safety assurance kudos for reliable autonomous vehicles ......safety assurance kudos for reliable...

1
Safety Assurance Kudos for Reliable Autonomous vehicles: SAKURA Project Socially acceptable and technically sound safety assurance methodologies are needed to safely introduce Automated Driving systems into the market. The SAKURA project is a large scale coordinated initiative funded by the Japanese Ministry of Economy, Trade and Industry (METI) that aims at harmonizing data collection, developing research methodologies and coordinating standardization activities through joint efforts by vehicle manufacturers and traffic safety research institutions. Within this project, a comprehensive safety assurance process has been developed and a number of activities are being deployed including real-traffic monitoring data collection, development of traffic scenarios for safety evaluation and definition of safety criteria. The safety assurance process will be applied to guide the development of the systems towards a safer Automated Driving society. Summary Trac Trajectory Data Scenario in AD Safety Validaon Driving Data Collecon Safety Criteria for AD Analyzing Parameter Human Driving Data Safety Criteria for AD Comparison with human driver capabilty Evaluaon of human driver capability of cut-in scenario by Driving Simulator Comparison of safety between human driver and Autonomous Emergency Braking System Relave Velocity: 30[km/h] Cut-in Timing : Three Condions Lateral Distance: 3.5 [m] Cut-in me : 3.4 [sec] Driving Data Collecon Data Collecng Vehicle Collect driving data of 360 degrees around ego-vehicle Camera LiDAR System equipment Fixed Locaon Camera Road users are detected Trajectory extracon of vehicles Camera 1,2 Camera 3,4 Recoded Distance (350m) y-axis x-axis Ego-Vehicle Target vehicle 1 trajectory Target vehicle 2 trajectory Target vehicle trajectory Ego-Vehicle Trajectory extracon of surrounding vehicles Bule Line: Reference Trajectory Red Line: Measurement Trajectory x-coordinate [m] y- ] m [ e t a n i d r o o c Blue Line: Scenario in AD Safety Validation Traffic Trajectory Data Classificaon For Example: Cut-in Parameter Distribuon For Example: Cut-in Scene Deceleraon [G] Lateral Distance [m] Longitudinal Distance [m] Target Vehicle Lateral Velocity [m/s] Ego-Vehicle Velocity [m/s] Target-Vehicle Velocity [m/s] For Example: Cut-in Concrete Scenario (a) (b) 1.00 (c) 2.00 (d) (e) (f) Initial State (0.00 sec) In 1.00 sec In 2.00 sec In AEBS Trigger ON (In 2.49 sec) Brake Start (In 2.99 sec) Collision (In 3.12 sec) Target Vehicle Ego Vehicle Longitudiual Distance Lateral Distance Lateral Velocity Deceleration Target Vehicle Velocity Ego Vehicle Velocity

Upload: others

Post on 28-Jan-2021

30 views

Category:

Documents


0 download

TRANSCRIPT

The SAKURA project is a large scale coordinated initiative funded by the Japanese Ministry of Economy, Trade and Industry (METI) that aims at harmonizing data collection, developing research methodologies and coordinating standardization activities through joint efforts by vehicle manufacturers and traffic safety research institutions.
Within this project, a comprehensive safety assurance process has been developed and a number of activities are being deployed including real-traffic monitoring data collection, development of traffic scenarios for safety evaluation and definition of safety criteria.
The safety assurance process will be applied to guide the development of the systems towards a safer Automated Driving society.
Summary
Driving Data Collection
Human Driving Data
Safety Criteria for AD Comparison with human driver capabitilty Evaluation of human driver capability of cut-in
scenario by Driving Simulator Comparison of safety between human driver
and Autonomous Emergency Braking System
• Relative Velocity: 30[km/h] • Cut-in Timing : Three Conditions • Lateral Distance: 3.5 [m] • Cut-in time : 3.4 [sec]
Driving Data Collection Data Collecting Vehicle Collect driving data of
360 degrees around ego-vehicle Camera LiDAR
System equipment
Fixed Location Camera Road users are detected Trajectory extraction of vehicles



Bule Line: Reference Trajectory Red Line: Measurement Trajectory
x-coordinate [m]
Traffic Trajectory
For Example: Cut-in Scene
Target Vehicle Lateral Velocity [m/s]
Ego-Vehicle Velocity [m/s] Target-Vehicle Velocity [m/s]
For Example: Cut-in Concrete Scenario
(a) 0.00 (b) 1.00 (c) 2.00
(d)
2.49
(e)
2.99
(f)
3.12
Initial State (0.00 sec) In 1.00 sec In 2.00 sec
In AEBS Trigger ON (In 2.49 sec)
Brake Start (In 2.99 sec)
Collision (In 3.12 sec)