ensuring the safety of an autonomous robot in interaction ...a ‘map’ of robotics for anthropic...

Machine Learning in Robot Assisted Therapy

Challenges and Considerations

Stefan Walke

[email protected]

SS 2018

Ensuring the Safety of an Autonomous Robot in Interaction with Children

mailto:[email protected]

Chair of Robotics, Artificial Intelligence and Embedded Systems

Overview

1

Physical SafetyMental

UnharmednessProposed Guidelines

Future Work


Pushing the lower boundary• Many talks on how to improve therapy:

• Add features• Improve therapy logic and reactions→ Pushing the upper limit of success

• Safety Considerations:• Remove or hold back new features• Decrease chance of physical or mental harm→ Improving the lower boundary

• Problem: When is a system “safe”?

• Minimizing False Negatives

2

Ther

apy

Succ

ess

Time

Danger

+ -

Ass

ess

men

t

+ True Positive False Positive

- False Negative True Negative


Ensuring Physical Safety

3

Source: Interaction Design Foundation – 2016


Ensuring Physical Safety

• We can use general human robot interaction as a baseline

• Adjusting for:

• Decreased experience of cause-effect chains

• Increased curiosity

• Lower pain threshold

• Different reaction to unforeseen situation

• Increased possibility of permanent trauma

4


Compliant Robots

• A compliant actuator allows deviations from its equilibrium position, depending applied external forces:

• Spring-type actuators

• Hydraulic-type actuators

• Tendon-type actuators

• Example: Variable Stiffness Actuator [1]

• Real-time control of reference position and mechanical impedance

• Two motors that run in opposite directions vary the tension

• Main shaft experiences different dampening

5

Perspective view of the Variable Stiffness Actuator. The transmission belt 1 connects the DC Motors pulleys 2-3 to the joint shaft 4, and it is tensioned by passive elastic elements 5-6-7 [1]

Practical Implementation of the Stiffness variation [1]


Soft Tissue & Artificial Skin

• The Idea of wrapping the robot skeleton in soft material

• This has multiple advantages:

• More life-like feel

• Dampen contact force

• Include sensors to stop movement in case of contact

• Other sensors (heart rate, pulse oximeter, etc)

• Soft material allows covering up joints in contrast to stiff material

6

Source: TUM – 2015

Source: Carnegie Mellon University, Soft Robotics and Bionics Lab


An atlas of physical human–robot interaction [2]

7

A ‘map’ of robotics for anthropic domains: main issues and superposition for pHRI [2]



Problems in the approach:

• Current Research is separated in two areas (CS and ME)

• Often no interaction (feed forward control)

• Danger of false mental Model (especially with children)

• Difficulty of defining Injury Guidelines in High DoF Systems

General/Basic Safety Rules:

• No sharp edges to reduce risk of lacerations

• Lightweight but stiff materials to reduce inertia

• Visco-elastic coatings or compliant actuators to dampen impacts

8



• Injury* is not a good metric for safe interaction:

• Actuators:

• Do not allow active Impact by monitoring space

• Speed and precision vs Safety Trade-off

• Variable-impedance actuation and Distributed macro-mini actuation

• Control:• Unstructured anthropic domains → no detailed description of the environment

• Real-time motion planning

• Impedance control

9

AIS score Severity Type

0 None None

1 Minor Superficial

2 Moderate Recoverable

3 Serious Possibly recoverable

… … …

*There is some research into pain tolerance, but as that varies widely from person to person and especially children it is not easy to define [3]


Mental Unharmedness

10

Source: AI won't just make us better at our jobs - they'll make us better humans, too. (Reuters/Francois Lenoir)


The Problem with Mental Unharmedness

• Hard to measure how well child is responding

→ Reduce features:

• Not concerned about disinterest or distraction

• Focus on fear, stress and wish to stop

• Often the first indicators are very subtle and might not be notice

• Very difficult topic, therefore we pick one special case:

Automated detection and classification of positive vs negative robot interactions with children with autism using distance based features [4]

11


Experiment Setup

• Participants:

• 8 children with ASD from 5 families

• 5-10 years of age (min. 2 years on communication subscale)

• In a room with robot and a parent for 3 x 5min

• Learning phase (get all functions explained)

• No protocol, child can do what it wants

• Room has one camera, Robot has IR emitters for orientation

• Background subtraction used to find child and parent (differentiate by shirt color)

12

The humanoid robot used in the experiment [4]


Robot Behaviour & Child State Classes

Robot (one contingent behaviour session and one random behaviour session)

• Child approaches/retreats → happy/sad (will approach child if further than 1m away)

• Button pushed or child talks → blow bubbles and spin

• Will try to face child, except if child is behind → ignore

• Parent is only an obstacle

Child

• Avoiding/Retreating

• Interaction with robot or bubbles

• Still (not near parent or wall)

• Near parent (not interacting)

• Near wall

13

Capture of the camera with participant and robot marked by algorithm [4]


Positive vs. Negative Robot Interactions

• Expert classification of states and overall positivity

• Previous approach used a heuristic measure to determine state

→ Only about 85% accuracy

14

Percentage of session time spent in each interaction state [4]


Results

• Classifier with 8-dimensional feature vector:

𝑣 = (𝑑𝑐𝑟 , 𝑑𝑐

𝑝, 𝑑𝑐

𝑤 , 𝜑𝑐𝑟 , 𝑣𝑐 , 𝑣𝑐

𝑟 , 𝑣𝑐𝑤 , 𝜑𝑐

𝑟𝑣𝑐𝑟)

• Trained with human labeled data

• A Gaussian Mixture Model was used as a Classifier

• Overall 91.4% accuracy in state recognition

• Real-time feasible (classification time below camera framerate)

15

avoidance interaction parent wall

avoidance 52.8 0.8 1.4 2.6

interaction 34.8 97.5 7.6 11.5

parent 9.9 1.5 90.8 3.7

wall 2.5 0.2 0.2 82.2


How to build a safe system – Proposal

• Build Systems Bottom up:

• Add one feature ( hardware or software ) at a time

• Minimize error before expanding

• This reduces error propagation and eliminates unforeseen interactions

• Guidelines for features:

• Needs graceful exit

• Needs to be adaptable and online learning enabled

• Should have provable functionality ( see functional programming)

16


The Data Problem – Future Work

• Huge problem of getting enough data with (autistic) children

• Main hindrance are ethical and medical concerns, unlikely to decrease

→ Problem will probably persist for quite a while

• Potential Fix: Simulation

• Simulating physical interaction is easy in principle

• For emotional interactions there are large amount of classifiers

• Use classifiers as generators

• Develop a framework that can simulate emotional states and corresponding gesture

17


Questions

?18


Sources[1] Design and Control of a Variable Stiffness Actuator for Safe and Fast Physical Human/Robot

Interaction G. Tonietti, R. Schiavi, A. Bicchi - 2005

[2] An atlas of physical human-robot interaction A. De Santis, et al. - 2007

[3] A Failure-to-Safety ‘Kyozon’ System with Simple Contact Detection and Stop Capabilities for Safe Human-Autonomous Robot CoexistenceK. Suita, H. Ikeda, et al. - 1995

[4] Automated detection and classification of positive vs negative robot interactions with children with autism using distance based featuresD. Feil-Seifer, M. J. Matari´c - 2011

19

ensuring the safety of an autonomous robot in interaction ...a ‘map’ of robotics for anthropic...

Documents