Proactive Release Behaviors During Human-Robot Handovers Zhao Han, - - PowerPoint PPT Presentation

▶
proactive release behaviors
SMART_READER_LITE
LIVE PREVIEW

Proactive Release Behaviors During Human-Robot Handovers Zhao Han, - - PowerPoint PPT Presentation

Dec 31, 2022 615 likes •772 views

The Effects of Proactive Release Behaviors During Human-Robot Handovers Zhao Han, Holly Yanco University of Massachusetts Lowell UMass Lowell Human-Robot Interaction Lab University of Massachusetts Lowell robotics.cs.uml.edu www.uml.edu

slide-1
SLIDE 1

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

The Effects of Proactive Release Behaviors During Human-Robot Handovers

Zhao Han, Holly Yanco

University of Massachusetts Lowell

slide-2
SLIDE 2

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Robot to Human Handover

  • Focus on release
  • In all conditions:

– Natural arm movement – Gazes at the object1,2 – Grasps the top part of the object3 – Arm is extended as much as possible3

  • 1. Moon et al., 2014
  • 2. Admoni et al, 2014
  • 3. Cakmak et al., 2011
slide-3
SLIDE 3

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Robot to Human Handover

  • Focus on release
  • In all conditions:

– Natural arm movement – Gazes at the object1,2 – Grasps the top part of the object3 – Arm is extended as much as possible3

  • 1. Moon et al., 2014
  • 2. Admoni et al, 2014
  • 3. Cakmak et al., 2011
slide-4
SLIDE 4

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Motivation

  • Three phases during a handover1
  • Transfer phase is vital

– Failure has severe consequences

  • Dropped and broken2, which may hurt people
  • Bad experience3

– Least studied

Approach Signal Transfer

  • 1. Strabala et al., 2013
  • 2. Chan et al., 2013
  • 3. Cakmak et al, 2011
slide-5
SLIDE 5

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Three Release Behaviors

  • Rigid

– Release when arm is extended – By checking a force threshold

  • Passive

– Can be released after partial extension – By checking the same force threshold

  • Proactive

– Can be released after partial extension – By checking a force change pattern

slide-6
SLIDE 6

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Proactive Release

  • Sample force pattern during a grasp
  • Implementation: moving average

– 90 windows of averaged data – 1 window: 180 voltage values – Release when 35% is decreasing

Time Voltage (force)

slide-7
SLIDE 7

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Methodology

  • Within subjects
  • Full counterbalancing
  • 36 participants

– 21 male, 15 female – Age ranged from 18 to 57 (M=29, SD=12)

  • Data collection

– Task completion time: logged – Additional timing: coding videos frame by frame – Subjective measures: Likert scale questionnaire

slide-8
SLIDE 8

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Preference

  • Among 29 participants who explicitly

stated a single preference, 20 participants preferred proactive.

slide-9
SLIDE 9

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Handover Efficiency

  • Completion time (one second less in proactive)
  • Release duration

1.3 vs 1.2 vs 0.5 (seconds) (rigid vs passive vs proactive)

M indicates median.

slide-10
SLIDE 10

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Overall Experience Improved

  • Significant differences

– Fluency (*) – Ease-of-taking (***)

  • Trends

– Trust (p=0.05) – Capability (p=0.06)

  • No detectable difference

– Discomfort

slide-11
SLIDE 11

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Why is Proactive Better?

  • To take the object

– People don’t need to pull – They simply hold or touch

  • People grasp differently in different trials

– The fixed force threshold is not flexible – The decreasing pattern is still present

slide-12
SLIDE 12

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Takeaways

Threshold-based approaches

  • Inefficient
  • Bad experience

Proactive release

  • Preferred
  • Increased fluency and

ease-of-taking

“It lets it go like humans do” “The robot won’t let it go” “Less resistant” “Very smooth” “Had to pull” “Difficult”

slide-13
SLIDE 13

UMass Lowell Human-Robot Interaction Lab robotics.cs.uml.edu University of Massachusetts Lowell www.uml.edu

Thanks!

  • Zhao Han: zhan@cs.uml.edu
  • UMass Lowell HRI Lab: robotics.cs.uml.edu
  • Code: github.com/uml-robotics/handover_moveit
  • The Effects of Proactive Release Behaviors

During Human-Robot Handovers