S´ eminaire Mod´ elisation des r´ eseaux de transport Motion planning and control techniques for driver assistance systems and autonomous vehicles Forschungszentrum J¨ ulich and Wuppertal University Antoine Tordeux a.tordeux@fz-juelich.de November 17, 2016 — Campus Descartes, Champs-sur-Marne
Motion planning and control techniques for autonomous vehicles SMRT — 17.11.16 Overview Introduction Motion planning techniques Functional architecture of automated vehicles Sensing and perception Motion planning Actuation control Control and safety Stability and homogenisation Functional safety Conclusion Slide 2 / 37
Motion planning and control techniques for autonomous vehicles SMRT — 17.11.16 Introduction Overview Introduction Motion planning techniques Functional architecture of automated vehicles Sensing and perception Motion planning Actuation control Control and safety Stability and homogenisation Functional safety Conclusion Slide 3 / 37
Motion planning and control techniques for autonomous vehicles SMRT — 17.11.16 Introduction Introduction Road vehicles are becoming increasingly automated (VDA, 2015). Advanced electric and electronic (E/E) driver assistance systems (ADAS) Connected and automated vehicles (autonomous car) Slide 4 / 37
Motion planning and control techniques for autonomous vehicles SMRT — 17.11.16 Introduction Introduction Road vehicles are becoming increasingly automated (VDA, 2015). Advanced electric and electronic (E/E) driver assistance systems (ADAS) Connected and automated vehicles (autonomous car) Motivations ◮ Safety More than 90% of road accidents attributed to driver error (with 31% involving legally intoxicated drivers, and 10% from distracted drivers) ◮ Performance Reduction of driver reaction time (short distance spacing, platooning) and optimal route choice (efficient use of the network) ◮ Mobility For children, old or disable persons with no driving licence; development of share use models and cost reduction of the road transportation ◮ Environment Efficient (smooth) driving and routing (less jam) reducing fuel consumption and pollutant emission Slide 4 / 37
Motion planning and control techniques for autonomous vehicles SMRT — 17.11.16 Introduction Automation classification Automation level classification for road vehicles (SAE, 2014) L0 Automated systems have no vehicle control, but may issue warnings No automation − − − L1 Assistance systems (ACC, lane keeping, ...) − − Assisted Under driver − Automation level − supervision − L2 Partial longitudinal and lateral controls for specific situations − Partial automation − − − L3 Longitudinal and lateral controls for specific situations − − Conditional automation − − − L4 Full automation for all situations in a defined use case Without − High automation − supervision − ← L5 Full automation for all situations of a given journey Full automation Slide 5 / 37
Motion planning and control techniques for autonomous vehicles SMRT — 17.11.16 Introduction Projections of development ◮ Manufacturers : L3 level by 2020 (Tesla, Google, Nissan, Volvo, BMW, ... ) ◮ Information services companies – Level 3 by 2020, level 4 by 2025 and level 5 by 2030 (IHS Markit) – L3, L4 and L5 Penetration rates of 100, 75 and 25% by 2030 (KPMG) – 75% of light-duty vehicle sales automated by 2035 (Navigant) ◮ Insurance institutes – All cars may be automated by 2030 (III) – Reduction from 30 to 80 % of the accidents (PWC Insurance Monitor) ◮ Research Survey during the Transportation Research Board Workshops on Road Vehicle Automation (around 500 experts, 2014) : When will automated vehicles take children to school ? → More than half expect 2030 at the very earliest; 20% said not until 2040; 10% never expect it. Slide 6 / 37
History Connectivity 1996 2002 2009 2019 2G network Bluetooth 3G network 5G network 1965 1989 2007 2020 Radio traffic Navigation system Car-To-Car Consortium HD map information 1991 2003 2015 Cell phone Mobile internet WLAN ITS G5 2002 2015 ADAS Company Lane dep. warning Traffic jam driving 1994 2005 2015 1965 ESP Parking assistant Park assist Cruise control ···− → 1987 1995 2001 2009 Braking Emergency Sign recognition Traction Levels 3, 4, 5 ? 1956 braking Power Control assistant steering 1977 2007 2015 Blind-spot ABS Highway 1998 driving ACC 2007 Lane keeping LEVELS 0 & 1 LEVEL 2 1950 1970 1990 2000 2010 2020 1952 1980 Wardrop’s Dynamic traffic assignment 2000 2014 Nonlinear stability Homogenisation Equilibria (Merchant & Nemhauser) (Komatsu, Sasa, Wilson) (Monneau, Forcadel) TA stability (Smith) STRATEGICAL Research 1995 2000 2007 OVM IDM GSOM (Lebacque) 1955 1971 ···− → Payne-Whitham LWR 1990 Optimisation 2002 Micro-Macro derivation (Papageorgiou) Safe and performant 1963 Follow-the-leader (Pipes) (Aw, Rascle) 2D models ? Linear stability (Kometani) 1988 Lane changing 2002 Multi-class LWR (Wong & Wong) 1968 Multi-ant. (Bexelus) Models 1985 1997 2004 2010 2015 ··· Google-Car ALV CYBERCARS DARPA PROUD Projects Challenges GCDC, VIAC EUREKA DEMO’97 DELPHI
Motion planning and control techniques for autonomous vehicles SMRT — 17.11.16 Motion planning techniques Overview Introduction Motion planning techniques Functional architecture of automated vehicles Sensing and perception Motion planning Actuation control Control and safety Stability and homogenisation Functional safety Conclusion Slide 8 / 37
Motion planning and control techniques for autonomous vehicles SMRT — 17.11.16 Motion planning techniques Functional architecture of automated vehicles Functional architecture of the motion planning Automated vehicles are mission-based and have a functional architecture (Behere und Torngren, 2015; Paden et al., 2016). Classical components of the autonomous driving : 1. Perception Collection, fusion and interpretation of the sensor (radar, camera) and connectivity (V2V, V2I) data → Building of a virtual world 2. Motion planning Routing choice and determination of continuous and collision-free reference trajectories → Calculation of short and safe feasible paths 3. Actuation Determination of stable commands to the vehicle to follow the reference trajectory → Steering, braking and acceleration rate controls Slide 9 / 37
Functional architecture of automated vehicles Motion planning Local Planning Reference-trajectory Continuous interpolation (Spline) Holonomic condition, Slipness Longitudinal Planning Path Actuation Perception Behavior planning Manneuver planning, Roadmap Collision avoidance technique Control planning Data collection Heuristic (NN, probabilistic) Stable reference-trajectory Radar, Laser, ultrasonic sensor Route Feedback mechanisms Camera, Infrared camera Inertial navigation system Routing Regulation Global positioning system V2V & V2I communications Shortest path problem Vehicle’s control Dijkstra’s algorithm Data Heuristic (A*, hierarchical, ... ) Steering Braking Interpretation Accelerating Data fusion (SLAM) Objects identification (Machine learning, clustering filtering, ... ) Virtual world Time-dependency
Functional architecture of automated vehicles Automatisation Motion planning Level L1 Local Planning ACC, lane keeping Reference-trajectory Continuous interpolation (Spline) Holonomic condition, Slipness Longitudinal Planning Path Actuation Perception Behavior planning Manneuver planning, Roadmap Collision avoidance technique Control planning Data collection Heuristic (NN, probabilistic) Stable reference-trajectory Radar, Laser, ultrasonic sensor Route Feedback mechanisms Camera, Infrared camera Inertial navigation system Routing Regulation Global positioning system V2V & V2I communications Shortest path problem Vehicle’s control Dijkstra’s algorithm Data Heuristic (A*, hierarchical, ... ) Steering Braking Interpretation Accelerating Data fusion (SLAM) Objects identification (Machine learning, clustering filtering, ... ) Virtual world Time-dependency
Functional architecture of automated vehicles Automatisation Motion planning Level L2 Local Planning ACC, lane keeping, Reference-trajectory Continuous interpolation (Spline) lane changing Holonomic condition, Slipness Longitudinal Planning Path Actuation Perception Behavior planning Manneuver planning, Roadmap Collision avoidance technique Control planning Data collection Heuristic (NN, probabilistic) Stable reference-trajectory Radar, Laser, ultrasonic sensor Route Feedback mechanisms Camera, Infrared camera Inertial navigation system Routing Regulation Global positioning system V2V & V2I communications Shortest path problem Vehicle’s control Dijkstra’s algorithm Data Heuristic (A*, hierarchical, ... ) Steering Braking Interpretation Accelerating Data fusion (SLAM) Objects identification (Machine learning, clustering filtering, ... ) Virtual world Time-dependency
Recommend
More recommend
