Intelligent Autonomous Vehicles

J. A. FarrellDepartment of Electrical Engineering

University of California, Riverside

Intelligent Autonomous Vehicles

ValueJudgment

Sensor World BehaviorProcessing Model Generation

Sensors Structure Actuators

World

Sensors Structure Actuators

World

SensorProcessing

BehaviorGeneration

Planning

WorldModel

Behavior Coordination

February 2009 UCR EE Department951-827-2159

Lane change: Interior view

Q: BehaviorsGT – go to point PUS – uninformed searchIS – informed searchMI – maintain: inMO – maintain: outPD – post-declaration maneuvers

: Eventsf – finishc – detect chemical @td

n1 – no detection at t = td + t1

d – declare source

DES: Chemical Plume TracingDesign behaviors Q, event definitions , and transition function such that an autonomous underwater vehicle (AUV) will

• Proceed from a home location to a region of operation• Search for a chemical plume• Track a chemical plume in a turbulent flow to its source• Declare the source location• Return home

Q: BehaviorsGT – go to point PUS – uninformed searchIS – informed searchMI – maintain: inMO – maintain: outPD – post-declaration maneuvers

: Eventsf – finishc – detect chemical @td

n1 – no detection at t = td + t1

d – declare source

DES: Chemical Plume TracingDesign behaviors Q, event definitions , and transition function such that an autonomous underwater vehicle (AUV) will

• Proceed from a home location to a region of operation• Search for a chemical plume• Track a chemical plume in a turbulent flow to its source• Declare the source location• Return home

f f

c c f

f c

n1 d

f

GT(P)

GT(H) PD

MI MO

US IS

CPT In-water Experimental Results (June 2003)

AUV for Hull Search

Behaviors:• velocity & angular rate• velocity & attitude• trajectory following w/ zero attitude• trajectory following w/ nonzero attitude• surface following• hold position and attitude• scan object at offset

Sim

UCR EE Department951-827-2159

Guidance: Positioning & GIS

UCR EE Department951-827-2159

Driver Warning• Lane Departure Warning & Guidance

– Requirement:• Accurate position determination relative to lane

• Collision Warning– Accurate determination of position relative to

nearby vehicles• Absolute position based

– Accurate position determination– Communication between vehicles

• Relative position based– Feature based: Vision, radar, lidar

UCR EE Department951-827-2159

Project Subgoals• Absolute Position Determination

– Determines: earth relative position, velocity,acceleration, attitude, angular rates

• Relative Position Determination– Lane relative– Neighboring vehicle relative

• Vehicle Control– Determine the steering commands to force

the vehicle states to desired values.

d

r

Enabling Technological Advances• Computational Hardware• Sensors and Sensor Processing• Computational Reasoning• Control Theoretic Advances• Software Engineering Principles

Topics:– Deliberative & reactive planning– Behaviors & nonlinear control– Discrete event & hybrid systems– Theory & practicality: Cognitive mapping

Sensors Structure Actuators

World

SensorProcessing

BehaviorGeneration

Planning

WorldModel

Behavior Coordination

Concluding Comments• Turing Test:

– Optimal– Strong super-human: performs better than all humans– Super human: performs better than most humans– Sub-human: performs worse than most humans

• Intelligent AV Capabilities, e.g.:

– All involve feedback processes, w/ many challenging & unsolved problems

– Control expertise has & continues to expand its role, both developing & utilizing new tools, to yield increasingly robust and capable systems

• The concept of behaviors, combined w/ advanced control methods, enables robust abstraction for higher level IAV performance

Navigation ControlData fusion Map buildingPlan management Learning