11/9/2015

1

National Highway Traffic Safety Administration

NHTSA’s Connected and Automated Vehicle Research

Cem Hatipoglu, PhD Division Chief, Electronic Systems Safety Research

1 1

Safer Drivers. Safer Cars. Safer Roads. 2

The Connected Vehicle Program

Vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) wireless communications for:

• Crash mitigation

• Improved mobility

• Environmental sustainability

V2V provides rich set of data for automated functions

11/9/2015

2

Safer Drivers. Safer Cars. Safer Roads. 3

Motor Vehicle Safety Challenge

• 32,719 highway fatalities in 2013 • 5.67 million reported crashes in 2013 • Leading cause of death for ages 4, 11-27

• Vehicle-to-vehicle communications technology can address a large majority of these crashes. Key types of crashes address by V2V include:

Rear-end and head-on collisions

Lane change related (blind spot warning)

Intersection related

Turning across path (left hand turns)

Safer Drivers. Safer Cars. Safer Roads. 4

NHTSA Agency Decision on Light Vehicle V2V

"Vehicle-to-vehicle technology represents the next generation of auto safety improvements …" U.S. Transportation Secretary Anthony Foxx.

February, 2014

U.S. Department of Transportation Announces Decision to Move Forward with Vehicle-to-Vehicle Communication Technology for Light Vehicles

August, 2014 : NHTSA releases ANPRM and “Readiness Report” on V2V technology

May, 2015: “The Department wants to speed the nation toward an era when vehicle safety isn’t just about surviving crashes; it’s about avoiding them;”

“Connected, automated vehicles that can sense the environment around them and communicate with other vehicles and with infrastructure have the potential to revolutionize road safety and save thousands of lives.”

11/9/2015

3

Safer Drivers. Safer Cars. Safer Roads. 5

• Human drivers: – Over 90% of police reported crashes involve some type of driver error.

[http://www-nrd.nhtsa.dot.gov/pubs/812115.pdf]

• Safety benefits and potential: – Data indicates there are safety benefits for driver assistance systems,

i.e. “smart” technologies;

– NHTSA is researching to quantify the potential safety impacts for concept automation functions.

Safety Enhancement Opportunities

Safer Drivers. Safer Cars. Safer Roads. 6

Automated Vehicle Levels

Level 0 No Automation

Level 1 Function- Specific Automation

Level 2 Combined Function Automation

Level 3 Limited Self-Driving

Level 4 Full Self-Driving Automation

No steering or braking/ throttle control e.g. crash warning systems

Braking/Throttle or Steering control, but not in combination e.g. automatic braking systems

• Integration of braking, throttle, and steering control • Driver available at all times to retake control

• Integration of braking, throttle, and steering control • Driver expected for occasional control • Driver can cede full monitoring and control authority

• Integration of braking, throttle and steering control • Driver NOT expected for control • Safety of operation is solely handled by the vehicle

• A Research Framework!

11/9/2015

4

Safer Drivers. Safer Cars. Safer Roads. 7

Automation Focus: Safety First

(Automated) Vehicle Safety

How does the automated system

improve Safety?

Target crashes it can

address Effectiveness

Is the automated system designed

Safely?

Requirements are sound and safe

Designed for Functional

safety

Designed for Cybersecurity

Designed for Human Factors

Research on processes, methods, principles, best practices related to artificial intelligence, cybersecurity, functional safety,

software development requirements, performance metrics, objective tests, simulations, validation, verification; sensor,

actuator, processing capabilities and limitations, etc.

Research on statistical assessment of concept function operations with respect to crash

databases; simulations, field operational tests, design of experiments to assess effectiveness

Safer Drivers. Safer Cars. Safer Roads. 8

Need to Inform/Guide Key Stakeholders (May 2013 Release)

• Described 3 major innovation areas

– Onboard systems (radar, camera, etc), V2V, Self Driving

• Outlined NHTSA Research Activities

• Guidance to States

– Testing, Licensing, etc

– CA, NV, FL, MI, DC

Automated Vehicle Policy Statement (May ‘13)

http://www.nhtsa.gov/

11/9/2015

5

Safer Drivers. Safer Cars. Safer Roads. 9

NHTSA Letter to California (Feb ‘15)

*White House memorandum on “Principles for Regulation and Oversight of Emerging Technologies” (2011)

Inform CA’s rulemaking activities of NHTSA Research in automation • Encouraged by the potential for

significant safety benefits at all levels.

• Regulation and oversight must fulfill legitimate objectives while promoting innovation and encouraging technological progress and trade*.

• There are issues that need resolution to continue supporting the innovation that is happening

• Attached a list of (10) current research questions

http://www.nhtsa.gov/Research/Crash+Avoidance/Automated+Vehicles

Safer Drivers. Safer Cars. Safer Roads. 10

Research and Rulemaking Priorities • V2V

– Light Vehicle Rulemaking (2016)

– Heavy Vehicle Decision (2015)

• Automation – Safety Benefits Potential (2015)

– Detailed Roadmap (2016)

• Electronics Reliability – MAP-21 Report on Electronics (2015)

– Agency Decision on Electronics Requirements (2016)

• Automotive Cybersecurity – Agency Decision on Cybersecurity

Requirements (2016)

NHTSA’s new Priority Plan (July ‘15)

http://www.nhtsa.gov/staticfiles/nvs/pdf/NVS_priority-plan-June2015_final.pdf

11/9/2015

6

Safer Drivers. Safer Cars. Safer Roads. 11

Key Areas of Automation Research

Human Factors Research

• Human factors evaluation of Level 2 and Level 3 automated driving concepts

• Initial human factors design principles for L2/L3

Electronic Control Systems Safety (including Cybersecurity)

• Functional safety of safety-critical automotive systems and extensions to L2-L4

• Cybersecurity threats, vulnerabilities, countermeasures assessment

System Performance Requirements

• System performance requirements framework

• Objective test procedures

Benefits Assessment

• Target crash population estimation for automated vehicles L2-L4

• Multi-modal benefits framework development

Testing and Evaluation

• Controlled test track studies

• Field operational tests (e.g. Level 2 Naturalistic Study)

Safer Drivers. Safer Cars. Safer Roads. 12

• 2015/Early 2016 Targets

– Human Factors Evaluation of L2/L3 Automated Vehicles (VTTI) Final Report on the three experiments conducted with concept L2/L3 vehicles investigating how the driver, as an intermittent operator, transitions between automated and non-automated vehicle operation, and how this interaction is affected by the human-machine interface (HMI).

– Target Crash Populations for Concept Automated Vehicle functions (Volpe) This study estimates the residual crashes AV concepts may have the opportunity to address with respect to lower levels of automated functions with overlapping target crashes.

– Automated Vehicle Research for Enhanced Safety (CAMP) Final report on an objective level classification methodology for concept automated vehicle functions and development of high level safety principles by levels

– Human Factors Design Assistance for L2/L3 Automated Driving Concepts Final report with particular guidance to developing DVI for L2/L3 concepts

NHTSA Research Publications

11/9/2015

7

Safer Drivers. Safer Cars. Safer Roads. 13

• Still much room to improve

• Need realistic safety impact metrics to guide priorities

• “Safety enhancement” versus “Safety preservation”

Focus on Safety is essential

• Human factors Principles around control handoff; Driver engagement in the driving task; potential misuse, abuse, unreasonable risk taking

• System requirements; functional safety requirements; impacts of levels

• Artificial Intelligence complexity and sufficiency

• Objective test procedures; Test domain for reasonable assurance

• Cybersecurity needs; Software safety assurance needs

Various key Challenges remain

• Automated Vehicles; Automotive Cybersecurity; Electronics Reliability

• Various research results targeted for publication in 2015-2016 timeframe.

Preliminary research results incoming

• With the intent to identify what existing rules may have implications over various levels of automation

Reviewing federal regulations

Summary

Safer Drivers. Safer Cars. Safer Roads.

Cem Hatipoglu, Ph.D. cem.hatipoglu@dot.gov

National Highway Traffic Safety Administration

www.nhtsa.gov

Contact Information:

14