pith. sign in

arxiv: 2008.03496 · v1 · pith:SNKYRY2Qnew · submitted 2020-08-08 · 💻 cs.AI · cs.LO· cs.RO

Human Robot Collaborative Assembly Planning: An Answer Set Programming Approach

Momina Rizwan , Volkan Patoglu , Esra Erdem This is my paper

Pith reviewed 2026-05-24 14:12 UTC · model grok-4.3

classification 💻 cs.AI cs.LOcs.RO
keywords answer set programmingcollaborative assembly planninghuman-robot collaborationconditional planningcommonsense reasoninguncertainty handlingfurniture assembly
0
0 comments X

The pith

Answer set programming lets a robot plan assembly steps with a human while handling uncertainty through conditional actions and communication.

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

The paper presents a method that encodes collaborative assembly planning as an answer set program. This encoding combines hybrid conditional planning with commonsense reasoning and a set of communication actions so the robot can act even when it has incomplete knowledge of the human partner's next moves. The authors demonstrate the approach on a bi-manual Baxter robot assembling furniture together with a human. If the encoding works as described, it supplies both high-level task ordering and geometric feasibility checks while keeping the collaboration safe under uncertainty. A sympathetic reader would care because real-world human-robot teams need exactly these capabilities to move beyond scripted sequences.

Core claim

The central claim is that answer set programming can represent hybrid conditional planning extended with commonsense reasoning and communication actions, thereby solving collaborative assembly tasks under uncertainty about human behavior; the authors illustrate this by encoding the domain for a Baxter robot that assembles furniture with a human teammate.

What carries the argument

Hybrid conditional planning extended with commonsense reasoning and communication actions, encoded directly as an answer set program.

If this is right

  • The robot can interleave its own actions with sensing and communication to reduce uncertainty about the human.
  • Geometric feasibility checks are integrated into the same planning process that handles conditional branches.
  • The same encoding supports a rich set of communication acts that keep the human informed during the assembly.
  • The method applies directly to the demonstrated furniture assembly domain without requiring separate planners for each subproblem.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The same ASP encoding style could be reused for other manipulation domains that mix discrete task choices with continuous geometric constraints.
  • If the communication actions are made bidirectional, the approach might support mutual adaptation where the human also adjusts to the robot's uncertainty.
  • Extending the commonsense rules to include fatigue or distraction models would allow the planner to insert more frequent safety checks.

Load-bearing premise

The answer set program encoding is expressive enough to capture the relevant uncertainty in human behavior and to produce usable plans in real time during physical assembly.

What would settle it

Run the Baxter robot on the furniture task and observe whether it generates safe collaborative sequences when the human deviates from expected behaviors in ways not covered by the commonsense rules.

Figures

Figures reproduced from arXiv: 2008.03496 by Esra Erdem, Momina Rizwan, Volkan Patoglu.

Figure 1
Figure 1. Figure 1: (a) Some part of a hybrid conditional plan computed for (b) a human-robot collaborative [PITH_FULL_IMAGE:figures/full_fig_p004_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Collaborative table assembly with a volunteer [PITH_FULL_IMAGE:figures/full_fig_p011_2.png] view at source ↗
read the original abstract

For planning an assembly of a product from a given set of parts, robots necessitate certain cognitive skills: high-level planning is needed to decide the order of actuation actions, while geometric reasoning is needed to check the feasibility of these actions. For collaborative assembly tasks with humans, robots require further cognitive capabilities, such as commonsense reasoning, sensing, and communication skills, not only to cope with the uncertainty caused by incomplete knowledge about the humans' behaviors but also to ensure safer collaborations. We propose a novel method for collaborative assembly planning under uncertainty, that utilizes hybrid conditional planning extended with commonsense reasoning and a rich set of communication actions for collaborative tasks. Our method is based on answer set programming. We show the applicability of our approach in a real-world assembly domain, where a bi-manual Baxter robot collaborates with a human teammate to assemble furniture. This manuscript is under consideration for acceptance in TPLP.

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.

Referee Report

1 major / 2 minor

Summary. The manuscript proposes an ASP-based approach to hybrid conditional planning for human-robot collaborative assembly under uncertainty. It extends standard conditional planning with commonsense reasoning and a rich set of communication actions to manage incomplete knowledge of human behavior. Applicability is shown via a physical demonstration in which a bi-manual Baxter robot assembles furniture with a human teammate.

Significance. If the encoding is sound, the work provides a declarative logic-programming framework that unifies high-level planning, geometric feasibility, sensing, and communication within a single ASP program; this is a useful application of stable-model semantics to robotics and is of direct interest to TPLP readers. The manuscript correctly credits the use of choice rules and non-deterministic fluents for modeling uncertainty. The stress-test concern that the ASP encoding cannot capture human uncertainty does not appear in the manuscript; the approach employs standard ASP mechanisms for this purpose. The demonstration remains qualitative, however, so claims of practical effectiveness rest on a single illustrative case rather than comparative or quantitative evidence.

major comments (1)
  1. [§5] §5 (Demonstration): the claim that the method supports 'effective real-time collaboration' rests on a single qualitative assembly sequence; no planning times, number of stable models generated, success rate across uncertainty scenarios, or comparison against a baseline planner is reported. This information is load-bearing for the applicability argument.
minor comments (2)
  1. [§3] Notation for the communication actions (e.g., the predicates used for human responses) is introduced without an explicit table or grammar; a compact listing would improve readability.
  2. [§2] The manuscript cites prior ASP planning work but does not discuss how the present encoding differs from existing hybrid planners such as those based on PDDL or other ASP robotics encodings; a short related-work paragraph would help situate the contribution.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for the positive summary and recommendation of minor revision. We address the single major comment below.

read point-by-point responses

  1. Referee: [§5] §5 (Demonstration): the claim that the method supports 'effective real-time collaboration' rests on a single qualitative assembly sequence; no planning times, number of stable models generated, success rate across uncertainty scenarios, or comparison against a baseline planner is reported. This information is load-bearing for the applicability argument.

    Authors: We agree that the demonstration in §5 is a single qualitative sequence and that quantitative metrics would strengthen the applicability claims. In revision we will report the ASP solver planning times and number of stable models generated for the scenarios shown. A multi-scenario success-rate study and baseline comparison are not present because the experiments were designed to illustrate integration of commonsense reasoning and communication actions rather than to benchmark performance; adding them would require new experiments outside the scope of the current declarative-framework contribution. revision: partial

Circularity Check

0 steps flagged

No significant circularity detected

full rationale

The paper proposes an application of established answer set programming (ASP) techniques to hybrid conditional planning for human-robot collaborative assembly under uncertainty, with extensions for commonsense reasoning and communication actions. The central claim rests on this declarative encoding and its demonstration in a Baxter robot domain, without any equations, fitted parameters, or derivations that reduce by construction to the paper's own inputs. No self-definitional steps, self-citation load-bearing premises, or renamed known results are present; the method is a standard use of ASP for planning with domain-specific extensions, rendering the derivation self-contained.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

No free parameters or new entities are introduced; the work relies on standard assumptions from answer set programming and planning literature.

axioms (2)
  • domain assumption Answer set programming can be used to model planning problems with uncertainty via conditional planning.
    This is the foundation of the hybrid approach.
  • domain assumption Commonsense reasoning about human behavior can be represented using ASP rules.
    Required for extending the planning with commonsense.

pith-pipeline@v0.9.0 · 5687 in / 1205 out tokens · 31786 ms · 2026-05-24T14:12:14.058973+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

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

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

18 extracted references · 18 canonical work pages

  1. [1]

    write newline

    " write newline "" before.all 'output.state := FUNCTION article output.bibitem format.authors "author" output.check author format.key output output.year.check new.block format.title "title" output.check new.block crossref missing format.jour.vol output format.article.crossref output.nonnull format.pages output if new.block note output fin.entry FUNCTION b...

    work page

  2. [2]

    , Kreinovich, V

    Baral, C. , Kreinovich, V. , and Trejo, R. 1999. Computational complexity of planning and approximate planning in presence of incompleteness. In International Joint Conference on Artificial Intelligence . 948--955

    work page 1999

  3. [3]

    , Eiter, T

    Brewka, G. , Eiter, T. , and Truszczynski, M. 2016. Answer set programming: An introduction to the special issue. AI Magazine\/ 37,\/ 3, 5--6

    work page 2016

  4. [4]

    , Ianni, G

    Eiter, T. , Ianni, G. , Schindlauer, R. , and Tompits, H. 2005. A Uniform Integration of Higher-Order Reasoning and External Evaluations in Answer-Set Programming . In International Joint Conference on Artificial Intelligence . 90--96

    work page 2005

  5. [5]

    , Petrick, R

    Giuliani, M. , Petrick, R. , Foster, M. E. , Gaschler, A. , Isard, A. , Pateraki, M. , and Sigalas, M. 2013. Comparing task-based and socially intelligent behaviour in a robot bartender. In ACM on International Conference on Multimodal Interaction . 263--270

    work page 2013

  6. [6]

    Grigore, E. C. and Scassellati, B. 2016. Constructing policies for supportive behaviors and communicative actions in human-robot teaming. In ACM/IEEE International Conference on Human-Robot Interaction . 615--616

    work page 2016

  7. [7]

    and Frazzoli, E

    Karaman, S. and Frazzoli, E. 2011. Sampling-based algorithms for optimal motion planning. The International Journal of Robotics Research\/ 30,\/ 7, 846--894

    work page 2011

  8. [8]

    , Banks, C

    Kim, J. , Banks, C. J. , and Shah, J. A. 2017. Collaborative planning with encoding of users' high-level strategies. In AAAI . 955--962

    work page 2017

  9. [9]

    Lasota, P. A. and Shah, J. A. 2015. Analyzing the effects of human-aware motion planning on close-proximity human--robot collaboration. Human factors\/ 57,\/ 1, 21--33

    work page 2015

  10. [10]

    Peot, M. A. and Smith, D. E. 1992. Conditional nonlinear planning. In Artificial Intelligence Planning Systems . Elsevier, 189--197

    work page 1992

  11. [11]

    Petrick, R. P. and Foster, M. E. 2013. Planning for social interaction in a robot bartender domain. In International Conference on Automated Planning and Scheduling

    work page 2013

  12. [12]

    and Collins, G

    Pryor, L. and Collins, G. 1996. Planning for contingencies: A decision-based approach. Journal of Artificial Intelligence Research\/ 4 , 287--339

    work page 1996

  13. [13]

    , Lallement, R

    Sebastiani, E. , Lallement, R. , Alami, R. , and Iocchi, L. 2017. Dealing with on-line human-robot negotiations in hierarchical agent-based task planner. In International Conference on Automated Planning and Scheduling

    work page 2017

  14. [14]

    S ucan, I. A. , Moll, M. , and Kavraki, L. E. 2012. The O pen M otion P lanning L ibrary. IEEE Robotics and Automation Magazine\/ 19,\/ 4, 72--82

    work page 2012

  15. [15]

    , Knepper, R

    Tellex, S. , Knepper, R. A. , Li, A. , Rus, D. , and Roy, N. 2014. Asking for help using inverse semantics. In Robotics Science and Systems

    work page 2014

  16. [16]

    Unhelkar, V. V. , Siu, H. C. , and Shah, J. A. 2014. Comparative performance of human and mobile robotic assistants in collaborative fetch-and-deliver tasks. In ACM/IEEE International Conference on Human-Robot Interaction . 82--89

    work page 2014

  17. [17]

    Warren, D. H. D. 1976. Generating conditional plans and programs. In Summer Conference on Artificial Intelligence and Simulation of Behaviour . 344--354

    work page 1976

  18. [18]

    Yalciner, I. F. , Nouman, A. , Patoglu, V. , and Erdem, E. 2017. Hybrid conditional planning using answer set programming. Theory and Practice of Logic Programming\/ 17,\/ 5-6, 1027--1047

    work page 2017