Into an automated , cooperative , diverse and integrated futuristic transportation system

22
School of Systems, Engineering, University of Reading rkala.99k.org 25 th June, 2013 Rahul Kala Into an automated, cooperative, diverse and integrated futuristic transportation system Motion Planning for Multiple Autonomous Vehicles

description

Into an automated , cooperative , diverse and integrated futuristic transportation system. Motion Planning for Multiple Autonomous Vehicles. Rahul Kala. Organized and Unorganized Traffic. - PowerPoint PPT Presentation

Transcript of Into an automated , cooperative , diverse and integrated futuristic transportation system

Motion Planning for Autonomous vehicles

25th June, 2013Rahul KalaInto an automated, cooperative, diverse and integrated futuristic transportation systemMotion Planning for Multiple Autonomous VehiclesSchool of Systems, Engineering, University of Readingrkala.99k.orgMotion Planning for Multiple Autonomous VehiclesOrganized and Unorganized Trafficrkala.99k.org

A distant future where all vehicles would autonomously be driven would be preceded by a transient period where automated and nonautomated vehicles coexist.Vanholme, B.; et al. "Highly Automated Driving on Highways Based on Legal Safety," IEEE Transactions on Intelligent Transportation Systems, vol.14, no.1, pp.333-347, March 2013Motion Planning for Multiple Autonomous Vehiclesrkala.99k.org

Organized and Unorganized TrafficOrganized

Image Courtesy: railway-technical.com, blogs.abc.net.au

UnorganizedMotion Planning for Multiple Autonomous VehiclesThesisrkala.99k.org

Motion Planning for Multiple Autonomous VehiclesTrajectory Generationrkala.99k.org

AStatic ObstaclesBCSelect the best plan: (a) A overtakes B from right, B drifts left, A crosses the obstacles, C waits, (b) A follows B and both cross the obstacles while C waits, (c) B crosses the obstacles followed by C and A, (d) C crosses the obstacle a from its left, while A follows B to cross the othersaMotion Planning for Multiple Autonomous VehiclesIntelligent Management of the Transportation System

rkala.99k.org

Motion Planning for Multiple Autonomous VehiclesGenetic AlgorithmR1R2R3Overtake seems to be too close, ask R2 to slowR3 lies directly ahead, ask R3 to drift to its leftGA optimized trajectoriesCoordination using traffic heuristicsrkala.99k.org

Under revision: Applied Soft Computing, IF: 2.140Motion Planning for Multiple Autonomous VehiclesRRT

Less exploration at the extremesMore exploration at the central areasrkala.99k.org

In Proc. IEEE Cybernetic Intelligent Systems, Docklands, London, pp. 20-25Motion Planning for Multiple Autonomous VehiclesRRT ConnectIf prospective collision with a vehicle in the same direction If you cannot overtake, follow Speed equal to the heading vehicle and re-planIf prospective collision with a vehicle in the opposite direction: Decrease speed iteratively and re-plan till a feasible plan is reachedIf going straight ahead possible, goTree expansionsrkala.99k.org

Paladyn Journal of Behavioural Robotics, 2(3): 134-144.Motion Planning for Multiple Autonomous VehiclesMulti-Level Planning Layer 1: Road Selection. Blue=selected road. Red= Road graph

Layer 2: Pathway Selection. Collaboratively decide whether each vehicle goes through left or right of an obstacle. Blue=selected pathway. Red=Entire Pathway Graph Equal distribution of pathway Layer 3:Pathway Distribution. At each slice (pathway segment) the expected vehicles at the same time are placed. Red=computed points for the vehicle, Blue=Rough trajectory joining the placement points, Green=Other expected vehicleLayer 4: Trajectory Generation. Smoothing, collision checking, local optimizationJ. Intell. Rob. Syst, DOI:10.1007/s10846-013-9817-7, IF: 0.827Motion Planning for Multiple Autonomous VehiclesDynamic Distributed LanesAny general state in graph searchKnown trajectory for the state for the higher priority vehiclesOvertake Red?, or Follow Red?, or Wait for green to cross obstacle? try all 3 possibilitiesrkala.99k.org

Motion Planning for Multiple Autonomous VehiclesFuzzy LogicInputsOutputsrkala.99k.org

Motion Planning for Multiple Autonomous VehiclesLateral PotentialsForward Potential: right/left decided by heuristics/ strategy parameter, time to collisionSide Potential: turn left, inversely proportional to distanceSide Potential: turn right, inversely proportional to distanceBack Potential: right/left decided by heuristics/ strategy parameter, time to collisionDiagonal Potential: turn right, inversely proportional to distanceDiagonal Potential: turn left, inversely proportional to distanceIn Proc. IEEE Intelligent Vehicles Symposium, Alcal de Henares, Spain, pp. 597-602.Motion Planning for Multiple Autonomous VehiclesElastic StripProjected position at the time of arrival Elastic Strip representing trajectory Repulsive potentials on strip from vehicles, obstacles, road boundariesOn seeing any new vehicle/ obstacle, try both overtaking from left and right and pick the better planAssign highest safe speed as per current position, trim plan such that it is feasiblerkala.99k.org

IEEE Trans. on Intell. Transp. Syst., DOI: 10.1109/TITS.2013.2266355, IF: 3.064 Motion Planning for Multiple Autonomous VehiclesBehaviours in decreasing order of priority

Logic Based Planning Engineering Applications of Artificial Intelligence, 26(5-6): 15881601.rkala.99k.org

Motion Planning for Multiple Autonomous VehiclesSemi-Autonomous Intelligent Transportation SystemCentral Information SystemVehicle Route PlanningVehicle ControlVehicle MonitoringTraffic Signal ModuleSpeed Lane ModuleVehicle Motion PlanningLane Booking Road Booking Scenario SpecificationMap/Initial conditionsTraffic at roadsSpeed of vehicles at lanesPosition/ SpeedSpeed LimitBooking SpecificationsSignal stateTraffic Info.Lane change, Follow, Stop/Start, TurnBooked?Booked?rkala.99k.org

Motion Planning for Multiple Autonomous VehiclesCongestion Avoidance in City TrafficHypothesisMotion Planning for Multiple Autonomous VehiclesReaching Destination before Deadline with Intelligent Transportation Systems Road Network GraphIntelligent Agents Placed at every intersectionRoadMonitor all incoming vehicles. Learn average speed and variationrkala.99k.org

Motion Planning for Multiple Autonomous VehiclesReaching Destination before Deadline with Cooperative Intelligent Transportation Systems Times in increasing orderExpected TimeLate TimeCancel TimeComfortable StateLate StateVery Late StateGive Up StateVehicle StatesVarious times at every intersectionCost of latenessrkala.99k.org

Motion Planning for Multiple Autonomous VehiclesResultsrkala.99k.org

Motion Planning for Multiple Autonomous VehiclesConclusionsSituational assessment

Context assessment

Algorithm switching

Studying the problems in local settings, using regional data sets

The future is unknown and diverse!rkala.99k.org

Motion Planning for Multiple Autonomous Vehiclesrkala.99k.org

Thank YouAcknowledgements:Commonwealth Scholarship Commission in the United Kingdom British CouncilMotion Planning for Multiple Autonomous Vehicles