Parking Potential: Why Autonomous Parking Will Happen First

Preview:

Citation preview

#CAM2019 @LCV_Event

Parking Potential: Why Autonomous Parking

Will Happen FirstDr Brian Holt

Head of Autonomous Driving & Parking – Parkopedia

CAM Seminar Hall Sponsor

WHY AUTOMATED

VALET PARKING

Dr. Brian Holt

SECTION 01

ABOUT PARKOPEDIA

Founded in 2007, Privately Held

120 full time staff across HQ in London and offices in

Detroit, Shanghai, Moldova

Global Leader in Digital Parking Services For B2B

Global Leader in Parking Data for B2C

ABOUT PARKOPEDIA

• 11 years of parking data collection

• 60m+ parking spaces

• 710k on-street parking locations

• 305k off-street parking locations

UNIQUE GLOBAL REACH

World’s largest and most advanced parking data and services

Market leader in every single country

Launched

5Private and confidential

Auto manufacturers / OEMs Navigationproviders

Tier 1 suppliers

Powering millions of connected cars

Global Market Leader In Digital Parking

Services For Automotive

Powering cloud-based parking services in connected cars for blue-chip customers

globally

Private and confidential

Apple

*: embedded navigation services

SECTION 02

AUTOMATED DRIVING

THE IDEA IS OLD

GM Motorama Exhibit 1956!

https://www.youtube.com/watch?v=Rx6keHpeYak

PIONEERING WORK AT TUM

Ernst Dickmanns VaMoRs (1986 – 1995)

https://en.wikipedia.org/wiki/Ernst_Dickmanns

EUREKA PROMETHEUS

Program for European Traffic of Highest Efficiency and

Unprecendented Safety (1987 – 1994)

https://www.eurekanetwork.org/project/id/45

DARPA GRAND CHALLENGES

Mojave Desert + Urban (2004 – 2007)

https://en.wikipedia.org/wiki/DARPA_Grand_Challenge

GOOGLE SELF-DRIVING CAR PROJECT

Waymo (2009 – present)

https://en.wikipedia.org/wiki/Waymo

WHY IS IT SO HARD?

Complex interactions

https://www.youtube.com/watch?v=LSX3qdy0dFg

“The first 90% of the

technology took only 10%

of the time. To finish the

last 10%, however, is

requiring 10x the initial

effort.”

Sacha Arnoud, Waymo

MOTORWAY CONTROL SYSTEMS

A motorway is a controlled environment

Source: Time Magazine, Tesla Autopilot GM Super Cruise is available now

LOW SPEED AUTOMATED DRIVING

Other examples include retirement villages

Source: Voyage.auto

AUTOMATED VALET PARKING

A car park is a controlled environment

Source: Google image search

SECTION 03

AUTONOMOUS VALET

PARKING

PAIN POINT

Parking is one of the most important challenges for a traveller

• Parking pain point experienced on

12% of UK (19% in London) journeys

• 1 in 5 journeys experience difficulty

finding a parking space

Source: TSC Traveller Needs Study

SELF-DRIVING FEATURES

What do consumers want?

• Improves the parking

experience by allowing drivers

to be dropped off at a

convenient location

• Utilises parking spaces more

efficiently

• Avoids unnecessary

congestion and pollution

SELF-DRIVING FEATURES

What do consumers want?

When would you want a driver assistance feature to take over for you? When would you be willing to hand over control to the car?

FEATURE COSTS

How much cost are consumers willing to bear?

• Low speeds mean much lower risk

• A constrained environment means

reduced complexity of interactions

• The cost of the required sensor suite

and hardware platforms is lower

MODELS OF AVP

Where is the intelligence?

Target positiondetermination

Path planning

Trajectory calculation

Vehicle motion control

localization Object and Event Detection and Response

Type1 Type2Type3

Vehicle AVP local(Infrastructure)

In-vehicle sub-system main

AVP local sub-system main

Combination of the two sub-systems

SECTION 03

AVP PROJECT

AUTONOMOUS VALET PARKING PROJECT

avp-project.uk

PROJECT

SCOPE

Paragraph Title

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

• Create maps of car parks suitable for navigation and localisation at SAE 4

• Develop localisation algorithm(s) that best utilise the maps

• Demonstrate maps, localisation and navigation on a test vehicle

• Develop safety case and prepare for in-car-park trials

• Engage with stakeholders to evaluate perceptions around the technology

SAFETY CASE

Paragraph Title

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Download safety documents at http://avp-project.uk/publications

CUSTOMER

EXPERIENCE

Paragraph Title

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Download safety documents at http://avp-project.uk/publications

• What are parking pain points can be resolved by AVP?

• What are other likely benefits of AVP?

• What are the key barriers to AVP deployment and

uptake, from a social and behavioural point of view?

• What will be the likely impact of AVP, on the

environment, the economy, and the parking industry?

DEMONSTRATION

SCENARIO

Paragraph Title

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

2:

Navigate &

Park

1: Start

Parking

4: Pick

up Driver

3: Summon

Back

SAE Level 4

AUTOWARE

FOUNDATION

Paragraph Title

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

AUTOWARE

FOUNDATION

Paragraph Title

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

AUTOWARE.AUTO

ROADMAP

Paragraph Title

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

SYSTEM

ARCHITECTURE

Paragraph Title

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Sensors

Perception:

Localisation

Perception:

Detection

Decision

Motion Planning:

(Local) Planner

Mission Planning:

(Global) Planner

Motion Planning:

Follower

Safety

Stop

User

Input

Motion Planning:

Control

Landmarks

Pose, Speed

Scene data:

Point Cloud

Image RGB

Scene data:

Image RGB

Odometry:

IMU

Encoders

Location/State of:

Live obstacles/

Traffic (lights)

Order command Stop command

Navigation

command

(see Driving

task)

Lanes

(Start/Goal)

Trajectory

(section)

Speed

(linear, angular)

Steering/Throttle

Scene

understanding

Lane

structure

Traffic rules

(live+offline)

Emergency

Localisation

Perception Decision Navigation Control

Map

Map

Sensors

STREETDRONE

VEHICLE

Paragraph Title

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

WHAT ARE WE

DEMONSTRATING?

Drop-off point

Pick-up point

Parking bay

Run 1: Parking

Run 2: Summon

20-30 mAutonomous

Emergency

BrakeDrop-off point

Pick-up point

Parking bay

20-30 m

2 m

WHAT ARE WE

DEMONSTRATING?

Paragraph Title

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Paragraph text here. Paragraph text here. Paragraph text here.

Sensors

Perception:

Localisation

Perception:

Detection

Decision

Motion Planning:

(Local) Planner

Mission Planning:

(Global) Planner

Motion Planning:

Follower

Safety

Stop

User

Input

Motion Planning:

Control

Landmarks

Pose, Speed

Scene data:

Point Cloud

Image RGB

Scene data:

Image RGB

Odometry:

IMU

Encoders

Location/State of:

Live obstacles/

Traffic (lights)

Order command Stop command

Navigation

command

(see Driving

task)

Lanes

(Start/Goal)

Trajectory

(section)

Speed

(linear, angular)

Steering/Throttle

Scene

understanding

Lane

structure

Emergency

Localisation

Perception Decision Navigation Control

Map

Map

Sensors

PROJECT

STATUS

2019 2020 2021Q1 Q2 Q3 Q4 Q5 Q6 Q7 Q8 Q9 Q10

StreetDrone

Preparation

Control and

waypoint following

Create XML Maps

Customer

Experience

Safety

Navigation +

Localisation with maps

Integration + testing

Demo + finishLocalisation

2018

SUMMARY

Automated Valet Parking is coming soon!

• Low cost, low speed, low risk feature

• Customer demand is high

• 30 month £1.5M CCAV & InnovateUK funded project

• Contributing member of ISO AVPS drafting team

• Autoware Foundation premium member

• Safety case developed with Connected Places Catapult

• Customer experience research completed

• Working to bring indoor maps to market to support AVP!

Recommended