Rural Intersection Decision Support (IDS) System: Status and Future Work Alec Gorjestani Arvind Menon Pi-Ming Cheng Lee Alexander Bryan Newstrom Craig.

Slides:



Advertisements
Similar presentations
Presented by: Richard Wood. Goals and strategies Methods Performance evaluation Performance improvements Remaining Challenges.
Advertisements

Driver Behavior Models NSF DriveSense Workshop Norfolk, VA Oct Mario Gerla UCLA, Computer Science Dept.
Mobile Resource Manager v2. Core Pillars  Engine - High fuel costs, vehicle maintenance  Productivity - Customers expect increasing levels of service.
Intersections & Right of Way
Department of Electrical and Computer Engineering Development of a Portable Work Zone Traffic Safety Information System using DSRC Based V2I and V2V Communication.
Advances And Vision In Active Road Safety Systems In The USA 3 rd Conference on Intelligent Transportation Systems in Israel Michael Freitas Ygomi LLC.
Final Year Project LYU0301 Location-Based Services Using GSM Cell Information over Symbian OS Mok Ming Fai CEG Lee Kwok Chau CEG
Human Factors Research Issues for Cooperative Intersection Collision Avoidance Systems (CICAS) Vicki Neale, Ph.D. Director, Center for Vehicle-Infrastructure.
A Tracking-based Traffic Performance measurement System for Roundabouts/Intersections PI: Hua Tang Graduate students: Hai Dinh Electrical and Computer.
Advanced Public Transit Systems (APTS) Transit ITS CEE582.
Final Year Project LYU0301 Location-Based Services Using GSM Cell Information over Symbian OS Mok Ming Fai CEG Lee Kwok Chau CEG.
Date / references EBMS Solution for Police Agenda EBMS Product Range Emergency Service Sensor Solution Tracking Solution Video Solution Check.
Cooperative Intersection Collision Avoidance Systems Initiative May 2005, ITS America Annual Meeting Mike Schagrin ITS Joint Program Office U.S. Department.
Cooperative crash prevention using human behavior monitoring Susumu Ishihara*† and Mario Gerla† (*Shizuoka University / †UCLA) Danger ! ! !
Driver Distraction: Results from Naturalistic Teenage Driving Studies Charlie Klauer, Ph. D. Research Scientist Group Lead: Teen Risk and Injury Prevention.
Mobile Video Systems Presents: Digital Eye Trans Cam 3/4G Live View vehicle camera system.
Rural ITS Safety Solutions (RITSS) 2010 ITS America Annual Meeting Houston, TX May 4, ITS America Annual Meeting Houston, TX May 4, 2010 Marthand.
Mobile Distributed 3D Sensing Sandia National Laboratories Intelligent Sensors and Robotics POC: Chris Lewis
MN IDS Intersection Construction Update. MN IDS Test Intersection u Design Completed 15 Jan 2004 u Design review with Mn/DOT traffic, geometric, district,
National VII Architecture – Data Perspective Michael Schagrin ITS Joint Program Office US Department of Transportation TRB 2008 Annual Meeting Session.
Intelligent Transportation System (ITS) ISYM 540 Current Topics in Information System Management Anas Hardan.
1. This seminar paper is based upon the project work being carried out by the collaboration of Delphi- Delco Electronics (DDE) and General Motors Corporation.It.
Chapter 16 Designing Effective Output. E – 2 Before H000 Produce Hardware Investment Report HI000 Produce Hardware Investment Lines H100 Read Hardware.
University of Maryland Department of Civil & Environmental Engineering By G.L. Chang, M.L. Franz, Y. Liu, Y. Lu & R. Tao BACKGROUND SYSTEM DESIGN DATA.
Autonomous Vehicles By: Rotha Aing. What makes a vehicle autonomous ? “Driverless” Different from remote controlled 3 D’s –Detection –Delivery –Data-Gathering.
Meeting of State Pooled Fund Partners April 20, 2005 "Reducing Crashes at Rural Intersections: Toward a Multi-State Consensus on Rural Intersection Decision.
Rural Intersection Collision Avoidance System (RICAS) US Highway 53 and State Highway 73 Minong, Wisconsin Additional information Project Website:
F Networked Embedded Applications and Technologies Lab Department of Computer Science and Information Engineering National Cheng Kung University, TAIWAN.
lesson 5.3 DECIDE AND EXECUTE
Travel Speed Study of Urban Streets Using GPS &GIS Tom E. Sellsted City of Yakima, Washington Information Systems and Traffic.
Test Intersection: Status, Results, Preparation for State Data Collection Lee Alexander Pi-Ming Cheng Alec Gorjestani Arvind Menon Craig Shankwitz Intelligent.
By Ayushi Pradhan News Event: Article: New Cars Won’t Let You Sleep! By Shweta Dhadiwal Under Automobiles from Electronics For You Issue March 2010.
Results of IDS Rural Intersection Data Collection Lee Alexander Pi-Ming Cheng Max Donath Alec Gorjestani Arvind Menon Bryan Newstrom Craig Shankwitz April.
Use of GIS Methodology for Online Urban Traffic Monitoring German Aerospace Center Institute of Transport Research M. Hetscher S. Lehmann I. Ernst A. Lippok.
Mitigation of Crashes At Unsignalized Rural Intersections IDS Quarterly Meeting June 14-5, 2004 Providing Intersection Decision Support for the Driver:
Portable IDS Design Issues and Tradeoffs Lee Alexander Intelligent Vehicles Lab University of Minnesota.
September 25, 2013 Greg Davis FHWA Office of Safety Research, Development and Test Overview of V2I Safety Applications.
Transit Signal Priority (TSP). Problem: Transit vehicles are slow Problem: Transit vehicles are effected even more than cars by traffic lights –The number.
Rural Intersection Decision Support (IDS) System Demo Highlights What you won’t see (Well, probably not this)
Vs >Slash fuel costs as much as 13.2%* by reducing idling, miles driven, & speeding >Complete more jobs and improve service with better dispatch.
University of Minnesota Intersection Decision Support Research - Results of Crash Analysis University of Minnesota Intersection Decision Support Research.
Vehicle Segmentation and Tracking From a Low-Angle Off-Axis Camera Neeraj K. Kanhere Committee members Dr. Stanley Birchfield Dr. Robert Schalkoff Dr.
Status of ITS research May Peter Sweatman David Kapp.
Toward a Multi-State Consensus on Rural Intersection Decision Support: Objectives u Gain understanding of issues involved with national rural intersection.
Cooperative Intersection Collision Avoidance Systems – Stop Sign Assist (CICAS-SSA) ITS America 2007 Annual Meeting Session.
Motivation, high level description for a portable IDS system Lee Alexander Pi-Ming Cheng Alec Gorjestani Arvind Menon Craig Shankwitz Intelligent Vehicles.
MN IDS Project Progress Update. MN IDS Update Progress to date v Test Intersection v Sensor evaluation results v Benefit:cost efforts progress v Human.
Hcm 2010: BASIC CONCEPTS praveen edara, ph.d., p.e., PTOE
Accessing and Integrating CV and AV Sensor Data into Traffic Engineering Practice Dr. Jonathan Corey ITITS 2015 December 12, 2015 Chang’an, China.
Using Adaptive Tracking To Classify And Monitor Activities In A Site W.E.L. Grimson, C. Stauffer, R. Romano, L. Lee.
SP1 – Meeting April 23 rd Schieberdingen Electronic Systems Page 1 of 13 Integrated Project Co-operative Systems for Road Safety “Smart Vehicles.
SHRP 2 Safety Databases: Continuous Observations of Seat Belt Use Jim Hedlund APHA Annual Meeting November 18, 2014 Accelerating solutions for highway.
1 The ILC Control Work Packages. ILC Control System Work Packages GDE Oct Who We Are Collaboration loosely formed at Snowmass which included SLAC,
Digital Highway Measurement System Qatar Ministry of Transportation August 15, 2007 Dr. Kunik Lee Chief Safety Scientist, Office of Safety R&D TFHRC, FHWA,
Human Factors Progress IDS Project Nicholas Ward Jason Laberge Mick Rakauskas HumanFIRST Program.
Mapping of Traffic Conditions at Downtown Thessaloniki with the Help of GPS Technology P. D. Savvaidis and K. Lakakis Aristotle University of Thessaloniki,
DSRC and SPaT, SSM, SRM & MAP
Minnesota Team: Mitigation of Crashes At Unsignalized Rural Intersections 1 st CICAS Coordination Meeting Sept. 27, 2004 Intersection Decision Support.
IDS Project Update on Human Factors and Simulation (Geometry Completed)
Intelligent and Non-Intelligent Transportation Systems 32 Foundations of Technology Standard 18 Students will develop an understanding of and be able to.
Rural Intersection Decision Support - Crash Analysis Rural Intersection Decision Support - Crash Analysis Presented at Pooled Fund Meeting April 19, 2004.
ParkNet: Drive-by Sensing of Road-Side Parking Statistics Irfan Ullah Department of Information and Communication Engineering Myongji university, Yongin,
IMAGE PROCESSING APPLIED TO TRAFFIC QUEUE DETECTION ALGORITHM.
Intelligent Transportation System
Sight Distances.
Overview of CV2X Requirements
Technologies and type examination
Vehicle Segmentation and Tracking in the Presence of Occlusions
Mike Schagrin ITS Joint Program Office
Presentation transcript:

Rural Intersection Decision Support (IDS) System: Status and Future Work Alec Gorjestani Arvind Menon Pi-Ming Cheng Lee Alexander Bryan Newstrom Craig Shankwitz University of Minnesota ITS Institute Intelligent Vehicles Lab

Late Breaking Surveillance

Presentation Overview u Present status u Validation/Characterization work u Optimization work u Data collection u Data analysis v driver behavior v 4 seasons of data, 24/7 u Additional technical capabilities for CICAS u Future Work u Anecdotes

Present Status u All Systems working (showed yesterday) u Open Architecture, we can integrate most any sensor, communication system, processor, etc. u Mostly off-the-shelf hardware u Need to add v Wireless communication Add hardware at radar station cabinets Add hardware at main controller cabinet v Radar based vehicle classification IV Lab has sensors No J1708 message set for vehicle classification capability Eaton-Vorad reorganizing, point of contact difficult to find

Present Status (cont’d) u Need to add v Delphi Mainline Radar Purchase Order June Sensors ordered for comparison to Vorad Not yet arrived Calls to Delphi not returned. u Would really like DSRC Test Kit (wink wink, nudge nudge)

Validation work: vehicle masking sensitivity u Radar sensitivity analysis v “masking” of small radar Xsections by large ones v Distance at which a motorcycle is masked by a passenger car or truck X Use DGPS equipped probe vehicles to determine X at which motorcycle is masked

Validation work: radar detection/accuracy validation u Radar detection miss rate v Use two reference sensors as a measure against radar detection and range accuracy v Light beam known location v Broken beam triggers interrupt v Compare radar data with light beam (presence/location) and camera (presence/location) v Complements previous accuracy work DGPS-Probe Vehicle Radar

Vehicle/Gap Tracker u Tracker program Kalman filter-based state estimator u Noisy radar signals v Internal sensor processing tends to “pull in” vehicle position along sensor longitudinal axis v If uncompensated, leads to lane assignment errors (azimuth errors) u States include vehicle location, vehicle speed, vehicle heading, lane assignment u Gap tracking = 1-vehicle tracking

Validation work: Vehicle/Gap Tracker Performance u All vehicles entering intersxn (both major and minor roads) assigned ID u All vehicles tracked within intersxn boundaries u DGPS position compared to tracker position/ID for lane changes, left turns, right turns, speed variations, etc.

Validation work: Vehicle/Gap Tracker sensitivity to loss of radar u Possibility radar may fail u Tracker program designed to v Detect radar loss v Compensate for radar sensor loss u Validate by disabling radar, running program, and comparing DGPS-based state estimate with tracker estimate

Validation work: Vehicle Classification System performance u Compare radar & laser based system performance v $1200 system vs. $13,000 system v Determine performance envelope for Benefit:Cost analysis u Presence verified by light beam sensor u Reference is visible light and IR Cameras aimed at minor roads u Image processing results compared to radar and Lidar results. If three agree, performance is as expected. (Automation improves efficiency) u Discrepancies analyzed by human viewing captured images v Identify problem areas v Improve system capability

Vehicle Classification Validation Configuration

Crossroads Trajectory Tracker Validation DGPS-Probe Vehicle

Optimization work: Radar u Radar Sensor Spacing v Intersection overbuilt v Presently, 100% coverage v Each sensor, 400’ range v Tracker good enough for 500’ spacing? 600’ spacing? Less spatial density => lower sensor cost  Less trenching  Lower power  Lower maintenance  Lower cost

Optimization Work: Radar u Radar Sensors Considered v Presently, Eaton v Delphi Ordered Will be installed as soon as they arrive Specifications close to Eaton Vorad Considerably more expensive v Autosense? Decision based on VTTI’s results. Autosense specs close to Eaton, but much longer range Considerably more expensive than Eaton. Geometric considerations – “seeing” over a hill v CA COTS Study Promising Technology

Optimization work: Communication u Wired vs. Wireless communication v Original thought was to go wireless. However, given effort to trench power, wired communication was an incremental cost. v Wireless Pros:  Offers significant cost savings: i.e., no trenching Cons:  Unknown reliability, sensitivity to local EMI conditions  Sufficient bandwidth for present and future applications?

Optimization work: Communication u Wired v Pros: Known bandwidth, known reliability, immunity from local EMI v Cons: Trenching costs, wire breakage, etc. (incremental cost not too great if power trenching done at same time). u Hardwired DSL to outside world for analysis, diagnostics, streaming video

Data Collection u Sensors v Mainline Radar Location, speed, heading, lane v Xroads: Camera, Laser, Radar Vehicle position, heading v Minor road Laser, Radar Vehicle length, height profile v Remote Weather Information System 0.9 miles North of Intersxn u Rates v Most sensors at 10 Hz v Laser at 30 Hz locally, processed data at 10 Hz v Video at 30 Hz v Weather at 15 minute intervals

Data Collection u Formats v Engineering data stored as a database of “snapshots” of the state of the intersection at 10 Hz v Video data.mpg4 at 30 Hz. 5 Cameras v 4 Gbyte data/day u Storage v Local 80 Gbyte removable drive v 2 Terabyte server at the U

Data Collection u Access v DSL at the Intersection, monitor status remotely v Mn/DOT truck station streaming video (maintenance, response) u Quality Assurance v Data checks v Periodic back-ups v Self-diagnostics

Data Analysis u Understand Driver Behavior v Statistics (Howard Preston’s work) showed that far-side (left turn) crashes (70% in general, 80% at our intersection) far outweigh nearside crashes v WHY? Right turns “easier?” Drivers take left in one motion rather than 2 (pause in median)? v Distribution of gaps accepted by drivers: what gaps are being taken? for right turns for left turns for crossing intersection How Safe are these?

Data Analysis – cont’d u Correlate driver behavior with v Vehicle type / size (vehicle classification) v Driver age (macroscopic level, limited basis initially license plate reader later) Limited basis means grad student observer v Driver gender (limited basis initially, license plate reader later) v Weather effects (R/WIS 0.9 Mile away), with in-road sensors (collecting data already) u Plan to collect data for 12 months, and analyze incrementally u Results directly applicable to Human Interface final design/deployment and algorithm strategy u Provides baseline measure for Field Operational Test

Future work u State Pooled Fund study underway v 7 states included v Goal is to instrument intersection in each state, determine regional behavioral differences with drivers u Portable Surveillance system v Sensors and comm. system built to analyze rural intersections (upcoming proposal to Minnesota Local Road Research Board) u Add microscopic driver data v License plate reader can yield driver age/gender information Important to understand crash causality v May eventually allow “tailoring” of warnings to specific driver v Early analysis complete. Details to be worked out Data from DPS Analysis

MN IDS Intersxn CICAS Capability - Communication u Wireless communication v Presently 2.4 GHZ B  Range about 1.6 Km 900 MHz RF Modem  Range about 4-6 Km v Future Mesh Networks DSRC (5.9 GHz) Emerging Technology  4 Foldable masts  4 transmit/receive sites  Easy to change HW  Not tied to a particular architecture

MN IDS Intersxn CICAS Capability - Communication u Differential GPS corrections v Intersection validation, mapping u Architecture Analysis v Data broadcasts v Client/Server v Router/switch v Bandwidth needs testing / analysis u Intersection state information comm. v Collision avoidance v Communication of data/in-vehicle warnings

MN IDS Intersxn CICAS Capability - Communication u Map Downloads v Map detail (we have layers of detail/info) v Range – how much /fundamental details needed for the intersection v Timing (data well in advance of the xroads) v Handshaking/verification Validation that vehicles which need data have it

MN IDS Intersxn CICAS Capability - Sensors u Differential GPS corrections v Methodology v Correction source v Validate accuracy requirements u Road Weather sensors v Warnings / notifications to vehicles u Vehicles as sensors v Road friction v Position/speed/heading for collision avoidance u Other v If it plugs in, we can use it.

Anecdotes u Local residents in favor of this technology v “dangerous intersection!” v “this will be great.” v “will that slow traffic on 52?” v “will that issue tickets?” v “when are you going online?” v “last winter, a LOT of cars went into the ditch…” u Two crashes have occurred since construction began in May v Right angle crash resulted in injuries (stretcher and ambulance)

This is a good summer job.