Social Robot Navigation
description
Transcript of Social Robot Navigation
![Page 1: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/1.jpg)
SOCIAL ROBOT NAVIGATION
Rachel Kirby
Committee:Reid Simmons, Co-ChairJodi Forlizzi, Co-ChairIllah NourbakhshHenrik Christensen (GA Tech)
![Page 2: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/2.jpg)
2
How should robots react around people? In hospitals, office buildings, etc.
Motivation
![Page 3: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/3.jpg)
3
Typical reaction: treat people as obstacles Don’t yield to oncoming people Stop and block people while recalculating
paths Collide with people if they move
unexpectedly
Motivation
This is the current state of the art!(studied by Mutlu and Forlizzi 2008)
![Page 4: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/4.jpg)
4
How do people react around people? Social conventions
Respect personal space Tend to one side of hallways Yield right-of-way
Common Ground (Clark 1996) Shared knowledge Can this be applied to a social robot?
Motivation
![Page 5: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/5.jpg)
5
Human social conventions for movement can be represented as a set of mathematical cost
functions. Robots that navigate according to these
cost functions are interpreted by people as being socially
correct.
Thesis Statement
![Page 6: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/6.jpg)
6
1. COMPANION framework2. Social navigation in hallways3. Companion robot4. Joint human-robot social navigation
Contributions
![Page 7: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/7.jpg)
7
Related Work Thesis Contributions Limitations and Future Work Conclusions
Outline
![Page 8: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/8.jpg)
8
Related Work Human navigation Robot navigation Social robots
Thesis Contributions Limitations and Future Work Conclusions
Outline
![Page 9: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/9.jpg)
9
Social conventions of walking around others Use of personal space (Hall 1966 and many others) Passing on a particular side (Whyte 1988; Bitgood and
Dukes 2006) Culturally shared conventions
Common ground (Clark 1996) Helps predict what others will do (Frith and Frith 2006)
Efficiency Minimize energy expenditure (Sparrow and Newell 1998) Minimize joint effort in collaborative tasks (Clark and
Brennan 1991)
Related Work: Human Navigation
![Page 10: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/10.jpg)
10
Local obstacle avoidance Many examples, e.g.:
Artificial Potential Fields (Khatib 1986) Vector Histograms (Borenstein and Koren 1989) Curvature Velocity Method (Simmons 1996)
Do not account for human social conventions Do not account for global goals
Global planning Random planners: RRTs (LaValle 1998) Heuristic search: A* (Hart et al. 1968)
Re-planners: D* (Stentz 1994), GAA* (Sun et al 2008)
Related work: Robot Navigation
![Page 11: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/11.jpg)
11
Specific tasks (non-generalizeable) Passing people (Olivera and Simmons 2002; Pacchierotti
et al. 2005) Standing in line (Nakauchi and Simmons 2000) Approaching groups of people (Althaus et al.
2004) Giving museum tours (Burgard et al. 1999; Thrun et
al. 1999) General navigation
Change velocity near people (Shi et al. 2008) Respect “human comfort” (Sisbot et al. 2007)
Related Work: Social Robots
![Page 12: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/12.jpg)
12
Outline Related Work Thesis Contributions
1. COMPANION framework2. Social navigation in hallways3. Companion robot4. Joint human-robot social
navigation Limitations and Future Work Conclusions
![Page 13: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/13.jpg)
13
Constraint-Optimizing Method for
Person-Acceptable NavigatION
COMPANION Framework
![Page 14: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/14.jpg)
14
1. Socially optimal global planning, not just locally reactive behaviors
2. Social behaviors represented as mathematical cost functions
COMPANION Framework
![Page 15: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/15.jpg)
15
Why global planning?
COMPANION: Global Planning
![Page 16: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/16.jpg)
16
Why global planning?
COMPANION: Global Planning
![Page 17: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/17.jpg)
17
What is global? Short-term
Between two offices on the same floor From an office to an elevator 10-20 meters
Goal is real-time search React to new sensor data Continuously generating new plans
COMPANION: Global Planning
![Page 18: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/18.jpg)
18
Heuristic planning (A*) Optimal paths Arbitrary cost function: distance plus other
constraints
COMPANION: Global Planning
),,(),,(cost 22 asscwass 1i
ii1
![Page 19: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/19.jpg)
19
Constraint: limit the allowable range of a variable Hard constraint: absolute limit Soft constraint: cost to passing a limit
Objective function “Cost” Can be optimized (maximized or
minimized) Mathematical equivalence between soft
constraints and objectives
COMPANION: Constraints
![Page 20: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/20.jpg)
20
COMPANION: Constraints1. Minimize Distance2. Static Obstacle Avoidance3. Obstacle Buffer4. People Avoidance5. Personal Space6. Robot “Personal” Space7. Pass on the Right8. Default Velocity9. Face Direction of Travel10. Inertia
![Page 21: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/21.jpg)
21
COMPANION: Constraints1. Minimize Distance2. Static Obstacle Avoidance3. Obstacle Buffer4. People Avoidance5. Personal Space6. Robot “Personal” Space7. Pass on the Right8. Default Velocity9. Face Direction of Travel10. Inertia
![Page 22: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/22.jpg)
22
Task-related: get to a goal Social aspect
Minimize energy expenditure (Sparrow and Newell 1998; Bitgood and Dukes 2006)
Take shortcuts when possible (Whyte 1988)
Cost is Euclidian distance
COMPANION: Distance
212
21221distance )..()..(),,( ysysxsxsassc
![Page 23: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/23.jpg)
23
“Bubble” of space that people try to keep around themselves and others (Hall 1966)
Changes based on walking speed (Gérin-Lajoie et al. 2005)
People keep the same space around robots (Nakauchi and Simmons 2000; Walters et al. 2005)
We model as a combination of two Gaussian functions
COMPANION: Personal Space
![Page 24: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/24.jpg)
24
Ability to side-step obstacles Not all robots can do this! Need holonomic robot
Do not walk sideways for an extended period Looks awkward (social) Kinematically expensive (task-related)
Cost relative to distance traveled sideways
COMPANION: Face Travel
|.|.),,( 21facing yvataassc
![Page 25: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/25.jpg)
25
How to combine constraints? Weighted linear combination
Range of social behavior Wide variation in human behavior Different weights yield different
“personalities”
COMPANION: Weighting Constraints
),,(),,(cost 22 asscwass 1i
ii1
![Page 26: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/26.jpg)
26
Constraint Name WeightMinimize Distance 1
Static Obstacle Avoidance
on
Obstacle Buffer 1People Avoidance onPersonal Space 2
Robot “Personal” Space 3Pass on the Right 2Default Velocity 2
Face Direction of Travel 2Inertia 2
COMPANION: Weighting Constraints
![Page 27: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/27.jpg)
27
CARMEN framework (robot control and simulation)
A* search on 8-connected grid Represent people in the state space Various techniques for improving search
speed Laser-based person-tracking system
COMPANION: Implementation
![Page 28: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/28.jpg)
28
Outline Related Work Thesis Contributions
1. COMPANION framework2. Social navigation in
hallways3. Companion robot4. Joint human-robot social
navigation Limitations and Future
Work Conclusions
![Page 29: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/29.jpg)
29
Hallway Interactions Simulations
Static paths Navigation
User study Human reactions Grace
![Page 30: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/30.jpg)
30
Hallway: Simulations Simple
environment One person
3 possible locations
3 possible speeds 3 possible goals
Left turn Right turn Straight
![Page 31: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/31.jpg)
31
Hallway: SimulationsRight turn, person on right Left turn, person on left
![Page 32: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/32.jpg)
32
What happens with different constraint weights?
Hallway: Simulations
![Page 33: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/33.jpg)
33
Hallway: Simulations
![Page 34: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/34.jpg)
34
Hallway: Simulations
Top robot point-of-view Bottom robot point-of-view
![Page 35: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/35.jpg)
35
Hallway Study Is the robot’s behavior
socially appropriate? Robot used in study: Grace Tested “social” versus “non-
social” “Social”: all defined
constraints “Non-social”: same
framework, but removed purely social conventions
![Page 36: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/36.jpg)
36
Constraint Name “Social” “Non-Social”Minimize Distance 1 1
Static Obstacle Avoidance
on on
Obstacle Buffer 1 1People Avoidance on onPersonal Space 2 0
Robot “Personal” Space
3 0
Pass on the Right 2 0Default Velocity 1 1
Face Direction of Travel
0 0
Inertia 1 1
Hallway Study: Constraints
![Page 37: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/37.jpg)
37
Hallway Study: Procedure 27 participants Within-subjects design Surveys
Affect (PANAS, SAM) General robot behavior (5
questions) Robot movement (4 questions) Free-response comments
![Page 38: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/38.jpg)
38
Hallway Study: Non-Social Example
![Page 39: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/39.jpg)
39
Hallway Study: Social Example
![Page 40: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/40.jpg)
40
Hallway Study: Results
General Behavior: p > 0.1 Robot Movement: p = 0.015 *
![Page 41: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/41.jpg)
41
Hallway Study: ResultsPersonal Space: p = 0.0003 * Move Away: p = 0.0006 *
![Page 42: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/42.jpg)
42
“I didn’t feel that the robot gave me enough space to walk on my side of the hallway.”
“The robot came much closer to me than humans usually do.”
“Robot acted like I would expect a slightly hostile/proud human (male?) to act regarding personal space—coming close to making me move without actually running into me.”
Hallway Study: “Non-Social” Comments
![Page 43: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/43.jpg)
43
“It was really cool how it got out of my way.”
“It felt like the robot went very close to the wall… which a human wouldn’t do as much (except maybe a very polite human…)”
“I felt that the robot obeyed social conventions by getting out of my way and passing me on the right. However, it seemed to turn away from me quite suddenly, which was very slightly jarring.”
Hallway Study: “Social” Comments
![Page 44: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/44.jpg)
44
“It was really cool how it got out of my way.”
“It felt like the robot went very close to the wall… which a human wouldn’t do as much (except maybe a very polite human…)”
“I felt that the robot obeyed social conventions by getting out of my way and passing me on the right. However, it seemed to turn away from me quite suddenly, which was very slightly jarring.”
Hallway Study: “Social” Comments
![Page 45: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/45.jpg)
45
“It was really cool how it got out of my way.”
“It felt like the robot went very close to the wall… which a human wouldn’t do as much (except maybe a very polite human…)”
“I felt that the robot obeyed social conventions by getting out of my way and passing me on the right. However, it seemed to turn away from me quite suddenly, which was very slightly jarring.”
Hallway Study: “Social” Comments
![Page 46: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/46.jpg)
46
“Jarring” behavior Robot turns away to yield Non-holonomic behavior
“Social” condition rated higher on social movement scale Better respected personal space Required less avoidance movements from people
No difference on other social scales Same robot both times
Even “non-social” behavior was not anti-social! Different personalities
Hallway Study: Discussion
![Page 47: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/47.jpg)
47
Simulation results COMPANION framework Flexible application of social conventions
User study Robot behaviors are interpreted according
to human social norms Ascribed personalities: “overly polite”
versus “hostile”
Hallways: Summary
![Page 48: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/48.jpg)
48
Outline Related Work Thesis contributions
1. COMPANION framework2. Social navigation in hallways3. Companion robot4. Joint human-robot social
navigation Limitations and Future Work Conclusions
![Page 49: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/49.jpg)
49
Research goal: social navigation around people
Ability to side-step obstacles Holonomic capability Necessary for social behavior
“Friendly” appearance Grace is ~6’ tall!
Companion Robot: Motivation
![Page 50: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/50.jpg)
50
Holonomic: can move sideways instantaneously
Designed primarily by Brian Kirby (staff) Capabilities
~2.0m/s maximum velocity 3-6 hours battery life Continuous acceleration 360-degree laser coverage
Companion Robot: Base
![Page 51: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/51.jpg)
51
Companion Robot: Base
![Page 52: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/52.jpg)
52
Companion Robot: Base
![Page 53: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/53.jpg)
53
Companion Robot: Shell Design criteria:
Organic shape; not a “trash can” Tall enough to travel with people,
but not intimidating Not suggestive of skills beyond
capabilities Have a face Provide orientation with distinct
front, back, and sides Iterative design process
Scott Smith, Josh Finkle, Erik Glaser
![Page 54: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/54.jpg)
54
Companion Robot: Final
![Page 55: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/55.jpg)
55
Companion Robot: Final
![Page 56: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/56.jpg)
56
Still in progress Shell: need to identify suitable fabric for
covering Base: joystick control (almost)
Motor controllers must be better tuned Higher-level control: need holonomic
localization
Companion Robot: Status
![Page 57: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/57.jpg)
57
Outline Related Work Thesis Contributions
1. COMPANION framework2. Social navigation in
hallways3. Companion robot4. Joint human-robot social
navigation Limitations and Future Work Conclusions
![Page 58: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/58.jpg)
58
What is joint planning and navigation? Joint tasks for a person and a robot Robot must stay coordinated with person
Task of side-by-side travel Nursing home assistant: escort residents
socially Smart shopping cart: stays in sight
Joint Social Navigation: Motivation
![Page 59: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/59.jpg)
59
Current robotic escorting systems require people to follow behind the robot
No regard for social conventions Not how people walk together
Joint Social Navigation: Motivation
![Page 60: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/60.jpg)
60
Extension to COMPANION framework Plan for a person to travel with the robot Common ground: robot can assume person will follow
cues Joint Goals
Desired final world state, including goals for both the robot and the person
Joint Actions Action to be taken by a robot plus action to be taken by
a person, over the same length of time Joint Constraints
Minimize joint cost for the robot and the person
Joint Social Navigation: Approach
![Page 61: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/61.jpg)
61
Constrain the relative position of robot and person
Two additional constraints: Walk with a person: keep a particular
distance Side-by-side: keep a particular angle
Balance weights with Personal Space
Joint Social Navigation: Side-by-side
![Page 62: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/62.jpg)
62
Joint Navigation: Examples
![Page 63: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/63.jpg)
63
Joint Navigation: Examples
![Page 64: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/64.jpg)
64
Extension to the COMPANION framework Joint goals Joint actions Joint constraints
Side-by-side escorting task Walk with a person constraint (distance) Side-by-side constraint (angle)
Still not real-time Huge state space to search
Joint Planning: Summary
![Page 65: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/65.jpg)
65
Related Work Thesis Contributions Limitations and Future Work Conclusions
Outline
![Page 66: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/66.jpg)
66
Real-time planning Currently only achieved at expense of
optimality Possible improvements:
Parallelization Other planners Moore’s Law
Person tracking Poor performance from current laser-based
system Improve with multi-sensor approach
Limitations
![Page 67: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/67.jpg)
67
Additional on-robot experiments More scenarios Companion versus Grace
Learning constraint weights Adding additional social conventions
Verbal/non-verbal cues Gender, age, etc.
Conventions for other cultures Additional tasks
Side-by-side following (rather than leading) Standing in line Elevator etiquette
Future Work
![Page 68: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/68.jpg)
68
Related Work Thesis Contributions Limitations and Future Work Conclusions
Outline
![Page 69: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/69.jpg)
69
Human social conventions for movement can be represented as mathematical cost functions, and robots that navigate according to these cost functions are interpreted by people as being socially correct.
Conclusion
![Page 70: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/70.jpg)
70
COMPANION framework 10 key social and task-related conventions Socially optimal global planning
Hallway navigation tasks Many results in simulation User study on the robot Grace
Companion robot Holonomic base Designed for human-robot interaction studies
Joint planning Extension to COMPANION framework Simulation results for side-by-side escorting task
Conclusion: Contributions
![Page 71: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/71.jpg)
71
Need for robots to follow human social norms
COMPANION framework produces social behavior
Foundation for future human-robot social interaction research
Conclusion: Summary
![Page 72: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/72.jpg)
72
Brian Kirby Reid Simmons, Jodi Forlizzi Suzanne Lyons-Muth, Jean Harpley, Karen Widmaier, Kristen
Schrauder, David Casillas Companion team:
Scott Smith, Josh Finkle, Erik Glaser, David Bromberg, Roni Cafri, Ben Brown, Greg Armstrong
Botrics, LLC, Advanced Motion Controlls, Outlaw Performance NSF CNS 0709077, NPRP grant from the Qatar National Research
Fund, Quality of Life Technology Center NSF Graduate Research Fellowship, NSF IGERT Graduate
Research Fellowship, NSF IIS 0329014, NSF IIS 0121426, NSF IIS 0624275
Many, many, many others
Acknowledgements
![Page 73: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/73.jpg)
73
Thanks!
![Page 74: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/74.jpg)
74
Passing an oncoming person US convention: move to the right (Bitgood
and Dukes 2006) Model as increased cost to the right-
hand side of people in environment
COMPANION: Pass on the Right
![Page 75: Social Robot Navigation](https://reader035.fdocuments.net/reader035/viewer/2022081422/5681677d550346895ddc8321/html5/thumbnails/75.jpg)
75
COMPANION: Pass on the Right