Ubotica Technologies Space Activities Overview Providing AI - - PowerPoint PPT Presentation

▶
ubotica technologies
SMART_READER_LITE
LIVE PREVIEW

Ubotica Technologies Space Activities Overview Providing AI - - PowerPoint PPT Presentation

Jun 04, 2023 107 likes •325 views

Ubotica Technologies Space Activities Overview Providing AI Solutions for Edge Based Computer Vision Applications Ubotica Introduction 2 Providing AI solutions for edge based Computer Vision applications Edge processing Process data at

slide-1
SLIDE 1

Providing AI Solutions for Edge Based Computer Vision Applications

Ubotica Technologies

Space Activities Overview

slide-2
SLIDE 2

2

Ubotica Introduction

  • Edge processing
  • Process data at source rather than central node
  • “Photons in, metadata out”
  • Space is the ultimate edge!
  • Why process at the edge?
  • Power | Latency | Autonomy

Providing AI solutions for edge based Computer Vision applications

slide-3
SLIDE 3

3

Ubotica Overview

  • Myriad MDK Development Licensee from

Intel/Movidius

  • Preferred partner

EMBEDDED AI & CV AUTOMATION SPACE BIOMEDICAL

Team of 15 split between Dublin and Madrid

slide-4
SLIDE 4

4

Ubotica Space Roadmap

Credit: CERN/Maximilien Brice

Qualification System SW HW

slide-5
SLIDE 5

5

Myriad Vision Processing Unit

  • Myriad 2 AI and CV engine
  • 12 VLIW SHAVE vector cores
  • >1 TOPS
  • Vision hardware accelerators
  • Stacked DDR
  • Software reconfigurable

hardware–software platform

  • 28nm HPC process node
  • Ideally suited for in-orbit
  • Low thermal budget
  • Low power budget (~1W)

9.5mm x 8mm

Credit: Intel Movidius

slide-6
SLIDE 6

6

Myriad Advantages

Neural Network Inference

  • Efficient embedded NN inference
  • 12 SHAVE vector engines and large cache-like CMX multi-ported memory
  • NN firmware optimised by Intel
  • Broad NN framework and network compatibility through OpenVINO
  • Caffe, TensorFlow, MXNet
  • Inception, ResNet, MobileNet, YOLO, SqueezeNet…
  • Large range of trained AI models
  • Models already qualified by Intel
  • Freely available and ready to use
  • Neural Compute Stick
  • Convenient development and hardware validation tool
slide-7
SLIDE 7

7

Myriad + Ubotica Advantages

Computer Vision (CV) and Image Signal Processing (ISP)

  • Efficient embedded CV and ISP functions on Myriad
  • Highly efficient hardware filters for common ISP functions
  • Library of optimised ISP and CV kernels executing in parallel on vector engines

processors

  • Custom ISP/CV pipelines
  • Drag-and-drop Configuration Tool
  • Runs in-browser
  • Runtime reconfigurable
  • New pipelines can be submitted to Myriad at

runtime

  • No re-compilation required
  • No interruption to embedded application
slide-8
SLIDE 8

8

CVAI Toolkit for Myriad

Ubotica HW & SW

UB0100 CubeSat CV & AI Board HPCB EO Data Processing Board

HW SW

slide-9
SLIDE 9

9

SW: CVAI Toolkit

  • Unlock the CV and ISP capabilities of the Myriad
  • Enable users to develop their own applications
  • User API
  • Utilise hardware blocks of Myriad 2 for efficient CV
  • Reconfigurable Image Signal Processing pipeline
  • Pre-process frames for inference
  • Perform optimised AI inference
  • Runtime interaction over Ethernet and USB
  • Integrates NN runtime dependability measure

CV AI ISP

slide-10
SLIDE 10

10

SW: CVAI Toolkit

slide-11
SLIDE 11

11

HW: UB0100 CubeSat Board for AI and CV Acceleration

  • USB/Ethernet control and data interface, PC104 form factor
  • For more details see: https://www.ubotica.com/ub0100
slide-12
SLIDE 12

12

HW: HPCB Backplane Solution

  • GR-VPX-XCKU060 and GR-HPCB-FMC-M2 High Performance Compute

Board for EO data processing

  • Led by Cobham Gaisler
  • Specifications
  • FPGA
  • Rad-hard supervisor
  • Myriad 2s
  • Board available Q2 2021
  • For more details see
  • https://www.gaisler.com/index.php/products/boards
slide-13
SLIDE 13

13

Myriad 2 Radiation Characterisation

  • COTS device
  • Performance under cosmic radiation must be characterised
  • Highly penetrating ion beams required due to Myriad 2 SoC

construction

  • Preliminary radiation characterisation
  • De-risk phase complete (low LETs)
  • SEL (CERN heavy-ion)
  • SEU (GSI heavy-ion)
  • TID (ESTEC Co-60)
  • No critical sensitivity observed
  • Further tests at higher LETs for full characterisation in 2021
  • Heavy Ion, Proton/Neutron

Credit: CERN/Maximilien Brice

slide-14
SLIDE 14

14

  • Ship identification & classification (time critical)
  • Hyperspectral filtering (data reduction)
  • Fire detection (time critical)
  • Navigation (autonomy)

Ubotica Edge CVAI - Applications

Credit: NASA

slide-15
SLIDE 15

15

Ubotica In-Orbit Use Case: PhiSat-1

  • Detecting clouds in EO data in real-time
  • Demonstrate AI inference in-flight
  • Improve downlink bandwidth utilisation
slide-16
SLIDE 16

16

Ubotica In-Orbit Use Case: PhiSat-1

  • Myriad 2-enabled in-orbit AI demonstrator
  • Flying on HyperScout-2 hyperspectral payload
  • Performing automatic cloud detection
  • Providing Myriad 2 in-flight performance data

Credit: CERN/Maximilien Brice Credit: cosine

Ubotica AI Engine HyperScout-2

slide-17
SLIDE 17

17

Ubotica In-Orbit Use Case: PhiSat-1

Engineering Model

Credit: ESA/Cosine

Ubotica AI Engine integrated on sensor payload PhiSat-1

Credit: Tyvak

slide-18
SLIDE 18

18

Ubotica GNC Use Case: AIVIONICS

  • AIVIONICS project
  • AI for Guidance, Navigation & Control applications
  • Incorporating AI dependability scoring
  • Two use cases being studied
  • Moon/asteroid landing
  • Uncooperative object grasping (space junk collection)

Credit: NASA Credit: NASA

22,000 trackable objects

slide-19
SLIDE 19

19

Further Information

  • Ubotica
  • Website
  • Article
  • Myriad 2
  • Website
  • Product Brief
  • Technical Paper
  • Radiation Testing Media
  • ESA News Brief
  • High Performance Compute Board (HPCB)
  • Cobham Gaisler Press Release
slide-20
SLIDE 20

Providing AI Solutions for Edge Based Computer Vision Applications

Ubotica Technologies Ltd.

DCU Alpha Innovation Campus Old Finglas Road Glasnevin Dublin D11 KXN4 Ireland