pith. sign in

arxiv: 2504.11901 · v5 · submitted 2025-04-16 · 💻 cs.RO · cs.AI

Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments

Luca Castri , Gloria Beraldo , Nicola Bellotto This is my paper

Pith reviewed 2026-05-22 20:40 UTC · model grok-4.3

classification 💻 cs.RO cs.AI
keywords causal inferencedecision makingautonomous robotsdynamic environmentshuman-robot interactionwarehouse simulationtask planning
0
0 comments X

The pith

Causal models let robots choose better task timing and strategies by estimating human obstructions and battery use in shared spaces.

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

The paper proposes a causality-based decision-making framework that reasons over a learned causal model to help autonomous robots anticipate key factors in environments shared with humans. Instead of relying on correlations, the approach models cause-and-effect links such as how people move through a space or how the robot's battery drains under different conditions. This reasoning supports choices about when to start a task and which strategy to use for completing it. The claims are tested in a warehouse-like setting using a new simulator called PeopleFlow that generates realistic human and robot trajectories based on time, layout, and robot state. The evaluation benchmarks the causal method against a non-causal baseline and concludes that the causal version produces more efficient and safer robot behavior.

Core claim

By leveraging causal inference to model cause-and-effect relationships, the framework estimates battery usage and human obstructions as factors influencing task execution and thereby assists the robot in deciding when and how to complete a given task, with the result that autonomous robots can operate more efficiently and safely in dynamic environments shared with humans.

What carries the argument

The causality-based decision-making framework that reasons over a learned causal model of environmental factors to support choices on task timing and strategy.

If this is right

  • Robots can anticipate critical environmental factors more reliably than with correlation-only methods.
  • Better decisions on task timing and strategy follow directly from the causal estimates of obstructions and battery drain.
  • The PeopleFlow simulator enables systematic benchmarking of interaction-aware planning in large-scale shared workspaces.
  • Overall robot operation becomes more efficient and safer when causal reasoning replaces purely reactive or statistical approaches.

Where Pith is reading between the lines

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

  • The same causal structure could be applied to other shared spaces such as hospitals or retail floors without major redesign.
  • Updating the causal model online from live sensor data might allow the robot to adapt when human movement patterns change over a shift.
  • Integrating the framework with existing path-planning algorithms could create a two-layer system where causal reasoning sets high-level timing and geometry handles low-level motion.

Load-bearing premise

The learned causal model accurately captures the true cause-and-effect relationships for factors like battery usage and human obstructions in the shared workspace.

What would settle it

In repeated runs of the PeopleFlow simulator or in a physical warehouse test, the robot using the causal framework shows no improvement in task completion time, energy use, or collision avoidance compared with the non-causal baseline.

Figures

Figures reproduced from arXiv: 2504.11901 by Gloria Beraldo, Luca Castri, Nicola Bellotto.

Figure 1
Figure 1. Figure 1: A mobile robot reasoning on the causal model of human spatial behaviours in a warehouse environment to [PITH_FULL_IMAGE:figures/full_fig_p002_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Block scheme of the causality-based decision making framework, consisting of three main pipelines: [PITH_FULL_IMAGE:figures/full_fig_p005_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Overview of PeopleFlow’s context-aware agent behaviour strategy. The Context Manager node handles the [PITH_FULL_IMAGE:figures/full_fig_p007_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: (a) An illustrative example of an Amazon warehouse setting. (b) Warehouse-like scenario map with obstacles [PITH_FULL_IMAGE:figures/full_fig_p008_4.png] view at source ↗
Figure 5
Figure 5. Figure 5: Causal model of the scenario staged by PeopleFlow. Contextual factors [PITH_FULL_IMAGE:figures/full_fig_p009_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Two examples of people congestion areas at different time-slots. (a) Probability distribution of waypoint [PITH_FULL_IMAGE:figures/full_fig_p011_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Experimental scenario simulated using our simulator, as described in Sec. 4. The scenario is divided into 11 [PITH_FULL_IMAGE:figures/full_fig_p014_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Gazebo view of our simulated warehouse-like scenario staged by PeopleFlow. The scenario shows workers [PITH_FULL_IMAGE:figures/full_fig_p015_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Causal model retrieved from the full scenario. Context variables are shown in grey, while system variables are [PITH_FULL_IMAGE:figures/full_fig_p017_9.png] view at source ↗
Figure 10
Figure 10. Figure 10: Summary of overall efficiency metrics across all time-slots. (a) Task outcomes: (blue) successful tasks, [PITH_FULL_IMAGE:figures/full_fig_p019_10.png] view at source ↗
Figure 11
Figure 11. Figure 11: Summary of overall safety results across all time-slots. (a) Number of human-robot collisions of the various [PITH_FULL_IMAGE:figures/full_fig_p020_11.png] view at source ↗
Figure 12
Figure 12. Figure 12: (a) TIAGo robot with a person in a real-world scenario. (b) TIAGo robot with a simulated agent in [PITH_FULL_IMAGE:figures/full_fig_p022_12.png] view at source ↗
Figure 13
Figure 13. Figure 13: Causal query scalability analysis. explode with map complexity, which allows us to confidently predict performance even on larger maps and validates the approach for real-time planning. B Heuristic Weight Sensitivity Analysis To evaluating the impact of heuristic weight changes on decision outcomes, we performed a comprehensive sensitivity analysis. The objective was to systematically validate our paramet… view at source ↗
read the original abstract

The growing integration of robots in shared environments-such as warehouses, shopping centres, and hospitals-demands a deep understanding of the underlying dynamics and human behaviours, including how, when, and where individuals engage in various activities and interactions. This knowledge goes beyond simple correlation studies and requires a more comprehensive causal analysis. By leveraging causal inference to model cause-and-effect relationships, we can better anticipate critical environmental factors and enable autonomous robots to plan and execute tasks more effectively. To this end, we propose a novel causality-based decision-making framework that reasons over a learned causal model to assist the robot in deciding when and how to complete a given task. In the examined use case-i.e., a warehouse shared with people-we exploit the causal model to estimate battery usage and human obstructions as factors influencing the robot's task execution. This reasoning framework supports the robot in making informed decisions about task timing and strategy. To achieve this, we developed also PeopleFlow, a new Gazebo-based simulator designed to model context-sensitive human-robot spatial interactions in shared workspaces. PeopleFlow features realistic human and robot trajectories influenced by contextual factors such as time, environment layout, and robot state, and can simulate a large number of agents. While the simulator is general-purpose, in this paper we focus on a warehouse-like environment as a case study, where we conduct an extensive evaluation benchmarking our causal approach against a non-causal baseline. Our findings demonstrate the efficacy of the proposed solutions, highlighting how causal reasoning enables autonomous robots to operate more efficiently and safely in dynamic environments shared with humans.

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

2 major / 1 minor

Summary. The manuscript proposes a causality-based decision-making framework for autonomous mobile robots in dynamic environments shared with humans. It learns a causal model to estimate factors such as battery usage and human obstructions, which then informs decisions on task timing and strategy. The approach is evaluated in a warehouse-like setting using a new Gazebo-based simulator (PeopleFlow) that generates context-sensitive human-robot trajectories, with benchmarking against a non-causal baseline; the abstract claims this demonstrates improved efficiency and safety via causal reasoning.

Significance. If the central claim holds after addressing validation concerns, the work could advance robot planning by showing concrete benefits of causal models over correlational baselines in human-shared spaces. The introduction of PeopleFlow as a simulator for large-scale, context-sensitive interactions is a positive, reusable contribution that may support future studies in the field.

major comments (2)
  1. [Abstract and Evaluation section] Abstract and Evaluation section: The efficacy claim (that reasoning over the learned causal model yields better task decisions than the non-causal baseline) is load-bearing on the model recovering true cause-and-effect relationships for battery usage and obstructions rather than simulator correlations. No description is provided of the causal discovery algorithm, identifiability assumptions, or validation against interventions in PeopleFlow trajectories, leaving open that reported gains could stem from richer state representation alone.
  2. [PeopleFlow simulator and case-study evaluation] PeopleFlow simulator and case-study evaluation: The framework is tested only in a warehouse-like environment; without explicit checks that the causal structure generalizes beyond the simulator's trajectory generation rules (e.g., via held-out interventions or alternative layouts), the safety and efficiency conclusions remain tied to the specific data-generating process.
minor comments (1)
  1. [Abstract] Abstract: The sentence 'we developed also PeopleFlow' is grammatically awkward; revise to 'we also developed PeopleFlow'.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive comments, which highlight important aspects of our work that require clarification. We address each major comment below and indicate planned revisions to the manuscript.

read point-by-point responses

  1. Referee: [Abstract and Evaluation section] The efficacy claim (that reasoning over the learned causal model yields better task decisions than the non-causal baseline) is load-bearing on the model recovering true cause-and-effect relationships for battery usage and obstructions rather than simulator correlations. No description is provided of the causal discovery algorithm, identifiability assumptions, or validation against interventions in PeopleFlow trajectories, leaving open that reported gains could stem from richer state representation alone.

    Authors: We agree that the manuscript would benefit from explicit details on these elements to strengthen the causal interpretation of the results. The current text focuses on the application of the learned model to decision-making but does not fully specify the discovery procedure or validation steps. In the revision, we will add a dedicated subsection describing the causal discovery algorithm, the identifiability assumptions (including causal sufficiency for the modeled variables), and results from intervention-based checks on simulator trajectories to confirm that performance gains arise from recovered causal relationships rather than state richness alone. revision: yes

  2. Referee: [PeopleFlow simulator and case-study evaluation] The framework is tested only in a warehouse-like environment; without explicit checks that the causal structure generalizes beyond the simulator's trajectory generation rules (e.g., via held-out interventions or alternative layouts), the safety and efficiency conclusions remain tied to the specific data-generating process.

    Authors: The evaluation is presented as a focused case study in a warehouse setting, as stated in the abstract and evaluation sections. PeopleFlow itself is designed as a general-purpose simulator supporting varied contexts and layouts. To address the generalization concern, the revised manuscript will include additional experiments using held-out interventions on trajectory rules and tests in alternative environment configurations. These will be reported to show that the learned causal structure and efficiency/safety benefits are not artifacts of the specific warehouse data-generating process. revision: yes

Circularity Check

0 steps flagged

No circularity: high-level framework with external simulator benchmarks

full rationale

The paper describes a causality-based decision-making framework at a conceptual level, proposing to reason over a learned causal model for estimating battery usage and human obstructions in a warehouse simulator called PeopleFlow. It benchmarks the causal approach against a non-causal baseline and reports efficacy in task timing and strategy. No equations, derivations, or parameter-fitting steps are referenced in the provided text. There are no self-definitional reductions, fitted inputs renamed as predictions, or load-bearing self-citations. The evaluation relies on independent simulator runs and comparisons, keeping the central claim self-contained against external benchmarks rather than reducing to its own inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 1 invented entities

Abstract-only; no explicit free parameters, axioms, or invented entities beyond the new simulator are detailed. The central claim rests on the unstated assumption that causal models learned from data will generalize to real environmental dynamics.

axioms (1)
  • domain assumption Causal models can be learned from observational data to accurately represent cause-and-effect relationships in human-robot spatial interactions.
    Invoked when the framework reasons over the learned causal model to estimate battery usage and human obstructions.
invented entities (1)
  • PeopleFlow simulator no independent evidence
    purpose: To model context-sensitive human-robot spatial interactions in shared workspaces for evaluation.
    New Gazebo-based simulator introduced as part of the contribution.

pith-pipeline@v0.9.0 · 5809 in / 1351 out tokens · 48551 ms · 2026-05-22T20:40:45.831522+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

81 extracted references · 81 canonical work pages

  1. [1]

    A unified vision for european robotics: A strategy for innovation, growth and societal impact, December 2024

    euRobotics. A unified vision for european robotics: A strategy for innovation, growth and societal impact, December 2024

    work page 2024

  2. [2]

    National Robotics Initiative 3.0: Innovations in Integration of Robotics (NRI-3.0), 2021

    National Science Foundation. National Robotics Initiative 3.0: Innovations in Integration of Robotics (NRI-3.0), 2021. 15https://drive.google.com/file/d/1oBtTpPZbstD2a66BGxG7XdfBZ84MLPM7/view?usp=sharing 23 Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments

    work page 2021

  3. [3]

    The relevance of causation in robotics: A review, categorization, and analysis.Paladyn, Journal of Behavioral Robotics, 12(1):238–255, 2021

    Thomas Hellström. The relevance of causation in robotics: A review, categorization, and analysis.Paladyn, Journal of Behavioral Robotics, 12(1):238–255, 2021

    work page 2021

  4. [4]

    A causal approach to tool affordance learning

    Jake Brawer, Meiying Qin, and Brian Scassellati. A causal approach to tool affordance learning. InIEEE/RSJ International Conference on Intelligent Robots & Systems (IROS), pages 8394–8399, 2020

    work page 2020

  5. [5]

    Reasoning operational decisions for robots via time series causal inference

    Yu Cao, Boyang Li, Qian Li, Adam Stokes, David Ingram, and Aristides Kiprakis. Reasoning operational decisions for robots via time series causal inference. In2021 IEEE International Conference on Robotics and Automation (ICRA), pages 6124–6131, 2021

    work page 2021

  6. [6]

    Causal discovery of dynamic models for predicting human spatial interactions

    Luca Castri, Sariah Mghames, Marc Hanheide, and Nicola Bellotto. Causal discovery of dynamic models for predicting human spatial interactions. InInternational Conference on Social Robotics, pages 154–164. Springer, 2022

    work page 2022

  7. [7]

    Enhancing causal discovery from robot sensor data in dynamic scenarios

    Luca Castri, Sariah Mghames, Marc Hanheide, and Nicola Bellotto. Enhancing causal discovery from robot sensor data in dynamic scenarios. In2nd Conference on Causal Learning and Reasoning, 2023

    work page 2023

  8. [8]

    A novel parsimonious cause- effect reasoning algorithm for robot imitation and plan recognition.IEEE Trans

    Garrett Katz, Di Wei Huang, Theresa Hauge, Rodolphe Gentili, and James Reggia. A novel parsimonious cause- effect reasoning algorithm for robot imitation and plan recognition.IEEE Trans. on Cognitive and Developmental Systems, 2018

    work page 2018

  9. [9]

    Using causal analysis to learn specifications from task demonstrations

    Daniel Angelov, Yordan Hristov, and Subramanian Ramamoorthy. Using causal analysis to learn specifications from task demonstrations. InProceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS, pages 1341–1349, 2019

    work page 2019

  10. [10]

    Lee, Jialiang Alan Zhao, Amrita S

    Tabitha E. Lee, Jialiang Alan Zhao, Amrita S. Sawhney, Siddharth Girdhar, and Oliver Kroemer. Causal reasoning in simulation for structure and transfer learning of robot manipulation policies. In2021 IEEE International Conference on Robotics and Automation (ICRA), pages 4776–4782, 2021

    work page 2021

  11. [11]

    Towards a causal probabilistic framework for prediction, action-selection & explanations for robot block-stacking tasks

    Ricardo Cannizzaro, Jonathan Routley, and Lars Kunze. Towards a causal probabilistic framework for prediction, action-selection & explanations for robot block-stacking tasks. InIEEE/RSJ International Conference on Intelligent Robots & Systems (IROS) Workshop on Causality for Robotics. IEEE, 2023

    work page 2023

  12. [12]

    Towards probabilistic causal discovery, inference & explanations for autonomous drones in mine surveying tasks

    Ricardo Cannizzaro, Rhys Howard, Paulina Lewinska, and Lars Kunze. Towards probabilistic causal discovery, inference & explanations for autonomous drones in mine surveying tasks. InIEEE/RSJ International Conference on Intelligent Robots & Systems (IROS) Workshop on Causality for Robotics. IEEE, 2023

    work page 2023

  13. [13]

    Car-despot: Causally-informed online pomdp planning for robots in confounded environments

    Ricardo Cannizzaro and Lars Kunze. Car-despot: Causally-informed online pomdp planning for robots in confounded environments. InIEEE/RSJ International Conference on Intelligent Robots & Systems (IROS). IEEE, October 2023

    work page 2023

  14. [14]

    What would i do if

    Tamlin Love, Antonio Andriella, and Guillem Alenyà. What would i do if. . . ? promoting understanding in hri through real-time explanations in the wild. In2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN), pages 504–509. IEEE, 2024

    work page 2024

  15. [15]

    Towards explainable proactive robot interactions for groups of people in unstructured environments

    Tamlin Love, Antonio Andriella, and Guillem Alenyà. Towards explainable proactive robot interactions for groups of people in unstructured environments. InCompanion of the 2024 ACM/IEEE International Conference on Human-Robot Interaction, pages 697–701, 2024

    work page 2024

  16. [16]

    Review of causal discovery methods based on graphical models

    Clark Glymour, Kun Zhang, and Peter Spirtes. Review of causal discovery methods based on graphical models. Frontiers in genetics, 10:524, 2019

    work page 2019

  17. [17]

    Survey and evaluation of causal discovery methods for time series.Journal of Artificial Intelligence Research, 73:767–819, 2022

    Charles K Assaad, Emilie Devijver, and Eric Gaussier. Survey and evaluation of causal discovery methods for time series.Journal of Artificial Intelligence Research, 73:767–819, 2022

    work page 2022

  18. [18]

    MIT press, 2000

    Peter Spirtes, Clark N Glymour, and Richard Scheines.Causation, prediction, and search. MIT press, 2000

    work page 2000

  19. [19]

    Causal network reconstruction from time series: From theoretical assumptions to practical estimation

    Jakob Runge. Causal network reconstruction from time series: From theoretical assumptions to practical estimation. Chaos: An Interdisciplinary Journal of Nonlinear Science, 28(7), 2018

    work page 2018

  20. [20]

    Detecting and quantifying causal associations in large nonlinear time series datasets.Science advances, 5(11):eaau4996, 2019

    Jakob Runge, Peer Nowack, Marlene Kretschmer, Seth Flaxman, and Dino Sejdinovic. Detecting and quantifying causal associations in large nonlinear time series datasets.Science advances, 5(11):eaau4996, 2019

    work page 2019

  21. [21]

    Constructing brain connectivity model using causal network reconstruction approach.Frontiers in Neuroinformatics, 15:619557, 2021

    Supat Saetia, Natsue Yoshimura, and Yasuharu Koike. Constructing brain connectivity model using causal network reconstruction approach.Frontiers in Neuroinformatics, 15:619557, 2021

    work page 2021

  22. [22]

    Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasets

    Jakob Runge. Discovering contemporaneous and lagged causal relations in autocorrelated nonlinear time series datasets. InConference on Uncertainty in Artificial Intelligence (UAI), pages 1388–1397. PMLR, 2020

    work page 2020

  23. [23]

    Causal discovery for time series from multiple datasets with latent contexts

    Wiebke Günther, Urmi Ninad, and Jakob Runge. Causal discovery for time series from multiple datasets with latent contexts. In Robin J. Evans and Ilya Shpitser, editors,Proceedings of the Thirty-Ninth Conference on Uncertainty in Artificial Intelligence, volume 216 ofProceedings of Machine Learning Research, pages 766–776. PMLR, 31 Jul–04 Aug 2023. 24 Caus...

    work page 2023

  24. [24]

    High-recall causal discovery for autocorrelated time series with latent confounders.Advances in Neural Information Processing Systems, 33:12615–12625, 2020

    Andreas Gerhardus and Jakob Runge. High-recall causal discovery for autocorrelated time series with latent confounders.Advances in Neural Information Processing Systems, 33:12615–12625, 2020

    work page 2020

  25. [25]

    Candoit: Causal discovery with observational and interventional data from time series.Advanced Intelligent Systems, 6(12):2400181, 2024

    Luca Castri, Sariah Mghames, Marc Hanheide, and Nicola Bellotto. Candoit: Causal discovery with observational and interventional data from time series.Advanced Intelligent Systems, 6(12):2400181, 2024

    work page 2024

  26. [26]

    Experimental evaluation of ros-causal in real-world human-robot spatial interaction scenarios

    Luca Castri, Gloria Beraldo, Sariah Mghames, Marc Hanheide, and Nicola Bellotto. Experimental evaluation of ros-causal in real-world human-robot spatial interaction scenarios. In2024 33rd IEEE International Conference on Robot and Human Interactive Communication (ROMAN), pages 1603–1609, 2024

    work page 2024

  27. [27]

    A survey of robot learning strategies for human-robot collaboration in industrial settings.Robotics and Computer-Integrated Manufacturing, 73:102231, 2022

    Debasmita Mukherjee, Kashish Gupta, Li Hsin Chang, and Homayoun Najjaran. A survey of robot learning strategies for human-robot collaboration in industrial settings.Robotics and Computer-Integrated Manufacturing, 73:102231, 2022

    work page 2022

  28. [28]

    Human–robot interaction in agriculture: A survey and current challenges.Biosystems engineering, 179:35–48, 2019

    Juan P Vasconez, George A Kantor, and Fernando A Auat Cheein. Human–robot interaction in agriculture: A survey and current challenges.Biosystems engineering, 179:35–48, 2019

    work page 2019

  29. [29]

    Human-robot interactions in manufacturing: A survey of human behavior modeling.Robotics and Computer-Integrated Manufacturing, 78:102404, 2022

    Roohollah Jahanmahin, Sara Masoud, Jeremy Rickli, and Ana Djuric. Human-robot interactions in manufacturing: A survey of human behavior modeling.Robotics and Computer-Integrated Manufacturing, 78:102404, 2022

    work page 2022

  30. [30]

    A survey of multi-agent human–robot interaction systems.Robotics and Autonomous Systems, 161:104335, 2023

    Abhinav Dahiya, Alexander M Aroyo, Kerstin Dautenhahn, and Stephen L Smith. A survey of multi-agent human–robot interaction systems.Robotics and Autonomous Systems, 161:104335, 2023

    work page 2023

  31. [31]

    A computational model of human-robot spatial interactions based on a qualitative trajectory calculus.Robotics, 4(1):63–102, 2015

    Christian Dondrup, Nicola Bellotto, Marc Hanheide, Kerstin Eder, and Ute Leonards. A computational model of human-robot spatial interactions based on a qualitative trajectory calculus.Robotics, 4(1):63–102, 2015

    work page 2015

  32. [32]

    A neuro-symbolic approach for enhanced human motion prediction

    Sariah Mghames, Luca Castri, Marc Hanheide, and Nicola Bellotto. A neuro-symbolic approach for enhanced human motion prediction. In2023 International Joint Conference on Neural Networks (IJCNN), pages 1–8. IEEE, 2023

    work page 2023

  33. [33]

    Qualitative prediction of multi-agent spatial interactions

    Sariah Mghames, Luca Castri, Marc Hanheide, and Nicola Bellotto. Qualitative prediction of multi-agent spatial interactions. In2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), pages 1170–1175. IEEE, 2023

    work page 2023

  34. [34]

    Y . Liu, R. Cadei, J. Schweizer, S. Bahmani, and A. Alahi. Towards robust and adaptive motion forecasting: A causal representation perspective. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 17081–17092, 2022

    work page 2022

  35. [35]

    Thör: Human-robot navigation data collection and accurate motion trajectories dataset.IEEE Robotics & Automation Letters, pages 676–682, 2020

    Andrey Rudenko, Tomasz P Kucner, Chittaranjan S Swaminathan, Ravi T Chadalavada, Kai O Arras, and Achim J Lilienthal. Thör: Human-robot navigation data collection and accurate motion trajectories dataset.IEEE Robotics & Automation Letters, pages 676–682, 2020

    work page 2020

  36. [36]

    Thör-magni: A large-scale indoor motion capture recording of human movement and robot interaction.The International Journal of Robotics Research, page 02783649241274794, 2024

    Tim Schreiter, Tiago Rodrigues de Almeida, Yufei Zhu, Eduardo Gutierrez Maestro, Lucas Morillo-Mendez, Andrey Rudenko, Luigi Palmieri, Tomasz P Kucner, Martin Magnusson, and Achim J Lilienthal. Thör-magni: A large-scale indoor motion capture recording of human movement and robot interaction.The International Journal of Robotics Research, page 027836492412...

    work page 2024

  37. [37]

    Person tracking in large public spaces using 3-d range sensors.IEEE Trans

    Dražen Bršˇci´c, Takayuki Kanda, Tetsushi Ikeda, and Takahiro Miyashita. Person tracking in large public spaces using 3-d range sensors.IEEE Trans. on Human-Machine Systems, pages 522–534, 2013

    work page 2013

  38. [38]

    Jrdb: A dataset and benchmark of egocentric robot visual perception of humans in built environments.IEEE transactions on pattern analysis and machine intelligence, 2021

    Roberto Martin-Martin, Mihir Patel, Hamid Rezatofighi, Abhijeet Shenoi, JunYoung Gwak, Eric Frankel, Amir Sadeghian, and Silvio Savarese. Jrdb: A dataset and benchmark of egocentric robot visual perception of humans in built environments.IEEE transactions on pattern analysis and machine intelligence, 2021

    work page 2021

  39. [39]

    Sohn, Greg Schwartz, Subashri Ramesh, Mohamed Hussein, Anjali W

    Nathan Tsoi, Alec Xiang, Peter Yu, Samuel S. Sohn, Greg Schwartz, Subashri Ramesh, Mohamed Hussein, Anjali W. Gupta, Mubbasir Kapadia, and Marynel Vázquez. Sean 2.0: Formalizing and generating social situations for robot navigation.IEEE Robotics and Automation Letters, pages 1–8, 2022

    work page 2022

  40. [40]

    Mengeros: A crowd simulation tool for autonomous robot navigation

    Anoop Aroor, Susan L Epstein, and Raj Korpan. Mengeros: A crowd simulation tool for autonomous robot navigation. InAAAI Fall Symposia, pages 123–125, 2017

    work page 2017

  41. [41]

    Crowd-robot interaction: Crowd-aware robot navigation with attention-based deep reinforcement learning

    Changan Chen, Yuejiang Liu, Sven Kreiss, and Alexandre Alahi. Crowd-robot interaction: Crowd-aware robot navigation with attention-based deep reinforcement learning. In2019 international conference on robotics and automation (ICRA), pages 6015–6022. IEEE, 2019

    work page 2019

  42. [42]

    Socialgym: A framework for benchmarking social robot navigation

    Jarrett Holtz and Joydeep Biswas. Socialgym: A framework for benchmarking social robot navigation. In2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 11246–11252. IEEE, 2022

    work page 2022

  43. [43]

    Basic books, 2018

    Judea Pearl and Dana Mackenzie.The book of why: the new science of cause and effect. Basic books, 2018

    work page 2018

  44. [44]

    Discretization of time series data.Journal of Computational Biology, 17(6):853–868, 2010

    Elena S Dimitrova, M Paola Vera Licona, John McGee, and Reinhard Laubenbacher. Discretization of time series data.Journal of Computational Biology, 17(6):853–868, 2010. 25 Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments

    work page 2010

  45. [45]

    Packt Publishing Ltd, 2017

    Pratap Dangeti.Statistics for machine learning. Packt Publishing Ltd, 2017

    work page 2017

  46. [46]

    Dynotears: Structure learning from time-series data

    Roxana Pamfil, Nisara Sriwattanaworachai, Shaan Desai, Philip Pilgerstorfer, Konstantinos Georgatzis, Paul Beaumont, and Bryon Aragam. Dynotears: Structure learning from time-series data. InInternational Conference on Artificial Intelligence and Statistics, pages 1595–1605. PMLR, 2020

    work page 2020

  47. [47]

    Estimation of a structural vector autoregression model using non-gaussianity.Journal of Machine Learning Research, 11(5), 2010

    Aapo Hyvärinen, Kun Zhang, Shohei Shimizu, and Patrik O Hoyer. Estimation of a structural vector autoregression model using non-gaussianity.Journal of Machine Learning Research, 11(5), 2010

    work page 2010

  48. [48]

    On causal discovery from time series data using fci.Probabilistic graphical models, pages 121–128, 2010

    Doris Entner and Patrik O Hoyer. On causal discovery from time series data using fci.Probabilistic graphical models, pages 121–128, 2010

    work page 2010

  49. [49]

    Estimating causal effects from learned causal networks

    Anna K Raichev, Jin Tian, Alexander Ihler, and Rina Dechter. Estimating causal effects from learned causal networks. In9th Causal Inference Workshop at UAI 2024, 2024

    work page 2024

  50. [50]

    Tutorial on maximum likelihood estimation.Journal of mathematical Psychology, 47(1):90–100, 2003

    In Jae Myung. Tutorial on maximum likelihood estimation.Journal of mathematical Psychology, 47(1):90–100, 2003

    work page 2003

  51. [51]

    Cambridge university press, 2009

    Judea Pearl.Causality. Cambridge university press, 2009

    work page 2009

  52. [52]

    agrum/pyagrum: a toolbox to build models and algorithms for probabilistic graphical models in python

    Gaspard Ducamp, Christophe Gonzales, and Pierre-Henri Wuillemin. agrum/pyagrum: a toolbox to build models and algorithms for probabilistic graphical models in python. InInternational Conference on Probabilistic Graphical Models. PMLR, 2020

    work page 2020

  53. [53]

    Ros-causal: A ros-based causal analysis framework for human-robot interaction applications

    Luca Castri, Gloria Beraldo, Sariah Mghames, Marc Hanheide, and Nicola Bellotto. Ros-causal: A ros-based causal analysis framework for human-robot interaction applications. InWorkshop on Causal Learning for Human-Robot Interaction (Causal-HRI), ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2024

    work page 2024

  54. [54]

    Social force model for pedestrian dynamics.Physical review E, 51(5):4282, 1995

    Dirk Helbing and Peter Molnar. Social force model for pedestrian dynamics.Physical review E, 51(5):4282, 1995

    work page 1995

  55. [55]

    Warehouse layouts

    Goran Dukic and Tihomir Opetuk. Warehouse layouts. InWarehousing in the Global Supply Chain: Advanced Models, Tools and Applications for Storage Systems, pages 55–69. Springer, 2012

    work page 2012

  56. [56]

    Battery charge scheduling in long-life autonomous mobile robots

    Milan Tomy, Bruno Lacerda, Nick Hawes, and Jeremy L Wyatt. Battery charge scheduling in long-life autonomous mobile robots. In2019 European Conference on Mobile Robots (ECMR), pages 1–6. IEEE, 2019

    work page 2019

  57. [57]

    Battery charge scheduling in long-life au- tonomous mobile robots via multi-objective decision making under uncertainty.Robotics and Autonomous Systems, 133:103629, 2020

    Milan Tomy, Bruno Lacerda, Nick Hawes, and Jeremy L Wyatt. Battery charge scheduling in long-life au- tonomous mobile robots via multi-objective decision making under uncertainty.Robotics and Autonomous Systems, 133:103629, 2020

    work page 2020

  58. [58]

    Planning and control of autonomous mobile robots for intralogistics: Literature review and research agenda.European Journal of Operational Research, 294(2):405–426, 2021

    Giuseppe Fragapane, Rene De Koster, Fabio Sgarbossa, and Jan Ola Strandhagen. Planning and control of autonomous mobile robots for intralogistics: Literature review and research agenda.European Journal of Operational Research, 294(2):405–426, 2021

    work page 2021

  59. [59]

    Opportunistic (re) planning for long-term deep-ocean inspection: An autonomous underwater architecture.IEEE Robotics & Automation Magazine, 2024

    Elisa Tosello, Paolo Bonel, Alberto Buranello, Marco Carraro, Alessandro Cimatti, Lorenzo Granelli, Stefan Panjkovic, and Andrea Micheli. Opportunistic (re) planning for long-term deep-ocean inspection: An autonomous underwater architecture.IEEE Robotics & Automation Magazine, 2024

    work page 2024

  60. [60]

    Energy modeling and power measurement for mobile robots

    Linfei Hou, Liang Zhang, and Jongwon Kim. Energy modeling and power measurement for mobile robots. Energies, 12(1):27, 2018

    work page 2018

  61. [61]

    Factory workers’ ordinary user experiences: An overlooked perspective.Human Technology, 14(2):209–232, 2018

    Thomas Meneweger, Daniela Wurhofer, Verena Fuchsberger, and Manfred Tscheligi. Factory workers’ ordinary user experiences: An overlooked perspective.Human Technology, 14(2):209–232, 2018

    work page 2018

  62. [62]

    Multi-agent path topology in support of socially competent navigation planning.The International Journal of Robotics Research, 38(2-3):338–356, 2019

    Christoforos I Mavrogiannis and Ross A Knepper. Multi-agent path topology in support of socially competent navigation planning.The International Journal of Robotics Research, 38(2-3):338–356, 2019

    work page 2019

  63. [63]

    Hamiltonian coordination primitives for decentralized multiagent navigation.The International Journal of Robotics Research, 40(10-11):1234–1254, 2021

    Christoforos Mavrogiannis and Ross A Knepper. Hamiltonian coordination primitives for decentralized multiagent navigation.The International Journal of Robotics Research, 40(10-11):1234–1254, 2021

    work page 2021

  64. [64]

    The office marathon: Robust navigation in an indoor office environment

    Eitan Marder-Eppstein, Eric Berger, Tully Foote, Brian Gerkey, and Kurt Konolige. The office marathon: Robust navigation in an indoor office environment. In2010 IEEE international conference on robotics and automation, pages 300–307. IEEE, 2010

    work page 2010

  65. [65]

    The navigation based on hybrid a star and teb algorithm implemented in obstacles avoidance

    Hongzhang Zheng, Min Dai, Zhisheng Zhang, Zhijie Xia, Guifu Zhang, and Fang Jia. The navigation based on hybrid a star and teb algorithm implemented in obstacles avoidance. In2023 29th International Conference on Mechatronics and Machine Vision in Practice (M2VIP), pages 1–6. IEEE, 2023

    work page 2023

  66. [66]

    Pedestrian-movement prediction based on mixed markov-chain model

    Akinori Asahara, Kishiko Maruyama, Akiko Sato, and Kouichi Seto. Pedestrian-movement prediction based on mixed markov-chain model. InProceedings of the 19th ACM SIGSPATIAL international conference on advances in geographic information systems, pages 25–33, 2011. 26 Causality-enhanced Decision-Making for Autonomous Mobile Robots in Dynamic Environments

    work page 2011

  67. [67]

    Human motion prediction for human-robot collaboration.Journal of Manufacturing Systems, 44:287–294, 2017

    Hongyi Liu and Lihui Wang. Human motion prediction for human-robot collaboration.Journal of Manufacturing Systems, 44:287–294, 2017

    work page 2017

  68. [68]

    Wakim, S

    C.F. Wakim, S. Capperon, and J. Oksman. A markovian model of pedestrian behavior. In2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583), volume 4, pages 4028–4033 vol.4, 2004

    work page 2004

  69. [69]

    Path planning of a mobile robot using genetic heuristics.Robotica, 16(5):575–588, 1998

    Andreas C Nearchou. Path planning of a mobile robot using genetic heuristics.Robotica, 16(5):575–588, 1998

    work page 1998

  70. [70]

    Sariff and N

    N. Sariff and N. Buniyamin. An overview of autonomous mobile robot path planning algorithms. In2006 4th Student Conference on Research and Development, pages 183–188, 2006

    work page 2006

  71. [71]

    A comprehensive review of coverage path planning in robotics using classical and heuristic algorithms.IEEE Access, 9:119310–119342, 2021

    Chee Sheng Tan, Rosmiwati Mohd-Mokhtar, and Mohd Rizal Arshad. A comprehensive review of coverage path planning in robotics using classical and heuristic algorithms.IEEE Access, 9:119310–119342, 2021

    work page 2021

  72. [72]

    Searching for a safe shortest path in a warehouse

    Aurélien Mombelli, Alain Quilliot, and Mourad Baiou. Searching for a safe shortest path in a warehouse. In11th International Conference on Operations Research and Enterprise Systems, 2022

    work page 2022

  73. [73]

    A novel path planning algorithm for warehouse robots based on a two-dimensional grid model.IEEE Access, 8:80347–80357, 2020

    Bo Yang, Wentao Li, Jianrong Wang, Jingjie Yang, Tiantian Wang, and Xin Liu. A novel path planning algorithm for warehouse robots based on a two-dimensional grid model.IEEE Access, 8:80347–80357, 2020

    work page 2020

  74. [74]

    Motion planning for a chain of mobile robots using a* and potential field.Robotics, 7(2):20, 2018

    Apoorva, Rahul Gautam, and Rahul Kala. Motion planning for a chain of mobile robots using a* and potential field.Robotics, 7(2):20, 2018

    work page 2018

  75. [75]

    Adaptive path finding algorithm in dynamic environment for warehouse robot.Neural Computing and Applications, 32(17):13155– 13171, 2020

    Mun-Kit Ng, Yung-Wey Chong, Kwang-man Ko, Young-Hoon Park, and Yu-Beng Leau. Adaptive path finding algorithm in dynamic environment for warehouse robot.Neural Computing and Applications, 32(17):13155– 13171, 2020

    work page 2020

  76. [76]

    Agv path planning based on improved a-star algorithm

    Dengxing Zhang, Chen Chen, and Guanyu Zhang. Agv path planning based on improved a-star algorithm. In2024 IEEE 7th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), volume 7, pages 1590–1595. IEEE, 2024

    work page 2024

  77. [77]

    Springer Science & Business Media, 2006

    Gregory Gutin and Abraham P Punnen.The traveling salesman problem and its variations, volume 12. Springer Science & Business Media, 2006

    work page 2006

  78. [78]

    How, Haresh Karnan, Tsang-Wei Edward Lee, Luis J

    Anthony Francis, Claudia Perez-D’Arpino, Chengshu Li, Fei Xia, Alexandre Alahi, Rachid Alami, Aniket Bera, Abhijat Biswas, Joydeep Biswas, Rohan Chandra, Hao-Tien Lewis Chiang, Michael Everett, Sehoon Ha, Justin Hart, Jonathan P. How, Haresh Karnan, Tsang-Wei Edward Lee, Luis J. Manso, Reuth Mirksy, Soeren Pirk, Phani Teja Singamaneni, Peter Stone, Ada V ...

    work page 2024

  79. [79]

    Core challenges of social robot navigation: A survey.ACM Transactions on Human-Robot Interaction, 12(3):1–39, 2023

    Christoforos Mavrogiannis, Francesca Baldini, Allan Wang, Dapeng Zhao, Pete Trautman, Aaron Steinfeld, and Jean Oh. Core challenges of social robot navigation: A survey.ACM Transactions on Human-Robot Interaction, 12(3):1–39, 2023

    work page 2023

  80. [80]

    Proxemics [and comments and replies]

    Edward T Hall, Ray L Birdwhistell, Bernhard Bock, Paul Bohannan, A Richard Diebold Jr, Marshall Durbin, Munro S Edmonson, JL Fischer, Dell Hymes, Solon T Kimball, et al. Proxemics [and comments and replies]. Current anthropology, 9(2/3):83–108, 1968

    work page 1968

Showing first 80 references.