TOWARDS AUTONOMY - Home - EPSRC website

JLR-EPSRC Workshop 9th December 2014

TOWARDS AUTONOMY SMART AND CONNECTED CONTROL


Agenda

11.00 Introductions from EPSRC and Jaguar Land Rover 11.10 Programme vision and scope 12.05 Q & A session 12.15 Lunch 13.15 Call for proposals – process and timeline, collaboration with JLR 13.55 Q & A session 14.05 Exploration and networking around themes 15.05 Summary and next steps 15.15 Informal networking 16.00 Event close


Introduction from EPSRC

Kedar Pandya – Head of Engineering, EPSRC


Introduction from Jaguar Land Rover

Tony Harper – Head of Research, Jaguar Land Rover


Jaguar Land Rover

• Largest UK car manufacturer with two iconic British brands - Jaguar and Land Rover • Vehicles engineered and designed in UK – JLR Research Team based here at Warwick Uni • Biggest UK investor in R&D in manufacturing sector and in top global 100 for R&D spend


TASCC Programme and Jaguar Land Rover

Aim: to expand research capability in the area of smart and connected control around the central challenge of moving towards a fully autonomous car

• Increasing digital capability of vehicles is central to future JLR product development and brand leadership

Opportunity

• Integrated approach is critical with system flexibility, communication between many components and new ground-up architecture.

Challenge


Programme Scope and Vision

Chris Holmes – Senior Manager, Smart and Connected Car, JLR Alex Mouzakitis – Senior Manager, Electrical, Electronics and Software Engineering, JLR


Experiencing the Future of Intelligent Transportation

http://www.intel.com/content/www/us/en/automotive/experiencing-future-intelligent-transportation-video.html












Autonomous Features of a Commercially-Viable Vehicle

Night and day autonomous driving on motorways, dual-carriageways and A-roads

Co-operative driving on motorways

In-traffic ‘stop-start’ autonomous driving

Auto ‘valet’ parking

Navigation-based autonomous traffic avoidance

Off-road driver assistance

Intelligent, adaptive vehicle with personalised interior


Relevance to Jaguar and Land Rover Brands

Intuitive technologies engage the

senses

Traffic avoidance

and reduced congestion

Adaptive dynamics enhance driving

experience

Mood-mapped adaptive interior and support in all

conditions

Increased journey productivity

Total digital integration with home, office and mobile devices

Intelligent personalised

interior makes driving a pleasure

Increased fuel

efficiency

Off-road assistance


TASCC Programme Themes

Human interaction

Data fusion & analytics

Distributed systems & control architecture

Verification, robustness & safety

Legislative framework

CORE THEMES

ENABLING THEMES

Autonomous vehicle control

Off-board data & infrastructure

Autonomous intelligent features

Sensing

Personalisation and user experience in intelligent vehicles

Autonomous driving control

Enabling techs, processes and legal framework


Legislative Framework – Starting Point

Where we are now: • Current production systems are

partially automated • Cruise & Parking features require driver

supervision • Legislation is driving automated safety

features - (Discovery Sport achieved EuroNCAP 5-Star rating with AEB)

Future directions: • Progression to higher levels of

autonomy • There will be a lower level of

supervision from the driver • There will be limitations on autonomy

unless the law is changed

£$

Worldwide 1.24M deaths per year


Legislative Framework – the Future

Example research challenges: • Legislative changes & accommodation

of global legislative differences • Product liability - how does the

industry protect itself? E.g. U.S. punitive damages

• International or national standards (ISO, CEN, SAE etc.) to be established

• Justification of ethics employed • Data protection when intelligent

features & analytics are introduced)


Autonomous Vehicle Control – Starting Point

Where we are now: • Control is achieved by taking sensor

data, processing it and actuating brakes, powertrain and steering

• Features operate as an orphan vehicle covering safety, parking and cruise

Future directions: • Predictive capability of other vehicle &

infrastructure data • Multiple-feature interaction for

consistent user-experience • Highly-automated discrete functionality • Fully autonomous vehicle connected to

various modes of transport

1

2

3


Autonomous Vehicle Control – the Future

Example research challenges: • Functionality must always be safe in any

environment • Ability to operate anytime & anywhere (weather,

territory & on/off-road) • Take account of vehicles with very different levels

of autonomy, connection and data sharing capability

• How can an autonomous vehicle manage complex junctions, and how does it cope with the fact that traffic protocol varies across the globe?

• How can the vehicle develop a predictive capability based on user patterns and real-time data?

• How does the vehicle achieve self-learning, dynamic control based on a holistic, system-level understanding?


Sensing – Starting Point

Where we are now: • Radars front, rear and corner • Cameras front, rear and side • Ultrasonics front & rear Future directions: • More sensors & connected input

such as FIR, V2X & eHorizon • Managing conflicts in sensed

information • Smarter algorithms & interoperability


Sensing – the Future

Example research challenges: • Prediction and anticipation e.g. seeing round bends pedestrians between parked cars VRU next movement

• Robust sensor data fusion & which sensors to believe when they are giving conflicting information?

• All-weather and lighting capability • Longer/wider range sensors &

integration to V2X • Optimisation – reduced number of

sensors & required data stream • Robust driver state and health


Land Rover’s Self-Learning Intelligent Vehicle

https://www.youtube.com/watch?v=F923EuB06CI

https://www.youtube.com/watch?v=F923EuB06CI


Data Fusion & Analytics – Starting Point

Where we are now:

• Until recently, virtually all data on the vehicle is not stored or transmitted (limited data is downloaded during a vehicle service)

• Data is usually therefore difficult to access and sparse

• Conventional analytic techniques are used to analyse data (e.g. fault causes)

• However, vehicles are increasingly connected to the cloud, which allows transfer of information (e.g. diagnostic data) without waiting for a service

Future directions:

• Access to quicker and richer data sources via vehicle telematics connections gives lots of opportunities

• Quicker identification and prediction of vehicle faults

• Optimisation of vehicle component and system design to match real-life customer usage and environmental condition (opportunities for weight/costs/C02 reduction)


Data Fusion & Analytics – the Future

Example research challenges: • Developing algorithms/techniques to

predict vehicle faults from data on vehicle usage, technical data and environmental conditions

• Prediction models that adapt to local market usage, updates to the vehicle, differences between vehicles

• Aggregating data from multiple vehicles/markets/driver types in order to find patterns across these parameters

• Communicating and presenting the results to both technical and non-technical users


Off-Board Data Sharing & Infrastructure – Starting Point

Where we are now: • Vehicles are cloud connected • Reliability of connectivity restricts

features • Drivers and passengers want to

access the connected services they use

Future directions: • 5G impact on vehicle and connected

landscape • How will the vehicle integrate with

Internet of Things? • Requirements on the Infotainment in

an autonomous vehicle


Off-Board Data Sharing & Infrastructure – the Future

Example research challenges: • What vehicle functions can be cloud

based? What is the fall back if connectivity is lost?

• How will the vehicle be integrated with smart cities?

• How will the user’s digital ecosystem be integrated into the vehicle experience?

• How will the digital media experience in the vehicle be supported?


Distributed Systems & Control Architecture – Starting Point Where we are now: • Vehicles are complex distributed computer

systems - managing compellability is a major issue

• Limited connectivity in and out of vehicle. • A ridged closely coupled architecture validated

as a system Future directions: • Architecture consolidation, a smaller number

of powerful engine control units • Migration towards a service orientated

architecture • Connectivity extends beyond infotainment

domain


Distributed Systems & Control Architecture – the Future

Example research challenges: • What vehicle functions can be cloud

based? What is the fall back if connectivity is lost?

• How do we run software components with different integrity levels on the same hardware?

• How do we manage the additional threats created by greater connectivity?

• What role will consumer electronics play in the vehicle of the future?

• Functional growth • Utilising printed electronics


Human Interaction – Starting Point

Where we are now:

• Vehicles are driven manually, driver is responsible for the safe control of the vehicle

• Driver needs to be aware of hazards, managing the demand of the environment

• Increasing demands of the wider environment including the connected life of the customer

• Some basic autonomy for driving (adaptive cruise control, lane keep, queue assistance, emergency stop), interfaces considered as discrete individual elements

Future directions:

• Increasing levels of autonomy of the driving task changing the demands of the environment

• Increased motivation from non-driving related activities

• Enhanced interface methodologies enabling smart feedback of threats and hazards


Human Interaction – the Future

Example research challenges: • Managing variable levels of driver-

vehicle control and defining the handover points considering driver skill, awareness and state

• What does the information content look like between autonomous and manually driven vehicles?

• How will the vehicle interior in autonomous vehicles change how users interact in our vehicles?


Autonomous Intelligent Features – Starting Point

Where we are now: • Comfort and convenience features: auto

lights, auto wipers • Advanced Driver Assistance (ADAS) features:

automatic cruise control, auto parallel park, automatic emergency braking

Future directions: • The Self-Learning Car Project • The car knows and responds to: who you

are, what you want and the environment around you

• Reduces the amount of driver interaction with vehicle required

• Applies to areas such as: climate, audio, phone


Autonomous Intelligent Features – the Future

Example research challenges: • Driver and passenger identification • Developing machine learning

algorithms to recognise driver routine

• Developing algorithms that are robust to changes and exceptions to customer routine

• Making inferences based on new sources of information and sensors

• Reliability of connectivity restricts features


Where we are now: • Prototype vehicle-based testing for

embedded software • Paper-based robustness system

assessment • Expensive vehicle tests to meet

safety regulations Future directions: • Reduce dependency on physical

prototypes • Methods, tools and techniques for

offline software development • Data analysis and system

modelling

Verification, Robustness & Safety – Starting Point


Verification, Robustness & Safety – the Future

Example research challenges: • Modelling of vehicle external

environment including connectivity • Data analysis and trust (human,

system) • Abstract modelling of digital eco-

systems


TASCC Programme Themes

Human interaction

Data fusion & analytics

Distributed systems & control architecture

Verification, robustness & safety

Legislative framework

CORE THEMES

ENABLING THEMES

Autonomous vehicle control

Off-board data & infrastructure

Autonomous intelligent features

Sensing

Personalisation and user experience in intelligent vehicles

Autonomous driving control

Enabling techs, processes and legal framework


Any Questions?


LUNCH

Please be back for 1.15pm


Call for Proposals Process and

Timeline Susan Soulsby – Portfolio Manager, EPSRC


Your Research Application

1. The process

2. How to apply

3. Funding available – what you can apply for


The Process

Outline Deadline

16:00 29 January 2015

Expert Outline Panel

9 March

Full Proposal Deadline

16:00 11 May 2015

Interview Panel 27-28 July 2015

Workshop Workshop


How to Apply - Writing Your Outline Application

Your outline proposal should consist of the Outline application form and Case for Support document.

• All proposals including multi-institutional bids must be submitted on one common Je-S proposal form by the lead organisation.

Outline Application Form - the summary section should contain an overview of the research proposed.

• All applicants must articulate how the proposed research addresses the scope of the call

• The outline will need to give an indication of the total research grant funds sought should a full proposal be invited. Costs for studentships should not be included on the outline application form.

Outline Case for Support – no more than four pages of A4, addressing the key assessment criteria and giving an indication of the resources being requested and any project partners.

• Applicants should give an overview of the project, clearly articulating the novel research being tackled, including a description of the approach and methodology being used and the expertise and experience of the team involved.

• The minimum acceptable font is size 11, and the minimum margin in all directions is 2cm.


Assessment Criteria (for both Outline and Full Proposals)

• Quality – the degree of excellence of the proposal making reference to: the novelty, relationship to the context, timeliness, ambition and adventure, and transformative aspects identified, appropriateness of the proposed methodology

• Applicant –the applicants’ ability to deliver the proposed project making reference to: Appropriateness of the track record of the applicant(s), and Balance of skills of the project team, including academic partners.

• Importance – the national importance over a 10 to 50 year time frame in relation to other research in the area and how the proposal demonstrates how the research would underpin or contribute to other research areas, societal challenges (including EPSRC challenge themes), and the success of the UK economy and emerging industry

• Fit to call – relevance of research proposed to call remit


Additional Two Assessment Criteria for Full Proposals

• Impact – How complete and realistic are the impacts identified for this work. The effectiveness of the activities identified to help realise these impacts, including the resources requested for this purpose. The relevance and appropriateness of any beneficiaries or collaborators

• Resources and management – The effectiveness of the proposed planning and management and on whether the requested resources are appropriate and have been fully justified. Please comment explicitly on the viability of the arrangements described to access equipment needed for this project, and particularly on any university or third party contribution.


Funding Available – What You Can Apply For

• EPSRC and JLR have allocated a budget of up to £10 million to support research arising from this call. It is anticipated that up to four to six projects will be sponsored and that grants will be up to five years in duration.

• To avoid delay to the start of the programme, all grants will be required to start by end of December 2015.


Funding Available – Eligible Costs

• Standard rules for EPSRC funding and eligible costs apply. Travel , Consumables, Specialist publications (not expected in institutional libraries) , Consultancy fees, Fieldwork fees/subjects/informants, Computing - including recurrent costs of computing dedicated to each project only, e.g. software licences, glass house consumables, Recruitment and advertising costs for staff directly employed on the project, Purchase/hire/running costs of vehicles if necessary for the project

• The EPSRC and JLR will not fund maintenance costs for equipment that was already the property of the research organisation when the application was submitted.


Equipment

• If equipment is needed applicants must follow EPSRC’s rules for requesting equipment over £10,000 in value.

• Individual items of equipment up to the current OJEC (Official Journal of the European Communities) procurement threshold can be included on research proposals submitted through this call, but research organisations will be expected to make a contribution to the cost.

• All requests for single items of equipment above the current OJEC threshold will need to go through a separate process which will assess the strategic need for the equipment and how to ensure maximum usage. These proposals will be assessed through the separate Strategic Equipment peer review process.

The current Official OJEU threshold is: £111,676 (excluding value added tax (VAT))

£134,011 (including VAT)


Equipment

Equipment below £10,000 (incl. VAT) • Individual items of equipment below £10k should be included in proposals for

individual research projects and will be paid at 80% FEC.

Equipment between £10,000 and the current OJEU threshold • Individual items of equipment between £10,000 and the current OJEU threshold

should be included on proposals for individual research projects. Letter of Support from the research organisation detailing the proposed contribution to the cost of the equipment. • This includes computers, laboratory/workshop equipment, major equipment

spares and software, installation costs and costs of major essential modifications necessary to house equipment (for example, clean rooms or extension of air conditioning).

• For equipment between £25K and OJEU we require 3 quotations. • These can be obtained verbally but they should be detailed in the proposal.

• Three written quotations are required for single items of equipment costing more than the current OJEU limit and must accompany the proposal.

The current Official OJEU threshold is: £111,676 (excluding value added tax (VAT))

£134,011 (including VAT)


Equipment

Instrument development Items of equipment for instrument development will not need to be co-funded by another partner or go through the strategic equipment process. Equipment for instrument development should be integral to a research proposal. For more information on equipment funding, please see: http://www.epsrc.ac.uk/research/ourportfolio/themes/researchinfrastructure/subthemes/equipment/ The current OJEC threshold can be found at: http://www.epsrc.ac.uk/research/facilities/equipment/

http://www.epsrc.ac.uk/research/ourportfolio/themes/researchinfrastructure/subthemes/equipment/

http://www.epsrc.ac.uk/research/ourportfolio/themes/researchinfrastructure/subthemes/equipment/

http://www.epsrc.ac.uk/research/facilities/equipment/


Facilities

• Investigators seeking access to major national and international facilities should apply to the relevant provider. It is the responsibility of the investigator to obtain any access needed for the research project. Planned usage should be identified on the relevant section of the proposal form.

• The EPSRC may provide support for access to other facilities at universities and elsewhere. Investigators seeking the use of such services are advised to contact the appropriate provider to confirm eligibility requirements and costs prior to submitting a proposal to the EPSRC.


Visiting Researchers

• Support may be requested for visits by scientists and engineers of acknowledged standing from within the UK or abroad to the investigator’s organisation.

• Funding is limited to 12 months per individual. • The research organisation should include Estates Costs and Indirect

Costs for any Visiting Researcher regardless of whether the support being requested includes a salary contribution or is only Travel and Subsistence.


Studentships

• The majority of the £10 million for this call will be on research grant funding which will be split between EPSRC and JLR.

• There will be specific funding from JLR for PhD/EngD students. • Applicants will be able to apply for one studentship for

approximately each £600k of research grant funding. • The number of students that applicants can apply for to be

associated with their research grant will be confirmed when the full proposals are invited.

• Do not include the costs for students in your application but explain how they will be involved within the case for support.


The Research (National Importance)

Your proposed research must fit within the call’s research scope and the majority of activity must be within EPSRC’s remit. All applications to this call must demonstrate broad support of EPSRC’s Delivery Plan objectives and articulate the contribution the award will make to strategies, priorities and national importance as detailed on the EPSRC website. Published EPSRC strategic statements should be considered. Relevant strategies include: • Towards an Intelligent Information Infrastructure

http://www.epsrc.ac.uk/research/ourportfolio/themes/ict/introduction/ti3/ • Many-core Architectures and Concurrency in Distributed and Embedded Systems

http://www.epsrc.ac.uk/research/ourportfolio/themes/ict/introduction/manycore/ • Working Together

http://www.epsrc.ac.uk/research/ourportfolio/themes/ict/introduction/workingtogether/

• For more information about EPSRC’s portfolio and specific Research Areas strategies, see our website: http://www.epsrc.ac.uk/research/ourportfolio/

http://www.epsrc.ac.uk/research/ourportfolio/themes/ict/introduction/ti3/

http://www.epsrc.ac.uk/research/ourportfolio/themes/ict/introduction/manycore/



http://www.epsrc.ac.uk/research/ourportfolio/


Framework for Responsible Innovation

As a public funder of research, we have a responsibility to ensure that our activities and the research we fund, are aligned with the principles of Responsible Innovation, creating value for society in an ethical and responsible way. A Responsible Innovation approach should be one that continuously seeks to: • Anticipate – describing and analysing the impacts, intended or otherwise, (for example

economic, social, environmental) that might arise. This does not seek to predict but rather to support an exploration of possible impacts and implications that may otherwise remain uncovered and little discussed.

• Reflect – reflecting on the purposes of, motivations for and potential implications of the research, and the associated uncertainties, areas of ignorance, assumptions, framings, questions, dilemmas and social transformations these may bring.

• Engage – opening up such visions, impacts and questioning to broader deliberation, dialogue, engagement and debate in an inclusive way.

• Act – using these processes to influence the direction and trajectory of the research and innovation process itself.

More details here http://www.epsrc.ac.uk/research/framework/

http://www.epsrc.ac.uk/research/framework/


Help!

In the first instance queries should be directed to [email protected] EPSRC • Susan Soulsby ([email protected] - 01793 44 4248) • Alex Broomsgrove ([email protected] - 01793 44 4223) • Diane Howard ([email protected] - 01793 44 4193)

Jaguar Land Rover • For questions relating to collaboration agreements and working with JLR in general, please

contact Mark Niziolomski, Research and Innovation Manager ([email protected]).

Je-S • Your research administration should be able to offer advice about costing your proposal

and the Je-S system. • If there are any queries related to Je-S, please contact the Je-S helpdesk:

[email protected] or 01793 444164. • Please allow enough time before the closing date for your organisation’s submission

process.

mailto:[email protected]


Collaboration with Jaguar Land Rover

Mark Niziolomski – Research & Innovation Manager, JLR


Non-Disclosure Agreements

• Non-disclosure agreements not required for the first stage of call (outline proposals)

• For next stage of call (development and submission of full proposals) • To help in facilitating discussions on research scope, institutional

non-disclosure agreement with JLR required if applicant accepts invitation to submit full proposal

• Non-disclosure agreement will be specific to call scope and time bound


JLR Collaboration Agreement

• Collaboration agreement with JLR required for funded projects – based on JLR standard template for research collaboration

• Standard template will be shared in March when full proposals are invited

• Collaboration agreements with any other partners also required to be in place before grant starts


Management of Projects

• JLR anticipates working closely with the funded work streams • Technical lead from JLR will be allocated to each project to work with the

grant principal investigator to deliver the research • Projects will be managed through JLR's TCDS or milestone processes • Processes will be mandated to reduce risk of breach of confidential

information, for example: • Information management protocol • Publication process

• TASCC programme steering group will meet quarterly – consists of JLR, EPSRC and grant principal investigators

• Applicants can request any admin support needed through the grant proposal


CA

NDA

Timeline for Legal Contracting

Workshop 1 (December

2014)

Workshop 2 (mid-late March

2015)

Workshop 2 onwards

conducted under NDA

Notification of

expectations for legal

contracting

NDA issued to short-listed

applicants for signature

CA issued for signature

Programme runs under

CA

Full proposals

invited (mid-March

2015)

Outline proposal

submission

Submission of full

proposals

Final selection

completed (end-July 2015)

Programme Start

(September 2015)

CA process engaged once participating

universities selected


Any Questions?


Exploration and Networking Around

Themes


Exploration and Networking – Purpose

• Purpose: to explore research challenges and enable informal discussions and networking

• 9 themes – posters around room Break-out groups:

• Cluster by theme of most interest: 30 minutes • Move to another theme: 30 minutes


Exploration and Networking – What to Do

In break-out groups: 1. Introductions – who you are and your areas of interest

2. Research challenges – any more to add?

3. How to address research challenges? Possible research projects?


JLR Technical Team here at the Event

• Chris Holmes – Senior Manager – Smart and Connected Car • Alex Mouzakitis – Senior Manager - Electrical, Electronics and Software Engineering • Lee Skyrpchuk - Human Machine Interface Technical Specialist • Tony Davis – Advanced Electrical Manager • Paul Sanderson – Software Engineer • Mark Cund – System Engineer • Damian Ward - Research delivery manager - Core Infotainment and Application HMI • Thomas Popham – Research Manager - Self-Learning Car & Data fusion • Carl Pickering – Head of Electrical/Electronic Research • David Sanchez – ADAS Technical Specialist • Frank McCullough - Electrical Research Tech Delivery Manager - Infotainment and Telematics • Nigel Clarke – Manager, Advanced Chassis Research • Phil Barber - Advanced Chassis & Vehicle Dynamics Technology Specialist • Paul Widdowson – Project Engineer - Vehicle Capability - Remote Sensing • Dave Willey


Summary and

Next Steps


Next Steps Timeline

Closing date for outline proposals: 29 January 2015

Full proposals invited: mid-March

Workshop 2: mid-late March


Contacts and further information

• Call for proposals: http://www.epsrc.ac.uk/funding/calls/tascc/ • Slides from this workshop will be published on EPSRC website and

linked to from the call

• For any questions, please contact [email protected]

http://www.epsrc.ac.uk/funding/calls/tascc/

mailto:[email protected]

Thank you


TOWARDS AUTONOMY - Home - EPSRC website

Documents

Transcript of TOWARDS AUTONOMY - Home - EPSRC website