Experiments in Implicit Control

1
Experiments in Implicit Control

• Katia P. Sycara
• School of Computer Science
• Carnegie Mellon University
• Michael Lewis
• School of Information Sciences
• University of Pittsburgh

2
Outline

• Agent Roles Functions
• Implicit Control
• Examples from our work
• Slippery Motion in VR
• Path planning for a military coordination task
• Robot control for urban search rescue (in
  progress)

3
Don Normans 7 stages of Action Agents can
assist anywhere in this loop
Secretary scheduler
eSnipe bidder
Spam filter
4
Problems in Human-Machine Interaction

• Synchronous Commands
• Asynchronous Commands
• Implicit Commands

• Difficult for long sequences or many parameters
  ex composing complex queries, setting up
  spreadsheet
• Difficult for long sequences or branching ex
  programming languages
• Difficult due to ambiguity ex plan recognition

5
Implicit Control as a special case

• Direct correspondence between interaction with
  automation the domain
• User directly performs some analog of task
• Restrictive, recognizable, repeatable
  automation subtasks
• Automated subtask is unique precise
• Means for unambiguous communication of intent
• Initiating conditions unique distinctive

6
Design Pattern

• User expresses intent by acting upon domain
  (imprecisely or failing to account for full range
  of constraints)
• Agent infers intent and elaborates action
• (do what I mean)
• Agent elaborated action is more consistent with
  users intent than original action

7
Collision Handling in VR

• Non-augmenting strategies
• Clunk- collide stop
• Ghost- collide pass through
• Implicit control (many possible)
• Slip- collide redirect

8
SLIP moves the actor along surfaces rather than
into them
9
The Baffles Maze
10
Implicit Control was faster
11
MokSAF Deliberative Planning

• Agents
• have access to digital information in the
  infosphere
• cannot consider intangible objectives which are
  not part of that digital infosphere
• Humans
• Understand Idiosyncratic and situation-specific
  factors
• local politics, non-quantified information,
  complex or vaguely specified mission objectives
• Dynamically changing situations
• Information, obstacles, enemy actions
• Problem
• To share and combine human and agent information
  and resources

12
Route Planning in MokSAF

• Control
• Autonomus
• Cooperative

13
Path Length, Route Times, and Fuel Usage were
uniformly better for Aided Teams
Route Times
Path Length
14
Errors in Vehicle Choice session 2
13
12
11
10
Errors
9
8
7
6
Cooperative
Autonomous
Control
15
MokSAF Implicit Control

• Augmentation improved path planning
• But
• Implicit control of the Cooperative RPA
• (elaborated user action rather than responding to
  commands) improved overall Task performance (path
  vehicle selection)

16
Robots in Urban Search Rescue (USAR)

• Earthquakes, fires, war, or terrorism can leave
  human victims trapped in unstable structures
  hidden within rubble
• Robotic Searchers are
• Expendable
• Can reach otherwise inaccessible areas
• Heightened sensory capabilities FLIR, Acoustic,
  Ladar, chemical
• Problems
• Expense
• Locomotion over irregular terrain
• Perceptual limitations

17
NISTs Urban Search Rescue Reference
Tasks(from Jacoff et al. 2003)

• Yellow Region
• Simple to traverse, no agility requirements
• Planar (2-D) maze
• Isolates sensors with obstacles/targets
• Reconfigurable in real time to test mapping
• Orange Region
• More difficult to traverse, variable floorings
• Spatial (3-D) maze, stairs, ramp, holes
• Similarly reconfigurable
• Red Region
• Difficult to traverse, unstructured environment
• Simulated rubble piles, shifting floors
• Problematic junk (rebar, plastic bags, pipes)

18
Orange Yellow Arenas from Jacoff et al. 2003
19
Human Factors Challenges

• World through a straw (restricted FOV)
• Camera control for search/navigation (Hughes
  Lewis, HFES 2002)
• Survey knowledge (mapping environment) from
  restricted FOV impeded movement
• Visual smearing from close surfaces
• unfamiliar ground level perspective
• Difficult distance judgments from degraded 2D
  image
• Difficult orientation judgments from visual cues
  in disorderly environment
• Difficult locomotion due to out-of-view
  negative obstacles

20
Orange Arena Simulation(January-February 2003)

• ProEngineer solid model converted to Unreal
  format
• Digital photographs used to create textures to be
  applied to the model
• Glass, mirrors, orange safety fencing, and other
  special effects added
• Rubble, debris, and victim models added to
  simulation
• Robot characteristics adapted from Karma vehicle
  class

21
Simulation of Orange Arena
22
Orange Arena Platform photo simulation
23
First generation interface(runs with both Corky
simulation)
24

• Robot interface demo

25
Implicit Control for teleoperation

• Hidden obstacle avoidance/safeguarding
• Camera control attention direction
• Automated scanning/scene reconstruction

26
END
27
Corky in real life simulation
28
Manual (naïve) path
29
Autonomous Agent with Constraints
Road
Building
Teammates route
Freeway
Soil
Rendezvous Point
River
Forest
Commanders route
Start Point
Constraint
30
Cooperative (hi-liter) Agent