Zhang(Simmy Zhang)Yishi17555827@qq.com


Zhongwang Hao(haozw)Yishizw.hao@msn.cn


Yipan DengIntelyipan.deng@intel.com


Haitao WangIntelhai.tao.wang@intel.com


Xiaopeng TongIntelxiaopeng.tong@intel.com


Tina TsouArmtina.tsou@arm.com


Dechao KongBaidukongdechao@baidu.com


Wenhui ZhangPSU




N



Proposed PTL: 

Hechun Zhang

Contributors: 

Tina Tsou 

Wenhui Zhang



  • No labels

6 Comments

  1. Hi Tina/Ken, do you have an architecture spec for this proposed blueprint?

    1. Hi Shane Dewing,

      This blueprint shares the same framework of Integrated Edge Cloud (IEC) Blueprint Family.

      We can build a specific arch spec if needed. How do you feel, Ken Yi?

      1. Hi Tina Tsou,

        It was actually a little different from the previous ai edge blueprint in software architecture(IaaS and PaaS level).

    2. Hi Shane Dewing,

      This blueprint belongs to the AI Edge Blueprint family. 

      You can find the architecture from the attached PDF file or I can send you the ppt version.

  2. @Aaron Williams, Added two committers(@haozw, @Simmy Zhang)from Xinhong Inc.

  3. For the auto valet parking use case, can we leverage with Autoware?

    https://gitlab.com/autowarefoundation/autoware.auto/AutowareAuto

    Use Cases

    Autoware.Auto will initially address the following 2 use case:

    1. Autonomous Valet Parking
    2. Autonomous Depot Maneuvering

    After the initial set of milestones will be completed, Autoware.Auto will allow you to easily map a parking lot, create a map for autonomous driving and drive over this parking lot entirely autonomously in less than 2 weeks.

    ...