Sensorweb Architecture and Dynamic Sensor Tasking in Mobile Sensor Networks Sanjoy K. Mitter, Massachusetts Institute of Technology Joint work with: Maurice Chu (currently at PARC, Palo Alto, CA) and Peter Jones (Lincoln Laboratory) Phone 617-253-2160, 617-258-8364 (Fax) Email [email protected]Web http://web.mit.edu/mitter/www/ MURI Review: SensorWeb Data Fusion in Large Arrays of Microsenso Dec 2, 2005 SensorWeb MURI Review Meeting, Dec 2, 2005
33
Embed
Sensorweb Architecture and Dynamic Sensor Tasking in Mobile Sensor Networks
Sensorweb Architecture and Dynamic Sensor Tasking in Mobile Sensor Networks. Sanjoy K. Mitter, Massachusetts Institute of Technology Joint work with: Maurice Chu (currently at PARC, Palo Alto, CA) and Peter Jones (Lincoln Laboratory). - PowerPoint PPT Presentation
Welcome message from author
This document is posted to help you gain knowledge. Please leave a comment to let me know what you think about it! Share it to your friends and learn new things together.
Transcript
Sensorweb Architecture and Dynamic Sensor Tasking in Mobile Sensor Networks
Sanjoy K. Mitter, Massachusetts Institute of TechnologyJoint work with: Maurice Chu (currently at PARC, Palo Alto, CA) and Peter Jones (Lincoln Laboratory)
MURI Review: SensorWebData Fusion in Large Arrays of MicrosensorsDec 2, 2005
SensorWeb MURI Review Meeting, Dec 2, 2005
Sensorweb Architecture …
Extension of Maurice Chu’s Ph.D Thesis
Current research at PARC (Palo Alto, CA)
S.M. Thesis of Peter Jones (currently at Lincoln Laboratory, MIT)
Distributed Attention for Sensor Networksand the
Beginnings of a Conceptual Framework for Designing Resource Aware Distributed Algorithms
Maurice ChuPARC
Research Vision
Goal Move from specialized information processing systems engineered for specific domains toward general-purpose systems embedded in unstructured, dynamic environments
Framework for managing the complexity in designing information processing algorithms for data interpretation.
Complexity can come from limited resources of the system like processing power,
communication bandwidth, sensing capabilities, energy, link/node failure characteristics
inherent algorithmic complexity to extract information Challenges
Information architecture Mapping to physical system (e.g., distributed implementations) Efficient representations of information Interpretation algorithms (estimation, detection, inference)
Sensor Networks Dense ad hoc network of heterogeneous
sensor nodes (equipped with sensing, processing, communication)
Enormous potential for extracting all kinds of information from data sensed about the environment
A few sensors can relatively easily find and track a vehicle in the desert.
But how do we find and monitor anything amongst all these distractors and clutter?
Large Scale Video Surveillance Goal
Enable video surveillance of large complex environments to monitor and detect multiple potential threats and surprises.
Difficulties Unstructured environment
Distractors, clutter, occlusions Information Overload
Human operators overwhelmed Resource limited
Insufficient sensing, processing, and communication resources to monitor all phenomena over extended periods
Solution: Distributed AttentionInspired by biological focusing mechanism
Challenges Information Processing
How do we efficiently represent and monitor known dynamic phenomena?
Abnormal BehaviorHow do we learn what is abnormal behavior, detect them, and react to them?
Peripheral AwarenessHow do we maintain awareness of newly emerging unboserved phenomena? How do we model the “emergence” of phenomena?
Resource AllocationHow do we share limited sensing resources among multiple competing tasks? How do we evaluate task priorities and what kinds of negotiations must occur to allocate resources optimally?
Distributed ImplementationHow do we implement algorithms in a distributed fashion under bandwidth constraints, energy considerations, processing time, latency constraints, etc.? What is the information exchanged and how does it flow through the network?
AdaptationHow can the system adapt to changes in the environment and failures and additions to the network?
Outline
Problem Statement and Challenges
Distributed Attention ArchitectureConceptual view
Testbed Implementation
Future Work
Outline
Problem Statement and Challenges
Distributed Attention ArchitectureConceptual view
Testbed Implementation
Future Work
Distributed Attention Architecture
Layered Information Processing Architecturedata interpretation unit (detection, estimation, inference)
Peripheral Awareness Moduleenables attention to the unobserved emergence of abnormal phenomena
Resource Allocationallocates tasks to resources
Adaptation - evolve system behavior according to dynamic system characteristics and environment
Layered Information Processing
Architecture Peripheral Awareness
Resource Allocation
Sensing
Adaptation
taskstasks
controls
observations
Layered Information Processing ArchitectureConcept Global view of the transformation from data to information
Multi-layered filtering approach Layers loosely ordered from continuous signal-level representations to discrete
symbolic representations Organize distinct information processing tasks into separate layers (modularity)
Information flow considerations for distributed implementation Lower layers – little cross node communications, high bit-rate local data Higher layers – cross node communications, low bit-rate global data
Cognitive
Attentive
Pre-attentive
anomalous flow
optical flow
tracking
groups of tracks
behavior recognition
attacker identities
adjust tracking priority
known track position
ignore anomalous flow detect flow to landmark
sensor observation
Signal level
Knowledge level
Layered Information Processing ArchitectureConcept
Transitioning to a distributed system architecture Vertical cuts of layers Communications across vertical boundaries within
layers
Cognitive
Attentive
Pre-attentive
anomalous flow
optical flow
tracking
groups of tracks
behavior recognition
attacker identities
adjust tracking priority
known track position
ignore anomalous flow detect flow to landmark
sensor observation
Cognitive
Attentive
Pre-attentive
anomalous flow
optical flow
tracking
groups of tracks
behavior recognition
attacker identities
adjust tracking priority
known track position
ignore anomalous flow
detect flow to landmark
sensor observation
Node 1Cognitive
Attentive
Pre-attentive
anomalous flow
optical flow
tracking
groups of tracks
behavior recognition
attacker identities
adjust tracking priority
known track position
ignore anomalous flow
detect flow to landmark
sensor observation
Node 2Cognitive
Attentive
Pre-attentive
anomalous flow
optical flow
tracking
groups of tracks
behavior recognition
attacker identities
adjust tracking priority
known track position
ignore anomalous flow
detect flow to landmark
sensor observation
Node 4Cognitive
Attentive
Pre-attentive
anomalous flow
optical flow
tracking
groups of tracks
behavior recognition
attacker identities
adjust tracking priority
known track position
ignore anomalous flow
detect flow to landmark
sensor observation
Node 3
Signallevel
Knowledgelevel
Information flow through sensor network
Distributed Attention ArchitectureConceptual View
Layered Information Processing
Architecture Peripheral Awareness
Resource Allocation
Sensing
Adaptation
taskstasks
controls
observations
Peripheral Awareness ModuleConcept
Models the emergence and propagation of abnormal behavior for intelligent focusing of attention on unobserved, emerging events.
Ex. Monte Carlo simulation of a stochastic process(flow of suspicion samples)
Mechanics Sensed areas clear suspicion
samples. Detection of abnormal behavior
handled by the information architecture
Effect Potential emerging targets compete
for resources with known targets
Bernoulli process generates suspicion samples
Propagation model simulates motion of suspicion samples
LSP Progress Review Presentation
Peter JonesMaster’s StudentJune 16, 2005
Completed Thesis Dynamic Sensor Tasking in Heterogeneous,
Mobile Sensor Networks Goal of time-optimal detection/discrimination in
sensor networks Extension of previous work in using conditional
entropy/mutual information for sensor tasking Methods applicable to multi-modal sensors Coordination protocol developed for exploiting
sensor inter-dependencies Accepted May 5, 2005 in fulfillment of the
requirements for EECS Master’s Degree
Background
Information Driven Sensor Query Intended to limit communication (and power usage) in sensor networks Compromises quality of inference (detection, tracking, etc.) for
computational and communication simplicity Primarily applied to static networks of power-limited, homogeneous
sensors Basic principle: choose a new “leader” in the neighborhood of the
current leader to maximize the expected information gain of the next sensory action
)]|()([max )(1 ssNsk zxHxIEsk
−= ∈+
Multi-Modal Sensor Management
Tsitsiklis, Popp, Bailey (MIT/Alphatech) Considered two discrete modes (HRR v. GMTI) Optimized for footprint location (continuous
Wide Area 6529 1174 4583 10511High Res 5667 759 4280 7258MIAR 5429 775 3957 7870
• Multi-modal Simulation
• Constants a,b now a function of mode
• Results of 50 monte-carlo simulations
Coordination Experiment Setup
Cannonical Problem Definition: Two sensors, three locations, one common between the two. If both sensors attempt to measure the common location, neither receives a good measurement (mutual jamming).
Coordination Results
Advanced Coordination Experiment
• Set of 5 heterogeneous sensors, each with different detection/discrimination characteristics
• 25 possible target locations, 3 different target types
• Entropic threshold set low enough that there were no missed detections or incorrect classifications in any of the 150 trials
Mean Time
Std Time
Min Time
Max Time
Random 874.06 146.76 567 1327
Utilitarian 94.74 6.68 81 115
Negotiated MIAR
124.52 10.96 107 165
Summary
• Information driven sensing helpful in groups of (possibly interacting) multi-modal sensors
• Extension of entropy-based measures to time-optimal scheduling
• Viable coordination protocol• Verification of entropy-based utilities and