Efficient Roadway Modeling and Behavior Control for Real-time ...

Efficient Roadway Modeling and Behavior Control for Real-time ...

Steering Behaviors for Autonomous Vehicles in Virtual Evironments Hongling Wang Joseph K. Kearney James Cremer Department Of Computer Science University of Iowa Peter Willemsen School of Computing University of Utah Focus

Control of Autonomous Vehicles in VE Ambient traffic Principal roles in scenarios Importance of Road Representation Frame of reference Natural coordinate system Intersection and Lane Changing Behaviors Complex interactions among vehicles Limits of independent control

Motivation VE as Laboratories for Studying Human Behavior Developmental differences in road crossing The influence of disease, drugs, and disabilities Design of in-vehicle technology Cell phones, navigation aids, collision warning Bicycle Simulator Video Gap Acceptance in the Hank Bicycle Simulator

Related Work Flocking Complex group behavior from simple rule-based behaviors (Reynolds) Hierarchical Distributed Contol Independent, goal-oriented sub-behaviors (Badler et al.; Blumberg and Galyean; Cremer, Kearney, and Papelis) Driving Simulation (Donikian; Lemessi)

ALV (Coulter, Sukthankar; Wit, Crane, and Armstrong) Human Driving Behavior (Ahmed; Boer, Kuge, and Yamamura; Fang, Pham, and Kobayashi; Salvucci and Liu) Roadway Modeling Roads as Ribbons Oriented Surface Smooth Strips Twist and turn in space Central Axis Arc-length parameterized curve

Twist Angle Linked through Intersections Ribbon Ribbon coordinate system Distance, Offset, and loft (D,O,L) Egocentric frame of reference Efficient Mapping (D,O,L) (X,Y,Z)

IntersectionsWhere Roads Join Shared regions Non-oriented Corridors connect incoming and outgoing lanes Single lane ribbons Annotated with right-of-way rules Ribbon to Ribbon Transitions Problem: Tangle of Ribbons Bookkeeping Tedious and Error Prone Possible switch in orientation Possible shift in alignment

Solution: Paths Composite ribbons Path One-lane Overlay Removes transitions between ribbons Immediate Plan of Action - Highly dynamic - Natural frame of reference

Distributed Control Multiple, Independent Controllers Each responsible for some aspect of behavior e.g. Cruising, Following Compete for control Control Parameters Acceleration Steering Angle

Road Tracking Non-holonomic constraint Rolling wheels Move on a circle Pursuit point control Steer to a point on the path Look-ahead distance Controlling Speed Cruising: Proportion Control c

a K p (v d v ) c Following: Proportional Derivative Controller a f f K p

( s ) f Kv ( v ) Intersection Behavior Gates access to shared regions Decision:

Go / No Go Action: stop at stopline Gap Acceptance Based on Interval Analysis Right-of-way rules encoded in DB Corridors as resources Compare crossing intervals

c0 c1 tenter texit c2 time Intersection Exceptions

Problem: deadlock Double blocked threats Solution: Recognition and response Problem: starvation

Unending stream of opposition Solution: Guaranteed progress a v 2 /(2 s ) Whats missing? Where do paths come from? Vehicles meander Pick corridors Add outgoing road

No goal seeking behavior Need directions Turn right at the first intersection, drive through two intersections, and then turn left. Route A succession of roads and intersections Like MapQuest Directions A global, strategic goal

The path must conform to the route May require lane changes Stages of Lane Changing Motivation Why change lanes? Decision Choosing a target lane Deciding when to go

Action How to change lanes? Motivation to Change Lanes Discretionary Lane Change (DLC) to improve driving conditions (e.g. speed, density) Mandatory Lane Change (MLC) to meet destination requirements (e.g. lane termination) Decision to Initiate a Lane Change Best conditions (e.g. flow)

Gap Acceptance Lead gap Lag gap Lane Changing Action Shift Pursuit Point Proportional Derivative Controller LC LC

o K p (o o ) K v ( o) t Speed Coupling Behavior Combination Combine accelerations from Cruising behavior Following behavior Intersection behavior Combine steering angle from

Tracking behavior Lane changing behavior Interactions Between Controllers Problem: impeded progress Following prevents overtaking Solution: Reduce following distance Stiffen controller

Problem: unveiled threat Appearance of leader in new lane Solution: Split attention follow 2 leaders Summary An accurate, efficient, robust roadway model Ribbon network Arc length parameterization

Efficient mapping between ribbon and Cartesian coordinates A framework for modeling behaviors Ribbon based tracking Path based behaviors Route as a strategic goal Future Work Pedestrians Modeling non-oriented navigable surfaces (e.g. intersections)

Pursuit Point Control Behavioral Diversity Acknowledgments NSF Support: INT-9724746, EIA-0130864, and IIS-0002535 Contributing students, staff, faculty Jodie Plumert David Schwebel Penney Nichols-Whitehead Jennifer Lee Sarah Rains

Sara Koschmeder Ben Fraga Kim Schroeder Stephanie Dawes Lloyd Frei Keith Miller Geb Thomas Pete Willemsen HongLing Wang Steffan Munteanu Joan Severson

Tom Drewes Forrest Meggers Paul Debbins Bohong Zhang Zhi-hong Wang Xiao-Qian Jiang

Recently Viewed Presentations

  • Management Information Systems

    Management Information Systems

    Management Information Systems Terminology Confusion MIS = the study of information technology in business settings But, MIS is also term to refer to class of systems used to support operational and tactical decisionmaking A Model for Problem Solving Decision Making...
  • ELECTRONIC COMMERCE E-COMMERCE ADVERTISING:  Affiliate Programs (Slide 1

    ELECTRONIC COMMERCE E-COMMERCE ADVERTISING: Affiliate Programs (Slide 1

    ELECTRONIC COMMERCE E-COMMERCE ADVERTISING: Affiliate Programs (Slide 1 of 2) E-COMMERCE ADVERTISING: Search Engine Marketing (Slide 1 of 2) E-COMMERCE ADVERTISING: Search Engine Marketing (Slide 2 of 2) E-COMMERCE ADVERTISING: Pay Per Click E-COMMERCE IMPLEMENTATION: Simplified E-Commerce E-COMMERCE IMPLEMENTATION: Virtual...
  • Ramping up Root Cause Analysis for UIP Introductions

    Ramping up Root Cause Analysis for UIP Introductions

    Two Types of Rating Scales. Frequency Rating Scales = how often something (criteria) has been done/met. Quality Rating Scales = judgement of the quality with which criteria were met without specific descriptions of different levels of quality (may involve making...
  • COMPENSATION CONVERSATION TEACHER POSITIONS ONLY erPoint 1 of

    COMPENSATION CONVERSATION TEACHER POSITIONS ONLY erPoint 1 of

    Does the new hire scheduleapply to existing teachers?. TOOL FOR EXTERNAL APPLICANTS:The NEW HIRE schedule is a tool to assist applicants in estimating what they would earn if they join our Denton ISD family. TOOL FOR HR ADMINISTRATORS: Our team...
  • Data Analysis Summary - National Cancer Institute

    Data Analysis Summary - National Cancer Institute

    Data Analysis Summary ... also present Talking about data analysis is difficult We do not yet have language to do so Complicated Not clear what details are important Overview Analytical Validity Enhance Clinical Utility Data Sharing Messages to NCI Analytical...
  • Introducing IPitomy Smart Personal Console (SPC)

    Introducing IPitomy Smart Personal Console (SPC)

    Smart Personal Console (SPC) Smart Personal Console Overview SPC allows users more control over their personal communications settings. Users can view/set: Received calls Buttons on their phones (dependent on system administrator settings) Forwarding options Follow-Me options Unified Messaging options (Voicemail-to-Email)...
  • GCSE English Language J35102 interactive SAM

    GCSE English Language J35102 interactive SAM

    the gladiators died and the slaves were thrown to the lions. A vulgar American . remarked to me, "It looks like a mighty fine quarry." They talk nasally. Mary, what ... The final Reading question is a comparative task, looking...
  • The Server Architecture Behind Killzone Shadow Fall

    The Server Architecture Behind Killzone Shadow Fall

    The Server Architecture Behind Killzone Shadow Fall. Jorrit Rouwé. Lead Game Tech, Guerrilla Games