arxiv: 2604.04374 · v1 · submitted 2026-04-06 · 💻 cs.RO · cs.AI· cs.HC

Towards Considerate Human-Robot Coexistence: A Dual-Space Framework of Robot Design and Human Perception in Healthcare

Yuanchen Bai , Zijian Ding , Ruixiang Han , Niti Parikh , Wendy Ju , Angelique Taylor This is my paper

Pith reviewed 2026-05-10 20:16 UTC · model grok-4.3

classification 💻 cs.RO cs.AIcs.HC

keywords human-robot coexistencehealthcare roboticsco-designperception spacedesign spaceinterpretive dimensionsrobot integration

0 comments

The pith

Human perception and robot design in healthcare form a co-evolving loop rather than static states.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

This paper draws on follow-up interviews from a 14-week co-design study involving healthcare robots to explore how humans and robots coexist dynamically. It identifies four interpretive dimensions in the human perception space that influence how robots are understood. The core contribution is framing the interaction between this perception space and the robot design space as a co-evolving loop driven by mutual influences over time. This matters because it highlights humans' active role in interpreting and mediating robots in real-world settings rather than passive acceptance. If the framework holds, it encourages designing robots with ongoing user interpretation in mind from the beginning.

Core claim

Through in-depth interviews with nine participants in a 14-week co-design study on healthcare robots, the authors extract four interpretive dimensions in the human perception space—degree of decomposition, temporal orientation, scope of reasoning, and source of evidence. They conceptualize the mutual relationship between the human perception space and the robot design space as a co-evolving loop in which human needs, design decisions, situated interpretations, and social mediation continuously reshape one another. Building on this, they propose considerate human-robot coexistence, where humans act as interpreters and mediators shaping how robots are understood and integrated across stages.

What carries the argument

The co-evolving loop between the human perception space, defined by four interpretive dimensions, and the robot design space, through which needs, decisions, interpretations, and mediation mutually influence each other over time.

Load-bearing premise

The four interpretive dimensions extracted from nine interviews in one 14-week study represent stable and generalizable aspects of human perception across healthcare robot contexts.

What would settle it

Observing whether the same four dimensions and co-evolving loop structure emerge when applying the interview approach to a separate healthcare robot project with different participants.

Figures

Figures reproduced from arXiv: 2604.04374 by Angelique Taylor, Niti Parikh, Ruixiang Han, Wendy Ju, Yuanchen Bai, Zijian Ding.

**Figure 2.** Figure 2: Robot design and human perception space for human-robot coexistence. On the left, the robot design space captures key system-level considerations, including use scenarios, embodiment, contextual constraints, and technical feasibility. On the right, the human perception space characterizes how stakeholders interpret robots along four interpretive dimensions: degree of decomposition, temporal orientation, sc… view at source ↗

read the original abstract

The rapid advancement of robotics, spanning expanded capabilities, more intuitive interaction, and more integration into real-world workflows, is reshaping what it means for humans and robots to coexist. Beyond sharing physical space, this coexistence is increasingly characterized by organizational embeddedness, temporal evolution, social situatedness, and open-ended uncertainty. However, prior work has largely focused on static snapshots of attitudes and acceptance, offering limited insight into how perceptions form and evolve, and what active role humans play in shaping coexistence as a dynamic process. We address these gaps through in-depth follow-up interviews with nine participants from a 14-week co-design study on healthcare robots. We identify the human perception space, including four interpretive dimensions (i.e., degree of decomposition, temporal orientation, scope of reasoning, and source of evidence). We enrich the conceptual framework of human-robot coexistence by conceptualizing the mutual relationship between the human perception space and the robot design space as a co-evolving loop, in which human needs, design decisions, situated interpretations, and social mediation continuously reshape one another over time. Building on this, we propose considerate human-robot coexistence, arguing that humans act not only as design contributors but also as interpreters and mediators who actively shape how robots are understood and integrated across deployment stages.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

The paper pulls four perception dimensions and a co-evolving loop idea from nine interviews in one 14-week healthcare robot co-design study, but the small sample leaves generalizability thin.

read the letter

The core contribution is a qualitative framework that treats human perception of robots and robot design as a mutual, time-evolving process rather than a one-way acceptance snapshot. From follow-up interviews, the authors extract four dimensions—degree of decomposition, temporal orientation, scope of reasoning, and source of evidence—and use them to describe a loop where needs, decisions, interpretations, and social factors keep reshaping each other. This moves the conversation past static metrics toward something more dynamic, which is useful for thinking about long-term deployment in healthcare settings.

Referee Report

3 major / 2 minor

Summary. The paper claims that follow-up interviews with nine participants from a 14-week healthcare-robot co-design study reveal a human perception space characterized by four interpretive dimensions (degree of decomposition, temporal orientation, scope of reasoning, and source of evidence). It enriches human-robot coexistence frameworks by modeling the relationship between this perception space and the robot design space as a co-evolving loop in which human needs, design decisions, situated interpretations, and social mediation continuously reshape one another, and proposes the notion of considerate human-robot coexistence in which humans actively serve as interpreters and mediators across deployment stages.

Significance. If the central claims hold, the work offers a valuable conceptual shift from static snapshots of robot acceptance toward a dynamic, mutual-influence model of coexistence. This could inform more adaptive robot design practices in healthcare by emphasizing ongoing human interpretation and social mediation. The qualitative grounding from a co-design study provides concrete interpretive dimensions that may serve as a starting point for future empirical work, though the manuscript does not yet demonstrate reproducibility or broader validation.

major comments (3)

[Results / Interview Analysis] The section describing the interview analysis and derivation of the four interpretive dimensions: no details are provided on the coding process, inter-coder reliability, participant selection criteria, or how the dimensions were systematically extracted from the nine follow-up interviews. This information is load-bearing for the co-evolving loop claim, as the framework is built directly from these observations.
[Framework Development / Discussion] The conceptualization of the co-evolving loop (human needs, design decisions, situated interpretations, and social mediation): the manuscript presents this as a continuous mutual reshaping but supplies no concrete temporal evidence or examples from the 14-week study showing iterative dynamics, leaving open whether the loop is observed or inferred post hoc.
[Implications / Conclusion] The claim that the four dimensions capture stable, generalizable features of human perception: the single 14-week study with nine participants provides limited basis for asserting applicability across different healthcare robot deployments and user groups, without explicit discussion of study-specific confounds such as the co-design setting or social mediation effects.

minor comments (2)

[Introduction / Framework] Define the terms 'human perception space' and 'robot design space' more explicitly at first use, including their boundaries and how they differ from prior constructs in the HRI literature.
[Framework Development] Consider adding a diagram that visually depicts the co-evolving loop and its four elements to improve conceptual clarity for readers.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We thank the referee for the constructive and insightful comments, which help clarify the methodological foundations and scope of our claims. We address each major point below and will incorporate revisions to enhance transparency and precision without overstating the study's reach.

read point-by-point responses

Referee: The section describing the interview analysis and derivation of the four interpretive dimensions: no details are provided on the coding process, inter-coder reliability, participant selection criteria, or how the dimensions were systematically extracted from the nine follow-up interviews. This information is load-bearing for the co-evolving loop claim, as the framework is built directly from these observations.

Authors: We agree that the current manuscript lacks sufficient methodological detail on the qualitative analysis. In the revised version, we will expand the relevant section to describe participant selection criteria (drawn from the original 14-week co-design cohort based on engagement levels and availability), the inductive thematic coding process used to identify patterns across interviews, and the systematic mapping of data excerpts to the four dimensions. We will also note any inter-coder procedures employed and include illustrative quotes to show the derivation. This addition will make the construction of the human perception space explicit and reproducible in principle. revision: yes
Referee: The conceptualization of the co-evolving loop (human needs, design decisions, situated interpretations, and social mediation): the manuscript presents this as a continuous mutual reshaping but supplies no concrete temporal evidence or examples from the 14-week study showing iterative dynamics, leaving open whether the loop is observed or inferred post hoc.

Authors: The co-evolving loop is presented as a conceptual model synthesized from patterns observed in the co-design process and participants' retrospective accounts of how needs and interpretations shifted over the 14 weeks. While the study provides longitudinal context through its duration and follow-up interviews, it does not contain exhaustive real-time tracking of multiple full iteration cycles. In revision, we will add specific examples drawn from the study timeline (e.g., how early design decisions prompted changes in temporal orientation that fed back into subsequent mediation discussions) and clarify that the loop represents an interpretive framework informed by the data rather than a strictly observed empirical sequence. If additional examples cannot be extracted without speculation, we will explicitly label the model as theoretically derived. revision: partial
Referee: The claim that the four dimensions capture stable, generalizable features of human perception: the single 14-week study with nine participants provides limited basis for asserting applicability across different healthcare robot deployments and user groups, without explicit discussion of study-specific confounds such as the co-design setting or social mediation effects.

Authors: We accept that the single-study, small-sample design precludes strong assertions of stability or broad generalizability. The revised manuscript will moderate language in the Implications and Conclusion sections, explicitly discuss study-specific factors (including the co-design context potentially amplifying interpretive engagement and social mediation), and reframe the four dimensions as a preliminary, context-informed starting point for future empirical validation across varied healthcare settings and populations. A new limitations paragraph will be added to the Discussion to address these boundaries directly. revision: yes

Circularity Check

0 steps flagged

No circularity: framework inductively derived from interview data

full rationale

The paper extracts four interpretive dimensions and conceptualizes the co-evolving loop between human perception space and robot design space directly from follow-up interviews with nine participants in a single 14-week co-design study. No equations, parameter fitting, self-definitional reductions, or load-bearing self-citations appear in the provided text; the central claims are presented as an enrichment based on observed patterns rather than tautological redefinitions or predictions forced by the inputs themselves. The derivation remains self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 2 invented entities

The paper introduces new conceptual constructs without external validation or formal definitions; it relies on the assumption that qualitative data from a small sample can ground a general framework.

axioms (1)

domain assumption Human perceptions of robots can be reliably categorized into four interpretive dimensions from interview transcripts.
Invoked when the authors distill the dimensions from the nine interviews without reporting inter-rater reliability or alternative categorizations.

invented entities (2)

Human perception space no independent evidence
purpose: To organize the four interpretive dimensions as a distinct conceptual domain.
New construct introduced to contrast with the robot design space.
Considerate human-robot coexistence no independent evidence
purpose: To name the proposed dynamic relationship in which humans act as interpreters and mediators.
New term and framing presented as the outcome of the dual-space model.

pith-pipeline@v0.9.0 · 5546 in / 1396 out tokens · 30201 ms · 2026-05-10T20:16:21.653800+00:00 · methodology

discussion (0)

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

IndisputableMonolith/Foundation/AbsoluteFloorClosure.lean reality_from_one_distinction unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

We identify the human perception space including four interpretive dimensions (i.e., degree of decomposition, temporal orientation, scope of reasoning, and source of evidence). We enrich the conceptual framework of human–robot coexistence by conceptualizing the mutual relationship between the human perception space and the robot design space as a co-evolving loop
IndisputableMonolith/Foundation/ArrowOfTime.lean arrow_from_z unclear

?

unclear
Relation between the paper passage and the cited Recognition theorem.

co-evolving loop in which human needs, design decisions, situated interpretations, and social mediation continuously reshape one another over time

What do these tags mean?

matches: The paper's claim is directly supported by a theorem in the formal canon.
supports: The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends: The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses: The paper appears to rely on the theorem as machinery.
contradicts: The paper's claim conflicts with a theorem or certificate in the canon.
unclear: Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

19 extracted references · 19 canonical work pages · 1 internal anchor

[1]

Agent AI: Surveying the Horizons of Multimodal Interaction

Z. Durante, Q. Huang, N. Wake, R. Gong, J. S. Park, B. Sarkar, R. Taori, Y . Noda, D. Terzopoulos, Y . Choiet al., “Agent ai: Surveying the horizons of multimodal interaction,”arXiv preprint arXiv:2401.03568, 2024

work page internal anchor Pith review arXiv 2024
[2]

Extracting robotic task plan from natural language instruction using bert and syntactic dependency parser,

S. Lu, J. Berger, and J. Schilp, “Extracting robotic task plan from natural language instruction using bert and syntactic dependency parser,” in2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN). IEEE, 2023, pp. 1794–1799

work page 2023
[3]

Generative expressive robot behaviors using large language models,

K. Mahadevan, J. Chien, N. Brown, Z. Xu, C. Parada, F. Xia, A. Zeng, L. Takayama, and D. Sadigh, “Generative expressive robot behaviors using large language models,” inProceedings of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, 2024, pp. 482– 491

work page 2024
[4]

Towards consider- ate embodied ai: Co-designing situated multi-site healthcare robots from abstract concepts to high-fidelity prototypes,

Y . Bai, R. Han, N. Parikh, W. Ju, and A. Taylor, “Towards consider- ate embodied ai: Co-designing situated multi-site healthcare robots from abstract concepts to high-fidelity prototypes,”arXiv preprint arXiv:2602.03054, 2026

work page arXiv 2026
[5]

Usage, definition, and measurement of coexistence, tolerance and acceptance in wildlife conservation research in africa,

J. Knox, K. Ruppert, B. Frank, C. C. Sponarski, and J. A. Glikman, “Usage, definition, and measurement of coexistence, tolerance and acceptance in wildlife conservation research in africa,”Ambio, vol. 50, no. 2, pp. 301–313, 2021

work page 2021
[6]

Coexistence of species competing for shared resources,

R. A. Armstrong and R. McGehee, “Coexistence of species competing for shared resources,”Theoretical population biology, vol. 9, no. 3, pp. 317–328, 1976

work page 1976
[7]

Chesson’s coexistence theory,

G. Barab ´as, R. D’Andrea, and S. M. Stump, “Chesson’s coexistence theory,”Ecological monographs, vol. 88, no. 3, pp. 277–303, 2018

work page 2018
[8]

Plant coexistence and the niche,

J. Silvertown, “Plant coexistence and the niche,”Trends in Ecology & evolution, vol. 19, no. 11, pp. 605–611, 2004

work page 2004
[9]

Toward a theory of coexistence in shared social- ecological systems: the case of cook inlet salmon fisheries,

P. A. Loring, “Toward a theory of coexistence in shared social- ecological systems: the case of cook inlet salmon fisheries,”Human Ecology, vol. 44, no. 2, pp. 153–165, 2016

work page 2016
[10]

Human-robot coexistence and interaction in open industrial cells,

E. Magrini, F. Ferraguti, A. J. Ronga, F. Pini, A. De Luca, and F. Leali, “Human-robot coexistence and interaction in open industrial cells,” Robotics and Computer-Integrated Manufacturing, vol. 61, p. 101846, 2020

work page 2020
[11]

Real-time motion control of robotic manipulators for safe human–robot coexistence,

K. Merckaert, B. Convens, C.-j. Wu, A. Roncone, M. M. Nicotra, and B. Vanderborght, “Real-time motion control of robotic manipulators for safe human–robot coexistence,”Robotics and Computer-Integrated Manufacturing, vol. 73, p. 102223, 2022

work page 2022
[12]

Human-aware social navigation with comfort space for mobile robots in human–robot coexistence environments,

Y . Zhang, W. Guan, G. Tian, C.-H. Zhang, G. Zhao, and C. Hua, “Human-aware social navigation with comfort space for mobile robots in human–robot coexistence environments,”IEEE Transactions on Computational Social Systems, 2025

work page 2025
[13]

Designing human-robot coexistence space,

J. Zhi, L.-F. Yu, and J.-M. Lien, “Designing human-robot coexistence space,”IEEE Robotics and Automation Letters, vol. 6, no. 4, pp. 7161– 7168, 2021

work page 2021
[14]

Human-robot teaming field deployments: A comparison between verbal and non-verbal communication,

T. Tanjim, P. Ekpo, H. Cao, J. S. George, K. Ching, H. R. Lee, and A. Taylor, “Human-robot teaming field deployments: A comparison between verbal and non-verbal communication,” in2025 34th IEEE International Conference on Robot and Human Interactive Communi- cation (RO-MAN). IEEE, 2025, pp. 1699–1704

work page 2025
[15]

Situating robots in the emergency department,

A. Taylor, S. Matsumoto, and L. D. Riek, “Situating robots in the emergency department,” inAAAI Spring Symposium on Applied AI in Healthcare: Safety, Community, and the Environment, 2020

work page 2020
[16]

Teaming up with robots: Analysing potential and challenges with healthcare workers and defining teamwork,

A. M. Abrams, L. Plum, and A. M. Rosenthal-von der P ¨utten, “Teaming up with robots: Analysing potential and challenges with healthcare workers and defining teamwork,”Computers in Human Behavior: Artificial Humans, vol. 4, p. 100136, 2025

work page 2025
[17]

Attitudes toward artificial intelligence and robots in healthcare in the general population: a qualitative study,

P. Smoła, I. Mło ´zniak, M. Wojcieszko, U. Zwierczyk, M. Kobryn, E. Rzepecka, and M. Duplaga, “Attitudes toward artificial intelligence and robots in healthcare in the general population: a qualitative study,” Frontiers in Digital Health, vol. 7, p. 1458685, 2025

work page 2025
[18]

Thematic analysis,

V . Clarke and V . Braun, “Thematic analysis,”The journal of positive psychology, vol. 12, no. 3, pp. 297–298, 2017

work page 2017
[19]

Understanding human-robot teamwork in the wild: The difference between success and failure for mobile robots in hospitals,

K. T. Eriksen and L. Bodenhagen, “Understanding human-robot teamwork in the wild: The difference between success and failure for mobile robots in hospitals,” in2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO- MAN). IEEE, 2023, pp. 277–284

work page 2023