Adaptive Autonomous Robot Teams for Situational Awareness

1
Adaptive Autonomous Robot Teams for Situational
Awareness

• Georgia Techs Role

2
Personnel

• Georgia Tech
• Faculty
• Prof. Ron Arkin
• Prof. Tucker Balch
• Dr. Robert Burridge
• GRAs
• Keith OHara
• Patrick Ulam
• Alan Wagner
• Matt Powers
• Mobile Intelligence Inc.
• Dr. Doug MacKenzie

3
Impact GT Role

• Provide communication-sensitive planning and
  behavioral control algorithms in support of
  network-centric warfare, that employ valid
  communications models provided by BBN
• Provide an integrated mission specification
  system (MissionLab) spanning heterogeneous teams
  of UAVs and UGVs
• Demonstrate warfighter-oriented tools in three
  contexts simulation, laboratory robots, and in
  the field

4
Communication Sensitive Planning

• Provide support for terrain models and other
  communications relevant topographic features to
  MissionLab
• Use plans-as-resources as a basis for multiagent
  robotic communication control (spatial,
  behavioral, formations, etc.) and integrate
  within MissionLab

5
Plans as Resources

• Motivated by Paytons work.
• A precompiled map is an enabling resource.
• Maps converted to a two dimensional gradient mesh
  a priori using A.
• Robot queries internalized plan for directional
  advice in the form of a vector.
• Queries and advice production are near real-time.

6
Internalized Plan as Behavior

• The GoToMapVector assemblage controls retrieval
  of plan vectors from maps, and consists of the
  following sub-assemblages
• GetMapVector Retrieves and injects a map vector
• Wander Inject noise
• Avoid Obstacles
• MoveToGoal Only used in experiments of mixed
  reactive/planning behavior.

7
Parallel Internalized Plans

• Different internalized plans can be combined by
  fusing individual plans.
• Base plan contains only physical objects.
• Other plans contain additional constraints.
• The robot queries advice from the most
  constrained plan (pessimistic).

8
Serial Internalized Plans

• Different internalized plans are used one after
  another.
• Each plan offers situation specific advice.
• Perceptual triggers transition from only plan to
  another.
• Opportunity for contingency plans.

9
(No Transcript)
10
Initial Results

• Additional resources in the form of internalized
  plans aids team communication.
• No difference results when using reactive
  behaviors vs. communication insensitive plans.
• Communication planning in serial and parallel
  result in significant improvement in
  communication.

11
Plans as Resources Upcoming work

• Conduct tests on teams of real robots.
• Determine the systems localization and map
  accuracy requirements.
• Develop techniques for dealing with localization
  errors and map inaccuracies.
• Extend the planning to 3D and generalize to other
  space-time dimensions for multi-robot coordination

12
Communication-sensitive Team Behaviors

• Generation and testing of a new set of reactive
  communications preserving and recovery behaviors
• Creation of communications recovery and
  preserving behaviors sensitive to QoS
• Expansion of behaviors in support of
  line-of-sight and subterranean operations

13
Communications Recovery Behaviors

• Retrotraverse Log robots position at regular
  intervals when comms breaks, move to last N
  positions logged until comms recovered
• Move to Higher Ground Use inclinometer data to
  guide ascent to vantage point for communications
  recovery
• Nearest Neighbor Track the last known position
  of connected robots if comms lost, move towards
  the nearest robots last position
• Bridging Couple separated networks by tracking
  positions and moving towards location of network
  lesion currently UAV behavior
• Shepherding Search out robots that have been cut
  off from the network once found, guide back
  (currently UAV)

14
(No Transcript)
15
Experimental Design

• Missions run on simulated Quantico map
• 20 trials starting at regularly spaced intervals
  along the western side of the map and moving to a
  central location on the eastern side of the map
• 2 UGVs moving in a line formation with 20m
  spacing
• Recovery behaviors used in isolation of one
  another
• Metrics Mission Completion Rate, Recovery time

16
Results
Using the Nearest Neighbor Recovery behavior
approximately 50 of the trials were finished
completely autonomously Retrotraverse and Move to
Higher Ground were usually not able to finish the
trials autonomously by themselves and will
require transitions/planning once communications
recovered
17
Results (2)
Retrotraverse results in the most rapid
communications recovery of the behaviors
tested. Move to higher ground results in the
slowest recovery rate, largely due to failure
when the terrain was level. Nearest Neighbor was
successful in most cases, except in some
situations around buildings where the attraction
to the lost robot and the repulsion to the
building that severed communications causes a
local minima
18
Summary Communications Recovery

• Retrotraverse provides the most rapid
  communications recovery
• Retrotraverse must be augmented with
  supplementary behaviors or teleoperation to
  complete mission
• Move to Higher Ground and Nearest Neighbor
  perform effectively in many cases
• There are a number of cases where the behavior
  will perform suboptimally
• Supplementary behaviors or a more complex
  behavioral selection may further improve results

19
Future Work

• Investigate means in which to activate recovery
  behaviors based on available perceptual features
• Integration of cognizant failure (Gat) for
  recovery behaviors
• Evaluate performance of recovery behaviors in the
  context of larger teams, increased formation
  size, and disparate goals

20
Communication-Preserving Behaviors with Limited
Memory

• Value-Based One-Step Look-Ahead
• Uses predictions of communication quality short
  distances from current position to hill-climb
  to better locations with respect to communication
• Currently assumes teammates remain still when
  predicting communication quality to reduce
  complexity

21
Communication-Preserving Behaviors

• Operation
• Predict communication quality at locations a
  small distance away using
• Map information
• Network attenuation model
• Teammates assumed to remain still
• Create motion vector based on predicted and
  current communication quality
• Bearing based on predicted quality
• Magnitude based on current quality

22
Communication-Preserving Behaviors
Predicted communication qualities
(r .89)
Resulting vector
X X
X X
(r .70)
(r .85)
(r .74)
Current communication quality
(r .68)
23
Communication-Preserving Behaviors
Without Look-Ahead Behavior
Obstacle-splitting endangers communication quality
24
Communication-Preserving Behaviors
With Look-Ahead Behavior
Obstacle-splitting phenomena eliminated
25
Communication-Preserving Behaviors 1 step

• Future work
• Extend behavior to larger groups
• Perform quantitative tests
• Compare to other communication-preserving
  behaviors
• Identify situations where most effective
• Integrate into larger scenarios

26
Memoryless Communication Preserving
BehaviorMaintain-Signal-Strength

• Servos on signal strength to preserve
  communication.
• Sum over every connected robot
• Vector_Magnitude (T-R)/T when (T-R) gt D
• Vector_Direction angle to the robot
• where T Target Signal Strength, D Signal
  Deadzone, R Actual Signal strength
• Connected can be defined to mean either directly
  connected or connected via a multi-hop route.

27
Illustration of Maintain-Signal-Strength
g1
g2
Communication Quality Increases
Communication Quality Decreases
s1
s2
28
(No Transcript)
29
Communication Preservation Experiments

• Mission Each robot navigates to its goal.
• Team Sizes 2, 4, 6, and 8
• Distance separating robots 10, 20, 40 meters
• 25 random worlds
• 12 obstacle coverage
• 256 x 256 meters
• Three behaviors are compared.
• No communication behavior (control)
• MSS using positions of directly connected robots
  (single-hop)
• MSS using all available positions (multi-hop)

30
Percentage of Time as One Network

• Some communication strategy is needed to keep
  the network one as you increase the distances or
  the number of robots.

• There doesnt seem to be a significant difference
  between the two variations of the behavior.

31
Mission Completion Time

• Both variations of the behavior add a
  significant amount of time to mission completion.

32
Communication Models and Fidelity

• Working with BBN to incorporate suitable
  communication models into MissionLab in support
  of both simulation and field tests

33
Current Network Model Status

• Models wireless communication networks in
  3 dimensions.
• Integrated into MissionLab
• Signal Attenuation
• Free-space path-loss
• Dependent on distance between robots, frequency
  of communication band, and antennae height.
• Line-of-Sight Obstructions
• Absolute signal attenuation.
• Obstructions modeled as arbitrary polygons or
  right cylinders with height.
• Terrain map can be used which can occlude LOS.

34
The Quantico Overlay From a Communications
Perspective
35
Next Steps in Modeling Network

• Obstructions will attenuate signal at different
  magnitudes.
• Model buildings and foliage.
• Accurate model of signal attenuation over rough
  terrain.
• Mimic capabilities of BBN black-box
• Understand how different levels of model fidelity
  impact multi-robot team performance.

36
Communication-sensitive Mission Specification

• MissionLab is a usability-tested
  Mission-specification software developed under
  extensive DARPA funding (RTPC / UGV Demo II / TMR
  / UGCV / MARS / FCS-C programs)
• Using MissionLab as a basis
• Adapt to incorporate air-ground
  communication-sensitive command and control
  mechanisms
• Extend to support physical and simulated
  experiments for objective air and ground
  platforms
• Incorporate new communication tasks and triggers

37
MissionLabs Spatial Planner

• Incorporates Navigator Component of the AuRA
  architecture
• - A map of obstacles is read in by the system
• - The map is grown to represent configuration
  space
• - The free space is partitioned into a collection
  of convex meadows
• - Start and End points are selected by the user
• - The planner performs A search to find an
  initial path
• - The path is improved by tautening
• Can be invoked from MissionLabs cfgedit tool
• Creates an FSA series of waypoints

38
Initial Map and Meadow Map
39
Path Chosen and Formation Run
40
Technology Integration

• Conduct Early-on Demonstrations on Ground Robots
  at GT
• Provide our Hummer Command and Control Vehicle
  for Team support at Objective Demonstration

41
Interface Control Document

• To explicitly capture all aspects of all
  interconnections between project components.
• Communications protocols, frequencies, and timing
• Language and data formats
• Experimental communications fault injection
• To define new mission description language CMDL
• To detail communications-sensitive behaviors
  developed by project teams.
• Communication-preserving
• Communication-recovering

42
(Mounted in GT Hummer)
PENN ROCI
ICD Ref 2.3.2
GaTech MLab
VIP Display
ICD Ref 2.3.6 XMLRPC
ICD Ref2.3.1
ICD Ref 2.3.4
ICD Ref 2.3.7
USC Player
USC Helo
ICD Ref 2.3.8
43
GPS Jammer

• Supports evaluation of robot localization methods
  in challenging environments
• White noise centered on selected frequency
• Power 50 to 200mw (about 50-100 meters)
• Performance to be characterized in the coming few
  weeks
• Engineered by Daniel Walker (BORG Lab)

44
Summary - Georgia Tech Contributions

• Communications Sensitive Behaviors
• Preserving
• Recovery
• Communications Planning Behaviors
• Plans as Resources
• One-step planning
• Team spatial waypoint planning
• Infrastructure
• Communications models support
• MissionLab as an integration vehicle
• ICD Development lead
• Hummer base station / Test equipment
• Scenario development

45
Backup Slides
46
Plans in Serial Demo explained

• Seven plans are used in this demo