cs.ROFeb 17, 2026
SaveRobot-Assisted Social Dining as a White Glove Service
Organizations: Robotics University of Michigan Ann Arbor, Michigan, USA · Leiden University Leiden, Netherlands
Abstract
Robot-assisted feeding enables people with disabilities who require assistance eating to enjoy a meal independently and with dignity. However, existing systems have only been tested in-lab or in-home, leaving in-the-wild social dining contexts (e.g., restaurants) largely unexplored. Designing a robot for such contexts presents unique challenges, such as dynamic and unsupervised dining environments that a robot needs to account for and respond to. Through speculative participatory design with people with disabilities, supported by semi-structured interviews and a custom AI-based visual storyboarding tool, we uncovered ideal scenarios for in-the-wild social dining. Our key insight suggests that such systems should: embody the principles of a white glove service where the robot (1) supports multimodal inputs and unobtrusive outputs; (2) has contextually sensitive social behavior and prioritizes the user; (3) has expanded roles beyond feeding; (4) adapts to other relationships at the dining table. Our work has implications for in-the-wild and group contexts of robot-assisted feeding.
Figures & tables
Figure 1. Examples of two Storyboards and their corresponding Moments created using Speak2Scene by P2 (left) and P3 (right). Participant-created storyboards and moments This figure captures P2 and P3's storyboards and moments that are created using Speak2Scene tool.
| ID | Age | Gender | Race | Self-described Disability | Assistance Type | Occupation | Chosen Scenario |
| P1 | 35–44 | Female | White | Quadriplegic | Full Meal | N/A | Family dinner |
| P2 | 65–74 | Female | White | Osteoarthritis; Shoulder Injury | Cutting/Meal Prep | Respiratory Therapist | Brunch w/ friends |
| P3 | 55–64 | Female | White | Spinal Muscular Atrophy | Full Meal | Social Worker; ED at Non-Profit | Business meal |
| P4 | 55–64 | Female | Mixed | Parkinson’s/Partial Paralysis | Full Meal | Remote Therapist | Business meal |
| P5 † | 35–44 | Female | White | Intention Tremors (Hand/Body) | Full Meal | N/A | Brunch w/ friends |
| P6 | 25–34 | Male | White | Multiple Sclerosis | Cutting/Drinking | Accountant | Business meal |
Table 1. Study participant demographics. All participants had experience using Assistive Technology (i.e., technology assisting with motor tasks) and reported dining in public spaces 1–5 times per month. Study Participant Demographics This table summarizes participant demographics, including age, gender, race, self-described disability, required assistance during dining, occupation, chosen scenario for the storyboard, and assistive technology use. It shows that participants varied widely in age, included both female/male, all used some form of assistive technology, and all reported to dine in public spaces approximately 1–5 times per month.
Figure 2. Study Setup. The study was conducted either at the university or at the participant’s home with the same set-up. Study Setup This illustration is a graphic portraying the study setup. There is a table with a monitor displaying Speak2Scene, the AI-based storyboarding tool, and a second computer displaying the slides. There is a microphone to capture participants' ideas. There are two additional seats for the two researchers to sit and be involved in the study.
Figure 3. Procedure of the design study included: (1) introducing the task to the participant, (2) creating an avatar based on their lived experience to be represented in the task, (3) creating a storyboard of a generic experience of dining at a restaurant, (4) zooming into 9 key moments (indicated in blue), (5) creating an imagined robot character, and (6) exit interviews to supplement participant’s design process. During steps (3) and (4), participants self-reflected to supplement their images. Procedure for design study The figure is a flow diagram titled “Speculative Design Task”. It illustrates six main steps in a participatory design activity, using icons, labels, and arrows to show the sequence. The steps are as follows: (1) Introduction of Task/Scenario – a researcher introduces the task or scenario to a participant (who has a disability); (2) Avatar Creation – the participant creates an avatar or character on a computer; (3) Storyboard Creation – six storyboard panels are created (which include, Greeting, Robot, Menu + Order, Eating, Drinking, and Payment. Each panel includes space for an image and text. Participants reflect after creating an image for each panel; (4) Moments Creation – a participant chooses from a List of 9 Moments (Learn about you, Waiting for Food, Conversations, Utensils, Serving food to yourself, Communication from the robot, Passing objects, Gestures of care, and Sharing food). Each moment has its own template card with space for an image and description; (5) Robot Character Creation – the participant designs a robot character (represented by an icon of a robotic arm on a screen); (6) Exit Interview – the researcher and participant engage in a final interview and reflection. Arrows connect the steps in order, showing progression from introduction, avatar and storyboard creation, moment detailing, robot character design, and ending with the exit interview.
Figure 4. Iteration of robot during speculative design. The caption captures the prompt by participant to create scenes.
Figure 5. Participants’ viewpoints on the Interaction Ecology in Robot-Assisted Social Dining described in Section 5.1 . Further details can be seen in Table 2 , 3 , and 4 in Appendix B Communication pathways in robot-assisted dining. The figure maps communication pathways among the user, the robot, and others (such as dining companions, caregivers, or staff). Four categories of interaction are shown with colored clusters and example participant quotes and they are as follows: (1) Robot-to-user communication (orange): via lights, haptics, beeps, voice, or screen, including minimal feedback or pre-action signaling; (2) User-to-robot communication (purple): input modalities ranging from least to most subtle, including voice, laptop/tablet, written/typed text, wand, buttons, tapping, head movements, eye gaze, finger pad, mouth joystick, and neural interfaces; (3) Others-to-robot communication (pink): caregivers may help correct robot errors or assist others; (4) Robot-to-others communication (green): engaging kids, introducing itself to others, signaling staff, or participating in conversation. Each pathway is illustrated with clustered keywords/codes and direct quotes from participants, highlighting preferences, disagreements, and envisioned interaction designs.
Figure 6. Participants’ perspective on context-sensitive robot behavior in social dining was generally in agreement. The four images within this figure were created by the participants using Speak2Scene , where each image captures some ideas. Further details can be seen in Appendix B . Participant feedback on context-sensitive robot behavior in social dining This illustration is an image summarizing some of participants perspectives. They are grouped into various sub-themes that are mentioned in Section~\ref{RQ2-results}. The subthemes are: (1) fade into background, (2) robot's social behavior includes performing shared table activities, (3) personality needs to be versatile and adaptable, (4) robot is contextually aware and reciprocates, and (5) pre-programming. In this diagram, some of these subthemes are further divided and there are specific participant quotes that are supporting them.
Figure 7. Participants’ standpoints on robot role. Top row shows their perspectives on robot role during mealtime and bottom row shows their perspectives outside of mealtime . The right-most section shows the robot requirements that are applicable for during and outside of mealtime. Rules synthesizing “dos” and “don’ts” are captured in the yellow boxes on the borders. See Appendix B for additional details. Participants’ standpoints on robot role This illustration summarizes participants' perspectives on robot role. They are grouped into three categories: (1) during mealtime, (2) outside of mealtime, and (3) during & outside of mealtime. Under the first category (during), there are two subthemes: (a) self-serve and (b) sharing and passing. Under the second category (outside), there are two subthemes: (a) support with navigation and (b) payment. Under the third category (during & outside), there is a miscellaneous subtheme. Each subtheme has several supporting participant quotes.
Figure 8. Speculative robot ideas by participants. Example speculative robot ideas generated by participants The figure presents three illustrations of how some participants imagined the robot’s appearance: (1) Left (P4): A mechanical looking robot arm. And the caption reads,
P3 imagines the robot to be mechanical.'' (2) Middle (P6): A bright, colorful robot arm is shown in orange and teal stripes. It has cartoon-like eyes, a playful snake-like shape, and wears a red bowtie. And the caption reads, P6 imagines the robot to be colorful, fun, and with a bowtie.'' (3) Right (P2): A gray robotic arm with a round head features a smiley face. Two indicator lights—one red and one green—are above the eyes. And, the caption reads, ``P2 imagines the robot to have a smiley face with lights.'' Together, the images highlight how some participants envisioned robot appearances differently, ranging from utilitarian and discreet to playful and expressive.Appendix figures & tables6 assets
Supplementary material from the paper’s appendix.
Appendix
Figure 9. Thematic Analysis Codes
| P. ID | R U | U R | R O | O R | |||||||||||||||||||
| lights | haptics | beeps | voice | screen | neural | mouth joy. | finger pad | tapping | eye gaze | buttons | head move. | wand | tablet | written | controller | voice | engage kids | intro others | signal staff | part of convo | correct | help | |
| P1 | ✓ | ✓ | – | – | – | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✓ | ✗ | ✗ | – | ✗ | – | ✗ |
| P2 | ✓ | – | – | ✓ | – | – | – | – | – | – | ✓ | – | – | – | ✓ | – | ✓ | ✗ | ✓ | ✓ | ✗ | – | ✗ |
| P3 | ✓ | ✓ | ✗ | ✗ | ✗ | ✓ | ✓ | ✓ | ✗ | ✓ | – | ✓ | – | ✓ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ | ✗ |
| P4 | ✓ | – | – | ✓ | ✓ | ✓ | ✓ | – | – | – | – | – | ✓ | ✓ | – | ✓ | ✓ | ✗ | ✗ | – | ✗ | ✓ | ✗ |
| P5 | – | – | – | ✓ | ✓ | ✗ | – | – | – | – | – | – | – | ✓ | ✓ | – | ✓ | ✓ | ✓ | – | ✓ | – | ✓ |
Table 2. Participant responses for user/robot/others communications. “✓” indicates that the participant prefers that modality, “✗” indicates that the participant does not prefer that modality, and “–” indicates either the participant did not have an opinion about the modality or was not brought up during the study. Participant responses for user/robot/others communications This table captures the participant preferences for if they envision robot-to-user, user-to-robot, robot-to-others, and others-to-robot communications to take place.
| Lbl. | P. ID | Sub-theme | Task | Agree? | Quote |
| A | P3 | R U | haptics | ✓ | "it has…pulsing mode or…vibration mode…make it go off in three pulses" |
| B | P1 | R U | haptics | ✓ | "I could just feel it start working or start…vibrating" |
| C | P4 | R U | voice | ✗ | "If the robot is confused and doesn’t understand the command, the robot could say to the person: ‘please explain’ or ‘I don’t understand’…" |
| D | P5 | R U | voice | ✗ | "I would want the robot to introduce itself with a name and ask me…what my name is" |
| E | P6 | O R | correct errors | ✗ | "[caregiver can] maybe correct the robot…or maybe better interpret the directive to the robot" |
| F | P6 | O R | help others | ✗ | "I would want it to be able to assist everyone around me and myself" |
Table 3. Participants’ perspectives on interaction ecology in robot-assisted social dining (Part 1). “R” indicates robot, “U” indicates user, and “O” indicates others (dining companions, staff, caregiver). “✓” indicates agreement and “✗” indicates disagreement. Participant quotes reflecting perspectives on interaction ecology in robot-assisted social dining.
| Lbl. | P. ID | Sub-theme | Task | Agree? | Quote |
| O | P4 | U R | neural interface | ✗ | "You could have…an AI chip that is interactive, that’s more intuitive…with thoughts" |
| P | P3 | U R | finger pad | ✗ | "Maybe a finger pad that doesn’t take a lot of physical movement" |
| Q | P4 | U R | wand | ✗ | "I envision the robot taking my instructions either verbal commands or type commands or perhaps through a wand" |
| R | P2 | U R | written/typed | ✗ | "[I would] even [pass] a note if [robot] could read and understand…visualize…something that wouldn’t interrupt the meeting" |
| S | P2 | U R | voice | ✗ | "I would ask my robot if he would mind cutting my food, my meat for me" |
| T | P2 | U R | buttons | ✗ | "I would…push button…for help" |
Table 4. Participants’ perspectives on interaction ecology in robot-assisted social dining (Part 2). “R” indicates robot, “U” indicates user, and “O” indicates others (dining companions, staff, caregiver). “✓” indicates agreement and “✗” indicates disagreement.
| Lbl. | P. ID | Sub-theme | Quote |
| A | P5 | fade into the background | "[Robot looks] as normal as possible" |
| B | P4 | fade into the background | "[Robot] would be…just a piece of adaptive equipment and…not…participating in the conversation or really…a discussion topic" |
| C | P2 | fade into the background | "I don’t want [the robot] to draw a lot of attention." |
| D | P5 | social etiquette | (When getting food from shareable dish): "The robot should say to Megan why don’t you go ahead and get some, then I’ll help and get some food" |
| E | P3 | support, but not initiate, in shared table practices | "[Robot] would…be small and inconspicuous not taking up a lot of space around me or interfering in the space of my dining companions" |
| F | P5 | personality needs to be versatile and adaptable | "Jackie, Megan and I are in the restaurant, the robot just introduced herself as Claire." |
Table 5. Participants’ perspectives on context-sensitive robot behavior in social dining Participant thoughts on context-sensitive robot behavior in social dining This table captures participant quotes supporting different subthemes that are highlighted in Section~\ref{RQ2-results}. The subthemes are: (1) fade into the background, (2) social etiquette, (3) help, but not initiate, in shared table practices, (4) personality needs to be versatile and adaptable, (5) pre-programming, (6) assess the user + check in, (7) moving across space, and (8) aware of surroundings.
| Lbl. | P. ID | Sub-theme | Robot Role | Quote |
| A | P4 | During Mealtime | self-serve | "If it is a computer menu like on a tablet and the person is disabled and they don’t feel comfortable with technology, maybe the robot could work the tablet for the person [to order]" |
| B | P2 | During Mealtime | self-serve | When ordering, "I might forget if I can’t see the menu very well so if the robot has a repeat button maybe where [it] could read back what we finalized that would help me" |
| C | P5 | During Mealtime | self-serve | "I tell the robot: will you please help me look at the menu and help me figure out what I want to eat at the restaurant because it’s all vegan here and its gonna be hard for me to decide" |
| D | P5 | During & Outside Mealtime | – | "I [ask] the robot, would you please get my medicine out and help me to put it in my mouth so I don’t drop it on the floor" |
| E | P4 | During Mealtime | sharing & passing | "waiter brings a shared dish but I can’t reach so I wonder if…your [robot arm] is either an extension or it’s folded where you can open it and reach further…I might also need [robot] to pass it around" |
| F | P1 | During Mealtime | sharing & passing | "I ask one of my family members to pass the appetizers to me and then have my robot hand grasp one of the items" |
Table 6. Participants’ viewpoints on robot’s role during and outside of mealtime Participant thoughts on robot role during and outside of mealtime This table captures participants' thoughts on robot role during and outside of mealtime. There are participant quotes that support different subthemes (during mealtime, outside of mealtime, and during+outside of mealtime) and various robot roles (self-serve, sharing & passing, support with navigation, payment, and miscellaneous).
More in this topic
Assistive Robotics
Assistive robotics develops robots and wearable devices that support mobility, daily activities, rehabilitation, and care.
See all 199 papers