dr. shankar sastry, chair electrical engineering & computer sciences university of california,...

12
Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

Post on 21-Dec-2015

217 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

Dr. Shankar Sastry, ChairElectrical Engineering & Computer Sciences

University of California, Berkeley

Page 2: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

Sub-problems for PEG

Sensing– Navigation sensors -> Self-localization– Detection of objects of interest

Framework for communication and data flow

Map building of environments and evaders– How to incorporate sensed data into agents’ belief states probability distribution over the state space of the world

(I.e. possible configuration of locations of agents and obstacles)– How to update belief states

Strategy planning – Computation of pursuit policy mapping from the belief state to the action space

Control / Action

SENSOR NETWORKS

Page 3: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

Localization & Map building

Localization : updating agent’s position relative to the environment

Map building: updating object locations relative to the agent’s position or to the environment

They can be benefited from different techniques, e.g.,Occupancy-based : well-suited to path planning, navigation, and

obstacle avoidance, expensive algorithms(e.g. pattern matching) required for localization

Beacon-based : successful to localization

Fail in cluttered environment , unknown types of objects

Page 4: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

How Sensor Web can help?

Current BEAR Framework for PEG– Navigation sensors(INS, GPS, ultrasonic sensor…) for localization– Ultrasonic sensor for obstacle avoidance– Vision-based detection for moving targets (enemy)– Occupancy-based map building for planning

Potential Issues for real-world PEG– GPS jamming, unbounded error of INS, noisy ultrasonic sensors– Computer vision algorithms are expensive– Unmanned vehicles are expensive It is unrealistic to employ many number of unmanned vehicles to

cover a large region to be monitored. Static optimal placement of unmanned vehicles for cooperative

observations are already difficult (e.g. art-gallery or vertex-cover problems).

Page 5: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

actuatorpositions

inertialpositions

height over

terrain

• obstacles detected• targets detectedcontrol

signals

INS GPSultrasonic altimeter

vision

state of agents

obstacles detected

targetsdetected

obstaclesdetected

agentspositions

desiredagentsactions

Tactical Planner& Regulation

Vehicle-level sensor fusion

Strategy Planner Map Builder

• position of targets • position of obstacles • positions of agents

Communications Network

tacticalplanner

trajectoryplanner

regulation

•lin. accel.•ang. vel.

Targets

Exogenousdisturbance

UAV

dynamics

Terrain

actuatorencoders

UGV dynamics

NEST SENSORS

•objects

detected

Page 6: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

Pursuit-Evasion Game Experiment Setup

Ground Command Post

Waypoint Command

Current Position, Vehicle Stats

Current Position, Vehicle Stats

Pursuer: UAV

Evader: UGV

Evader location detected by Vision system

Page 7: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

AerialPursuer

Current Experimental Setup for PEG

Centralized Ground Station

Experiment Setup

-Cooperation of

-One Aerial Pursuer (Ursa Magna 2)-Three Ground Pursuer (Pioneer UGV)

-Against One Ground Evader (Pioneer UGV)

(Random or Counter-intelligent Motion)

-Wireless Peer-to-Peer Network

Arena: Cell: 1m x 1mDetection: Vision-based or simulated

GroundEvader

Ground Pursuer

3x3m Camera View

Waypt Request

Vehicle PositionVision Sensor

Vehicle PositionVision Sensor

Page 8: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

Experimental Results: Pursuit-Evasion Games with 4UGVs and 1 UAV (Spring’ 01)

Page 9: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

Sensor Webs in BEAR Network

Ground Monitoring System

Landing Decks

Ground Mobile Robots

UAVs

LucentOrinoco (WaveLAN)

(Ad Hoc Mode)

Sensor Webs

Gateways

Page 10: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

Sensor Nets for Map Building & PEG

Necessary information for map building and PEGBinary detection + time stamp + ID(or position) of the node

Sensing

Platform

Time-

synchronization

Self-localization

Page 11: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

Abstraction of Sensor Nets

Properties of general sensor nodes are described by

– sensing range, confidence on the sensed data

– memory, computation capability

– Clock skew

– Communication range, bandwidth, time delay, transmission loss

– broadcasting methods (periodic or event-based)

– And more…

To apply sensor nodes for the experiments with BEAR platform,

introduce super-nodes ( or gateways ), which can

– gather information from sub-nodes

( filtering or fusion of the data from sub-nodes for partial map building)

– communicate with UAV/UGVs

Page 12: Dr. Shankar Sastry, Chair Electrical Engineering & Computer Sciences University of California, Berkeley

Roadmap towards complete PEG Experiments

I. N nodes uniformly distributed in each cell in an N-grid environment,

e.g, 400 nodes placed in each 1-by-1 m cell for 20x20 meter flat surface at

RFS.

( test self-localization and detection, and integrate with BEAR platform )

II. Nn nodes randomly placed, with known positions

(capture time vs.Nn )

III. Nn nodes randomly placed, with unknown positions