illah nourbakhsh | cmu robotics institute principles of human-robot interaction guest lecture

Illah Nourbakhsh | CMU Robotics Institute

Principles of Human-Robot Interaction

Guest Lecture

Illah Nourbakhsh | CMU Robotics Institute

1. Interaction and Design

Illah Nourbakhsh | CMU Robotics Institute | HRI Summer Course


Defining Interaction


Ancestry of Interaction Studies

Barnlund

p. 7: the Assumptive World

p. 8: context as all-important



Barnlund



Terry Winograd’s trajectory an an example



Barnlund



p. 9: superiority of interaction


Formalizing Interaction

Barnlund

p. 10: Communication as Change


Pitfalls for Interactive Communication

Barnlund, p.12 ..

verbal – nonverbal discrepancy

attitude of infallibility

manipulative purpose

one-way communication

threatening context

evaluative context


The Delight of Radical Surprise


Influence

Technology People


Influence

People Technology


Breakthroughs

“Teamwork is hard especially with varying levels of skill and different personalities…can be rewarding only through compromise.”

“Make active decisions. Have the attitude that if I don’t do it, no one will and remember that if you choose something, you are also choosing not to do other things because you have limited time, energy, etc. Choose what to do with your talents wisely and don’t waste them!”


The Robot Design Challenge


Dourish

• Robot interface – later in this slide set

• Embodiment/situatedness– Hide-and-seek– Embodiment deleterious example?

• Brooks and embodiment-architecture– “Use the world as its own best model”– Philosophy ; Descartes vs. Heidegger?


Evolving Toward Physical Interaction

• Text-based computer interaction• narrow; single-threaded & synchronous; symbolic

• Graphical computer interaction

• parallel/peripheral; somewhat asynchronous; visual

metaphor

• Animate but sessile robot

• multimodal; more asynchronous/episodic;

palpable/continuous


Animate but sessile...


Social Mobile Robot

• Invasive: shared physical space• extended interaction context: the human

social-physical frame• social communication as a co-habitant• incidental & opportunistic interaction•

• Asynchronous; episodic• demands intentional transparency• active communication acts•


Social mobile robot...


Points of Departure

• Mobile robots are unlike standard computers• More like independent agents; less human augmentation

• Computers can represent real things; robots are real things

• Robots push back on the world

• Mobile robots differ from standard physical artifacts

• “…uncertainty, randomness, free will or independence so

strikingly absent in well-designed machines” – Grey Walter

• Invasive in human social space

• Need to reflect or externalize their internal states and intentions


High-level Goal

• Effective and pleasurable social interaction using embodied agents that share our space


Challenges in Social Robotics

• Perception & Representation• Perceptual competency for spatial and social context

• Locomotion & Manipulation• Physical competency, expressiveness, terrainability

• Behavior & Communication• Social competency, deliberation and interaction in

social spaces using time, intention, perceptual action


Motivation

• Rich, effective, satisfying interactions


The ‘Wicked Problem’* in HRC

Problem Identification Every solution exposes new aspects of the

problem.

Satisficing There is no clear stopping criterion nor right or

wrong.

Uniqueness Each problem is embedded in a distinct physical

and social context making its solution totally novel.

*Horst Rittel


Tools for HRC

1. The Science & Technology of Interaction modeling, reasoning, execution

perception, actuation

2. Physical and Interaction Design morphology, behavior

3. Evaluation: HCI, Human Factors, Education formative & summative techniques


DiSalvo: formalizing Product

<read pp. 10 -18>

Four dimensions:

Materiality

Expression

Function

Form



Materiality



Expression – Tatsuya Matsui



Expression



Expression

"Today, we are using technology to further an agenda of destruction and violence, which is why—more than ever—we need to rethink its role in our society and make sure that it is only used to better humanity. By creating Posy, I hope to unleash a weapon of peace—a reminder that one small robot's step is a giant leap toward a peaceful and equitable future for all."

—Tatsuya Matsui



Function


DiSalvo: formalizing ProductForm as organization of all other dimensions


Pearl: example & discussion


Projects

• Insect Telepresence: HCI formal techniques

• Chips in museums: informal learning assessment

• Grace: human tests and drama; perception

• USAR: urban search and rescue

• Mobot: long-term historical experiment


Insect Telepresence

Educational telepresence designed using formal HCI inquiry tools.


Insect Telepresence Robot

• Problem• Increase visitors’ engagement with and

appreciation of insects in a museum terrarium at CMNH.

• Approach• Provide a scalar telepresence experience with

insect-safe visual browsing • Apply HCI techniques to design and evaluate the

input device and system• Cultural modeling, expert interview, baseline observation

• Measure engagement indirectly by ‘time on task’• Partner with HCII, CMNH



• Innovations• Asymmetric exhibit layout• Mechanical transparency• Clutched gantry lever arm• FOV-relative 3 DOF joystick



• Evaluation Results:• Average group size: 3• Average age of users: 19.5 years• Three age modes: 8 years, 10 years, and 35

years• Average time on task of all users: 60 seconds• Average time on task of a single user: 27

seconds• Average time on task for user groups: 93

seconds


Insect Telepresence

Time on Task: from 15 seconds to 5 minutes


Robots in Museums

Educational tours in public spaces.


• Visitor observation• Robot observation• Demographic analysis• Knowledge tests• .5 .9 All dinosaurs lived during same

period.• .5 .7 All dinosaurs were huge animals.• .5 .8 Other animals lived on the Earth with

din.• .4 .8 All dinosaurs were carnivorous.• .4 .7 Scientists agree how to assemble

bones.• .4 .5 All bones in Dinosaur hall are real.

Robots in Museums


Evolving museum robots

• Human attention and expectation

• Body pose and verbal attitude


HRC Insights

• Reliable public deployments are possible

• Iterative design cycle is essential• Diagnostic, interaction transparency• Two-way interaction is preferable

• Human learning in human-robot collaborations can be quantified.

• Rich robotic interaction can trigger human behavioral change.


A Human-Scale Museum Edubot

• Problem• Increase visitors’ engagement and • learning at secondary exhibits in• Dinosaur Hall.

• Approach• Lead visitors to secondary exhibits and new facts• Design a robot to share the human social space• Establish long-term iterative testing over years, not

days• Time on task, observation and learning evaluations • Partner with Magic Lantern, Maya, CMNH


Museum Edubot: Technical Contributions• Required Robot

Competencies:• Safety, navigation, longevity

• Approaches• Property-based control

programming• Visual landmark-based SUF

(Latombe)• Visual self-docking• h/w and s/w restart diagnostics• Fault detection & communication


Museum Edubot: Technical Contributions• Required Robot

Competencies:• Safety, navigation, longevity

• Outcome• Zero human injuries• 4 years deployment, over 500 km

traversed• MTBF converging beyond 1 week• Uptime: 98%• Active diagnosis approaching

100%


Museum Edubot: Iterative Design Cycle• Design Refinements

• Physical Design– Morphological Transparency: designing

informative form

• Interaction Design– Behavioral Transparency: affective

interaction model– Shortened length of media segments– Two-way interaction, goal-based

learning


Human-scale InteractionGrange, Meyer, Soto, Kunz, Willeke

Educational tours in public spaces.


Interaction Design Process

• Educational design: education division• Content development: production

company• Behavior specification: education

division• Formative evaluations and re-design• robot observation, human observation• interviews, written tests


Robot Components

• Nomadic XR-4000 base• Pentium-scale running

Linux• Vision, ultrasonic, ir, tactile• 8 lead-acid deep-cycle

batteries– 12V, ~25AH each– ~ 5 hrs endurance

• Customized interaction “top”– LCD + DVD media system– Interaction button(s)– High-quality speaker system


Chips

• Carnegie Museum of Natural History• Autonomy

– 5 years, > 500 km navigated, auto-docking

– MTBF convergence at 1 week– Proactive health state identification


Chips - BBC


Sweetlips

• Hall of North American Wildlife

• 3 years, > 185 km navigated

• Tour theme interaction


Joe Historybot• Heinz History Center• 2 years, > 160 km• Touchscreen, quiz,

speech generation


Adam 40-80

• Free-agent robot for hire• More than 30 days of

work finished– Republican National Conv.– Democratic National Conv.

illah nourbakhsh | cmu robotics institute principles of human-robot interaction guest lecture

Documents

allimportant slide

design slide

change slide

robot design challenge

assumptive world

sessile robot multimodal

active decisions

dont waste