pith. the verified trust layer for science. sign in

arxiv: 2510.14063 · v2 · submitted 2025-10-15 · 💻 cs.RO

Adaptive Obstacle-Aware Task Assignment and Planning for Heterogeneous Robot Teaming

Nan Li , Jiming Ren , Haris Miller , Samuel Coogan , Karen M. Feigh , Ye Zhao This is my paper

Pith reviewed 2026-05-18 06:34 UTC · model grok-4.3

classification 💻 cs.RO
keywords multi-agent systemstask assignmentobstacle avoidanceheterogeneous robotsHalton samplingauction algorithmsLLM integrationrobot planning
0
0 comments X p. Extension

The pith

OATH framework assigns tasks to robot teams with obstacle awareness for better scalability and adaptability.

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

Multi-agent task assignment and planning struggles with obstacles, scalability, and dynamic changes in robot teams. The OATH method introduces an adaptive Halton sequence map to adjust sampling density around obstacles and pairs it with a cluster-auction-selection process for coordinating different robots. It also uses large language models to turn human instructions into real-time planner guidance. If this works as intended, robot teams could complete missions more reliably in messy real-world spaces like warehouses or disaster zones, outperforming existing approaches in both speed and quality of assignments.

Core claim

OATH advances MATP by introducing a novel obstacle-aware strategy for task assignment. First, an adaptive Halton sequence map adjusts sampling density based on obstacle distribution. Second, a cluster-auction-selection framework integrates obstacle-aware clustering with weighted auctions and intra-cluster task selection. These mechanisms enable effective coordination among heterogeneous robots while maintaining scalability and suboptimal allocation performance. The framework also leverages an LLM to interpret human instructions and directly guide the planner in real time.

What carries the argument

Adaptive Halton sequence map for obstacle-aware sampling combined with cluster-auction-selection framework for robot coordination.

If this is right

  • Improved task assignment quality in obstacle-rich environments
  • Greater scalability for handling more robots or tasks
  • Enhanced adaptability to dynamic changes in the environment
  • Superior overall execution performance in simulations and real-world tests

Where Pith is reading between the lines

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

  • Potential application to drone delivery systems in urban settings with buildings as obstacles.
  • Further integration with computer vision could allow real-time obstacle map updates from onboard sensors.
  • May lead to lower operational costs by minimizing robot travel distances in cluttered areas.

Load-bearing premise

The adaptive Halton sequence map and cluster-auction-selection framework integrate effectively with LLM guidance to deliver scalability and performance improvements in both simulation and real hardware.

What would settle it

An experiment increasing the complexity of obstacles or team size and measuring if improvements in assignment quality and completion time hold compared to baselines.

Figures

Figures reproduced from arXiv: 2510.14063 by Haris Miller, Jiming Ren, Karen M. Feigh, Nan Li, Samuel Coogan, Ye Zhao.

Figure 1
Figure 1. Figure 1: Problem setup in the Isaac simulation environment. A heteroge [PITH_FULL_IMAGE:figures/full_fig_p001_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Overview of the OATH framework: the planning module is composed of three parts — environment and map preprocessing, task assignment, and path [PITH_FULL_IMAGE:figures/full_fig_p004_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Spatial modeling and task clustering process. The left figure shows the construction of the adaptive Halton sequence, generating obstacle-aware [PITH_FULL_IMAGE:figures/full_fig_p005_3.png] view at source ↗
Figure 4
Figure 4. Figure 4: Illustration of the hierarchical task-assignment framework. Tasks are [PITH_FULL_IMAGE:figures/full_fig_p006_4.png] view at source ↗
Figure 3
Figure 3. Figure 3: This graph captures obstacle-aware traversal costs and [PITH_FULL_IMAGE:figures/full_fig_p006_3.png] view at source ↗
Figure 5
Figure 5. Figure 5: Comparison of heterogeneous task assignment results under different numbers of task types. Each subfigure illustrates the final task assignment for [PITH_FULL_IMAGE:figures/full_fig_p008_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Overview of how the LLM parses human instructions and how the planner reacts. The LLM converts natural language into structured intents [PITH_FULL_IMAGE:figures/full_fig_p009_6.png] view at source ↗
Figure 7
Figure 7. Figure 7: Demonstration of obstacle-aware task assignment and route replanning under LLM-parsed human instructions in Isaac Sim. The first row shows the [PITH_FULL_IMAGE:figures/full_fig_p010_7.png] view at source ↗
Figure 8
Figure 8. Figure 8: Computational time of the task assignment algorithm under different experimental settings. Left: varying the task size while keeping the number of [PITH_FULL_IMAGE:figures/full_fig_p012_8.png] view at source ↗
Figure 9
Figure 9. Figure 9: Experimental results of the task assignment algorithm in a simulated [PITH_FULL_IMAGE:figures/full_fig_p013_9.png] view at source ↗
Figure 11
Figure 11. Figure 11: Comparison between human-issued and system built-in instructions for three instruction types: New Obstacles Detected, Add New Tasks, and Change Task Priority. The left column reports execution time (s), and the right column reports the total number of robot steps. The top row shows means (bar plots), and the bottom row shows variability across trials (box plots). Yellow and pink bars/boxes denote the two … view at source ↗
read the original abstract

Multi-Agent Task Assignment and Planning (MATP) has attracted growing attention but remains challenging in terms of scalability, spatial reasoning, and adaptability in obstacle-rich environments. To address these challenges, we propose OATH - Adaptive Obstacle-Aware Task Assignment and Planning for Heterogeneous Robot Teaming - which advances MATP by introducing a novel obstacle-aware strategy for task assignment. First, we develop an adaptive Halton sequence map, the first known application of Halton sampling with obstacle-aware adaptation in MATP, which adjusts sampling density based on obstacle distribution. Second, we propose a cluster-auction-selection framework that integrates obstacle-aware clustering with weighted auctions and intra-cluster task selection. These mechanisms jointly enable effective coordination among heterogeneous robots while maintaining scalability and suboptimal allocation performance. In addition, our framework leverages an LLM to interpret human instructions and directly guide the planner in real time. We validate OATH in both NVIDIA Isaac Sim and real-world hardware experiments using TurtleBot platforms, demonstrating substantial improvements in task assignment quality, scalability, adaptability to dynamic changes, and overall execution performance compared to state-of-the-art MATP baselines. A project website is available at https://llm-oath.github.io/.

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 OATH, a framework for Multi-Agent Task Assignment and Planning (MATP) for heterogeneous robot teams in obstacle-rich environments. It introduces an adaptive Halton sequence map that adjusts sampling density based on obstacle distribution (claimed as the first such application in MATP), a cluster-auction-selection framework that combines obstacle-aware clustering with weighted auctions and intra-cluster task selection, and LLM-based interpretation of human instructions for real-time planner guidance. The approach is validated in NVIDIA Isaac Sim simulations and real-world TurtleBot hardware experiments, with claims of substantial improvements over state-of-the-art MATP baselines in task assignment quality, scalability, adaptability to dynamic changes, and overall execution performance.

Significance. If the performance claims hold under rigorous quantitative evaluation, the work could advance MATP by showing a practical combination of adaptive low-discrepancy sampling, auction-based assignment, and LLM guidance for heterogeneous teams in dynamic obstacle settings. The dual simulation-plus-hardware validation and the explicit novelty claim for obstacle-aware Halton sampling are positive elements. However, the absence of any numerical results, baselines, or statistical details in the abstract substantially weakens the ability to gauge the magnitude or generality of the reported gains.

major comments (2)
  1. [Abstract] Abstract: the claim of 'substantial improvements' in task assignment quality, scalability, adaptability, and execution performance is unsupported by any quantitative metrics, baseline comparisons, statistical analysis, error bars, or specific numerical results. This directly undermines verification of the central empirical claims.
  2. [Abstract / Proposed Framework] Abstract / Proposed Framework: no complexity bound or scaling analysis is given for the cluster-auction-selection phase as the number of clusters or degree of robot heterogeneity increases. In addition, no ablation isolates the adaptive Halton component from the LLM guidance or the intra-cluster heuristic, leaving open the possibility that reported gains in Isaac Sim and TurtleBot trials are environment-specific rather than general properties of the framework.
minor comments (1)
  1. [Abstract] The project website link is a helpful addition for potential reproducibility.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive feedback on our manuscript. We address each major comment below and have revised the manuscript to incorporate the suggested improvements, particularly strengthening the abstract and adding supporting analyses.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the claim of 'substantial improvements' in task assignment quality, scalability, adaptability, and execution performance is unsupported by any quantitative metrics, baseline comparisons, statistical analysis, error bars, or specific numerical results. This directly undermines verification of the central empirical claims.

    Authors: We agree that the abstract would be strengthened by including concrete quantitative results to support the performance claims. In the revised manuscript, we have updated the abstract to incorporate key numerical findings from our experiments, such as specific percentage improvements in task completion time and assignment quality relative to baselines, along with references to statistical significance and error bars detailed in the results section. This makes the central empirical claims directly verifiable from the abstract. revision: yes

  2. Referee: [Abstract / Proposed Framework] Abstract / Proposed Framework: no complexity bound or scaling analysis is given for the cluster-auction-selection phase as the number of clusters or degree of robot heterogeneity increases. In addition, no ablation isolates the adaptive Halton component from the LLM guidance or the intra-cluster heuristic, leaving open the possibility that reported gains in Isaac Sim and TurtleBot trials are environment-specific rather than general properties of the framework.

    Authors: We acknowledge the value of explicit complexity analysis and ablations. We have added a dedicated subsection analyzing the computational complexity of the cluster-auction-selection phase, establishing that it scales as O(C log T + C * R) where C denotes clusters, T tasks, and R robots, remaining efficient even as heterogeneity increases. We have also included new ablation experiments that isolate the adaptive Halton sampling from the LLM guidance and intra-cluster heuristic. These results demonstrate the individual contributions of each component and confirm that performance gains generalize beyond the specific simulation and hardware environments tested. revision: yes

Circularity Check

0 steps flagged

No circularity: novel integration of adaptive Halton sampling and cluster-auction framework

full rationale

The paper introduces OATH as a new obstacle-aware strategy for MATP, built from an adaptive Halton sequence map (density adjusted by obstacle distribution) and a cluster-auction-selection framework, with LLM guidance for real-time human instruction interpretation. These are presented as first-known applications and novel combinations, validated through empirical comparisons in Isaac Sim and TurtleBot hardware against state-of-the-art baselines. No equations, fitted parameters renamed as predictions, self-definitional reductions, or load-bearing self-citations appear in the derivation; the central claims rest on the described integration and experimental performance gains rather than reducing to inputs by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Based on abstract only; no explicit free parameters, axioms, or invented entities are detailed beyond high-level algorithmic descriptions.

pith-pipeline@v0.9.0 · 5750 in / 1184 out tokens · 36809 ms · 2026-05-18T06:34:48.221457+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

67 extracted references · 67 canonical work pages · 8 internal anchors

  1. [1]

    Optimization techniques for multi-robot task allocation problems: Review on the state- of-the-art,

    H. Chakraa, F. Gu ´erin, E. Leclercq, and D. Lefebvre, “Optimization techniques for multi-robot task allocation problems: Review on the state- of-the-art,”Robotics and Autonomous Systems, vol. 168, p. 104492, 2023

    work page 2023

  2. [2]

    A review on multirobot systems in agriculture,

    C. Ju, J. Kim, J. Seol, and H. I. Son, “A review on multirobot systems in agriculture,”Computers and Electronics in Agriculture, vol. 202, p. 107336, 2022

    work page 2022

  3. [3]

    A dis- tributed task allocation algorithm for a multi-robot system in healthcare facilities,

    G. P. Das, T. M. McGinnity, S. A. Coleman, and L. Behera, “A dis- tributed task allocation algorithm for a multi-robot system in healthcare facilities,”Journal of Intelligent & Robotic Systems, vol. 80, pp. 33–58, 2015

    work page 2015

  4. [4]

    Drone-surveillance for search and rescue in natural disaster,

    B. Mishra, D. Garg, P. Narang, and V . Mishra, “Drone-surveillance for search and rescue in natural disaster,”Computer Communications, vol. 156, pp. 1–10, 2020

    work page 2020

  5. [5]

    Leverag- ing heterogeneous capabilities in multi-agent systems for environmental conflict resolution,

    M. E. Cao, X. Ni, J. Warnke, Y . Han, S. Coogan, and Y . Zhao, “Leverag- ing heterogeneous capabilities in multi-agent systems for environmental conflict resolution,” in2022 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR). IEEE, 2022, pp. 94–101

    work page 2022

  6. [6]

    Research challenges and opportunities in multi-agent path finding and multi-agent pickup and delivery problems,

    O. Salzman and R. Stern, “Research challenges and opportunities in multi-agent path finding and multi-agent pickup and delivery problems,” inProceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems, 2020, pp. 1711–1715

    work page 2020

  7. [7]

    Terrain- aware model predictive control of heterogeneous bipedal and aerial robot coordination for search and rescue tasks,

    A. Shamsah, J. Jiang, Z. Yoon, S. Coogan, and Y . Zhao, “Terrain- aware model predictive control of heterogeneous bipedal and aerial robot coordination for search and rescue tasks,” in2025 IEEE International Conference on Robotics and Automation (ICRA). IEEE, 2025, pp. 12 352–12 358

    work page 2025

  8. [8]

    Reactive task allocation and planning for quadrupedal and wheeled robot teaming,

    Z. Zhou, D. J. Lee, Y . Yoshinaga, S. Balakirsky, D. Guo, and Y . Zhao, “Reactive task allocation and planning for quadrupedal and wheeled robot teaming,” in2022 IEEE 18th International Conference on Automa- tion Science and Engineering (CASE). IEEE, 2022, pp. 2110–2117

    work page 2022

  9. [9]

    Integrated task assignment and path planning for capacitated multi- agent pickup and delivery,

    Z. Chen, J. Alonso-Mora, X. Bai, D. D. Harabor, and P. J. Stuckey, “Integrated task assignment and path planning for capacitated multi- agent pickup and delivery,”IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 5816–5823, 2021

    work page 2021

  10. [10]

    Consensus-based decentralized auctions for robust task allocation,

    H.-L. Choi, L. Brunet, and J. P. How, “Consensus-based decentralized auctions for robust task allocation,”IEEE transactions on robotics, vol. 25, no. 4, pp. 912–926, 2009

    work page 2009

  11. [11]

    Decentral task allocation for industrial agv-systems with routing constraints,

    M. De Ryck, D. Pissoort, T. Holvoet, and E. Demeester, “Decentral task allocation for industrial agv-systems with routing constraints,”Journal of Manufacturing Systems, vol. 62, pp. 135–144, 2022

    work page 2022

  12. [12]

    Multi-robot auctions for allocation of tasks with temporal constraints,

    E. Nunes and M. Gini, “Multi-robot auctions for allocation of tasks with temporal constraints,” inProceedings of the AAAI conference on artificial intelligence, vol. 29, no. 1, 2015

    work page 2015

  13. [13]

    Distributed algorithms for multirobot task assignment with task deadline constraints,

    L. Luo, N. Chakraborty, and K. Sycara, “Distributed algorithms for multirobot task assignment with task deadline constraints,”IEEE Trans- actions on Automation Science and Engineering, vol. 12, no. 3, pp. 876–888, 2015. 15

    work page 2015

  14. [14]

    Multi-objective optimisation of multi-robot task allocation with prece- dence constraints

    K. Padmanabhan Panchu, M. Rajmohan, R. Sundar, and R. Baskaran, “Multi-objective optimisation of multi-robot task allocation with prece- dence constraints.”Defence Science Journal, vol. 68, no. 2, 2018

    work page 2018

  15. [15]

    Multi-robot task allocation using clustering method,

    F. Janati, F. Abdollahi, S. S. Ghidary, M. Jannatifar, J. Baltes, and S. Sadeghnejad, “Multi-robot task allocation using clustering method,” inRobot Intelligence Technology and Applications 4: Results from the 4th International Conference on Robot Intelligence Technology and Applications. Springer, 2016, pp. 233–247

    work page 2016

  16. [16]

    Mobile robot naviga- tion system based on probabilistic road map (prm) with halton sampling of configuration space,

    J. Velagi ´c, D. Delimustafi ´c, and D. Osmankovi ´c, “Mobile robot naviga- tion system based on probabilistic road map (prm) with halton sampling of configuration space,” in2014 IEEE 23rd International Symposium on Industrial Electronics (ISIE). IEEE, 2014, pp. 1227–1232

    work page 2014

  17. [17]

    Deterministic sampling-based motion planning: Optimality, complexity, and performance,

    L. Janson, B. Ichter, and M. Pavone, “Deterministic sampling-based motion planning: Optimality, complexity, and performance,”The Inter- national Journal of Robotics Research, vol. 37, no. 1, pp. 46–61, 2018

    work page 2018

  18. [18]

    Research on sbmpc algorithm for path planning of rescue and detection robot,

    L.-L. Wang and L.-X. Pan, “Research on sbmpc algorithm for path planning of rescue and detection robot,”Discrete Dynamics in Nature and Society, vol. 2020, no. 1, p. 7821942, 2020

    work page 2020

  19. [19]

    Obstacle aware sampling for path planning,

    M. Tukan, A. Maalouf, D. Feldman, and R. Poranne, “Obstacle aware sampling for path planning,” in2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2022, pp. 13 676– 13 683

    work page 2022

  20. [20]

    Real-time path planning for robot using op-prm in complex dynamic environment,

    L. Ye, J. Chen, and Y . Zhou, “Real-time path planning for robot using op-prm in complex dynamic environment,”Frontiers in Neurorobotics, vol. 16, p. 910859, 2022

    work page 2022

  21. [21]

    A novel multi- robot task assignment scheme based on a multi-angle k-means clustering algorithm and a two-stage load-balancing strategy,

    J. You, J. Jia, X. Pang, J. Wen, Y . Shi, and J. Zeng, “A novel multi- robot task assignment scheme based on a multi-angle k-means clustering algorithm and a two-stage load-balancing strategy,”Electronics, vol. 12, no. 18, p. 3842, 2023

    work page 2023

  22. [22]

    An algorithm for task allocation and planning for a heterogeneous multi-robot system to minimize the last task completion time,

    A. Patil, J. Bae, and M. Park, “An algorithm for task allocation and planning for a heterogeneous multi-robot system to minimize the last task completion time,”Sensors, vol. 22, no. 15, p. 5637, 2022

    work page 2022

  23. [23]

    GPT-4 Technical Report

    J. Achiam, S. Adler, S. Agarwal, L. Ahmad, I. Akkaya, F. L. Aleman, D. Almeida, J. Altenschmidt, S. Altman, S. Anadkatet al., “Gpt-4 technical report,”arXiv preprint arXiv:2303.08774, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  24. [24]

    A comprehensive capability analysis of gpt-3 and gpt-3.5 series models,

    J. Ye, X. Chen, N. Xu, C. Zu, Z. Shao, S. Liu, Y . Cui, Z. Zhou, C. Gong, Y . Shenet al., “A comprehensive capability analysis of gpt-3 and gpt-3.5 series models,”arXiv preprint arXiv:2303.10420, 2023

    work page arXiv 2023

  25. [25]

    The Llama 3 Herd of Models

    A. Grattafiori, A. Dubey, A. Jauhri, A. Pandey, A. Kadian, A. Al-Dahle, A. Letman, A. Mathur, A. Schelten, A. Vaughanet al., “The llama 3 herd of models,”arXiv preprint arXiv:2407.21783, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  26. [26]

    Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context

    G. Team, P. Georgiev, V . I. Lei, R. Burnell, L. Bai, A. Gulati, G. Tanzer, D. Vincent, Z. Pan, S. Wanget al., “Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context,”arXiv preprint arXiv:2403.05530, 2024

    work page internal anchor Pith review Pith/arXiv arXiv 2024

  27. [27]

    Llm-based multi-agent rein- forcement learning: Current and future directions,

    C. Sun, S. Huang, and D. Pompili, “Llm-based multi-agent rein- forcement learning: Current and future directions,”arXiv preprint arXiv:2405.11106, 2024

    work page arXiv 2024

  28. [28]

    Autotamp: Autoregressive task and motion planning with llms as translators and checkers,

    Y . Chen, J. Arkin, C. Dawson, Y . Zhang, N. Roy, and C. Fan, “Autotamp: Autoregressive task and motion planning with llms as translators and checkers,” in2024 IEEE International conference on robotics and automation (ICRA). IEEE, 2024, pp. 6695–6702

    work page 2024

  29. [29]

    Lang2ltl: Translating natural language commands to temporal specification with large language models,

    J. X. Liu, Z. Yang, B. Schornstein, S. Liang, I. Idrees, S. Tellex, and A. Shah, “Lang2ltl: Translating natural language commands to temporal specification with large language models,” inWorkshop on Language and Robotics at CoRL 2022, 2022

    work page 2022

  30. [30]

    Lamma-p: General- izable multi-agent long-horizon task allocation and planning with lm- driven pddl planner,

    X. Zhang, H. Qin, F. Wang, Y . Dong, and J. Li, “Lamma-p: General- izable multi-agent long-horizon task allocation and planning with lm- driven pddl planner,”arXiv preprint arXiv:2409.20560, 2024

    work page arXiv 2024

  31. [31]

    Smart-llm: Smart multi-agent robot task planning using large language models,

    S. S. Kannan, V . L. Venkatesh, and B.-C. Min, “Smart-llm: Smart multi-agent robot task planning using large language models,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2024, pp. 12 140–12 147

    work page 2024

  32. [32]

    Do As I Can, Not As I Say: Grounding Language in Robotic Affordances

    M. Ahn, A. Brohan, N. Brown, Y . Chebotar, O. Cortes, B. David, C. Finn, C. Fu, K. Gopalakrishnan, K. Hausmanet al., “Do as i can, not as i say: Grounding language in robotic affordances,”arXiv preprint arXiv:2204.01691, 2022

    work page internal anchor Pith review Pith/arXiv arXiv 2022

  33. [33]

    Language models as zero-shot planners: Extracting actionable knowledge for embodied agents,

    W. Huang, P. Abbeel, D. Pathak, and I. Mordatch, “Language models as zero-shot planners: Extracting actionable knowledge for embodied agents,” inInternational conference on machine learning. PMLR, 2022, pp. 9118–9147

    work page 2022

  34. [34]

    Large Language Models for Multi-Robot Systems: A Survey

    P. Li, Z. An, S. Abrar, and L. Zhou, “Large language models for multi- robot systems: A survey,”arXiv preprint arXiv:2502.03814, 2025

    work page internal anchor Pith review Pith/arXiv arXiv 2025

  35. [35]

    Vader: Visual affordance detection and error recovery for multi robot human collaboration,

    M. Ahn, M. G. Arenas, M. Bennice, N. Brown, C. Chan, B. David, A. Francis, G. Gonzalez, R. Hessmer, T. Jacksonet al., “Vader: Visual affordance detection and error recovery for multi robot human collaboration,”arXiv preprint arXiv:2405.16021, 2024

    work page arXiv 2024

  36. [36]

    Conversational language models for human-in-the-loop multi-robot coordination,

    W. Hunt, T. Godfrey, and M. D. Soorati, “Conversational language models for human-in-the-loop multi-robot coordination,”arXiv preprint arXiv:2402.19166, 2024

    work page arXiv 2024

  37. [37]

    Llm-mars: Large language model for behavior tree generation and nlp-enhanced di- alogue in multi-agent robot systems,

    A. Lykov, M. Dronova, N. Naglov, M. Litvinov, S. Satsevich, A. Bazhenov, V . Berman, A. Shcherbak, and D. Tsetserukou, “Llm-mars: Large language model for behavior tree generation and nlp-enhanced di- alogue in multi-agent robot systems,”arXiv preprint arXiv:2312.09348, 2023

    work page arXiv 2023

  38. [38]

    Multiple task assignments for cooperating uninhabited aerial vehicles using genetic algorithms,

    T. Shima, S. J. Rasmussen, A. G. Sparks, and K. M. Passino, “Multiple task assignments for cooperating uninhabited aerial vehicles using genetic algorithms,”Computers & operations research, vol. 33, no. 11, pp. 3252–3269, 2006

    work page 2006

  39. [39]

    A coalition formation algorithm for multi-robot task allocation in large-scale natural disasters,

    C. Mouradian, J. Sahoo, R. H. Glitho, M. J. Morrow, and P. A. Polakos, “A coalition formation algorithm for multi-robot task allocation in large-scale natural disasters,” in2017 13th international wireless communications and mobile computing conference (IWCMC). IEEE, 2017, pp. 1909–1914

    work page 2017

  40. [40]

    Real-time city-scale ridesharing via linear assignment problems,

    A. Simonetto, J. Monteil, and C. Gambella, “Real-time city-scale ridesharing via linear assignment problems,”Transportation Research Part C: Emerging Technologies, vol. 101, pp. 208–232, 2019

    work page 2019

  41. [41]

    Multi-robot task allocation and scheduling considering cooperative tasks and precedence constraints,

    E. Bischoff, F. Meyer, J. Inga, and S. Hohmann, “Multi-robot task allocation and scheduling considering cooperative tasks and precedence constraints,” in2020 IEEE international conference on systems, man, and cybernetics (SMC). IEEE, 2020, pp. 3949–3956

    work page 2020

  42. [42]

    Auctions for multi-robot task allocation in communication limited environments,

    M. Otte, M. J. Kuhlman, and D. Sofge, “Auctions for multi-robot task allocation in communication limited environments,”Autonomous Robots, vol. 44, pp. 547–584, 2020

    work page 2020

  43. [43]

    A sequential task addition distributed assignment algorithm for multi-robot systems,

    N. Lindsay, R. K. Buehling, and L. Sun, “A sequential task addition distributed assignment algorithm for multi-robot systems,”Journal of Intelligent & Robotic Systems, vol. 102, no. 2, p. 51, 2021

    work page 2021

  44. [44]

    Group-based distributed auction algorithms for multi-robot task as- signment,

    X. Bai, A. Fielbaum, M. Kronm ¨uller, L. Knoedler, and J. Alonso-Mora, “Group-based distributed auction algorithms for multi-robot task as- signment,”IEEE Transactions on Automation Science and Engineering, vol. 20, no. 2, pp. 1292–1303, 2022

    work page 2022

  45. [45]

    A heuristic distributed task allocation method for multivehicle multitask problems and its application to search and rescue scenario,

    W. Zhao, Q. Meng, and P. W. Chung, “A heuristic distributed task allocation method for multivehicle multitask problems and its application to search and rescue scenario,”IEEE transactions on cybernetics, vol. 46, no. 4, pp. 902–915, 2015

    work page 2015

  46. [46]

    Rtaw: An attention inspired reinforcement learning method for multi-robot task allocation in ware- house environments,

    A. Agrawal, A. S. Bedi, and D. Manocha, “Rtaw: An attention inspired reinforcement learning method for multi-robot task allocation in ware- house environments,”arXiv preprint arXiv:2209.05738, 2022

    work page arXiv 2022

  47. [47]

    Magnnet: Multi-agent graph neural network-based efficient task allocation for autonomous vehicles with deep reinforcement learning,

    L. Ratnabala, A. Fedoseev, R. Peter, and D. Tsetserukou, “Magnnet: Multi-agent graph neural network-based efficient task allocation for autonomous vehicles with deep reinforcement learning,”arXiv preprint arXiv:2502.02311, 2025

    work page arXiv 2025

  48. [48]

    Scalable multi-robot task allocation using graph deep reinforcement learning with graph normalization,

    Z. Zhang, X. Jiang, Z. Yang, S. Ma, J. Chen, and W. Sun, “Scalable multi-robot task allocation using graph deep reinforcement learning with graph normalization,”Electronics, vol. 13, no. 8, p. 1561, 2024

    work page 2024

  49. [49]

    Towards learning-based distributed task allocation approach for multi- robot system,

    Z. Chekakta, N. Aouf, S. Govindaraj, F. Polisano, and G. De Cubber, “Towards learning-based distributed task allocation approach for multi- robot system,” in2024 10th International Conference on Automation, Robotics and Applications (ICARA). IEEE, 2024, pp. 34–39

    work page 2024

  50. [50]

    Multi-goal multi-agent pickup and delivery,

    Q. Xu, J. Li, S. Koenig, and H. Ma, “Multi-goal multi-agent pickup and delivery,” in2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2022, pp. 9964–9971

    work page 2022

  51. [51]

    Conflict- based search with optimal task assignment,

    W. H ¨onig, S. Kiesel, A. Tinka, J. Durham, and N. Ayanian, “Conflict- based search with optimal task assignment,” inProceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, 2018

    work page 2018

  52. [52]

    Lifelong Multi-Agent Path Finding for Online Pickup and Delivery Tasks

    H. Ma, J. Li, T. Kumar, and S. Koenig, “Lifelong multi-agent path finding for online pickup and delivery tasks,”arXiv preprint arXiv:1705.10868, 2017

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  53. [53]

    A survey of optimization-based task and motion planning: From classical to learning approaches,

    Z. Zhao, S. Cheng, Y . Ding, Z. Zhou, S. Zhang, D. Xu, and Y . Zhao, “A survey of optimization-based task and motion planning: From classical to learning approaches,”IEEE/ASME Transactions on Mechatronics, 2024

    work page 2024

  54. [54]

    Text2motion: From natural language instructions to feasible plans,

    K. Lin, C. Agia, T. Migimatsu, M. Pavone, and J. Bohg, “Text2motion: From natural language instructions to feasible plans,”Autonomous Robots, vol. 47, no. 8, pp. 1345–1365, 2023

    work page 2023

  55. [55]

    Translating natural language to planning goals with large-language models,

    Y . Xie, C. Yu, T. Zhu, J. Bai, Z. Gong, and H. Soh, “Translating natural language to planning goals with large-language models,”arXiv preprint arXiv:2302.05128, 2023

    work page arXiv 2023

  56. [56]

    LLM+P: Empowering Large Language Models with Optimal Planning Proficiency

    B. Liu, Y . Jiang, X. Zhang, Q. Liu, S. Zhang, J. Biswas, and P. Stone, “Llm+ p: Empowering large language models with optimal planning proficiency,”arXiv preprint arXiv:2304.11477, 2023

    work page internal anchor Pith review Pith/arXiv arXiv 2023

  57. [57]

    Auto- matic behavior tree expansion with llms for robotic manipulation,

    J. Styrud, M. Iovino, M. Norrl ¨of, M. Bj ¨orkman, and C. Smith, “Auto- matic behavior tree expansion with llms for robotic manipulation,”arXiv preprint arXiv:2409.13356, 2024. 16

    work page arXiv 2024

  58. [58]

    Lang2ltl-2: Grounding spatiotemporal navigation commands using large language and vision-language models,

    J. X. Liu, A. Shah, G. Konidaris, S. Tellex, and D. Paulius, “Lang2ltl-2: Grounding spatiotemporal navigation commands using large language and vision-language models,” in2024 IEEE/RSJ International Confer- ence on Intelligent Robots and Systems (IROS). IEEE, 2024, pp. 2325– 2332

    work page 2024

  59. [59]

    Modern hierarchical, agglomerative clustering algorithms

    D. M ¨ullner, “Modern hierarchical, agglomerative clustering algorithms,” arXiv preprint arXiv:1109.2378, 2011

    work page internal anchor Pith review Pith/arXiv arXiv 2011

  60. [60]

    A multi-robot task allocation method based on the synergy of the k-means++ algorithm and the particle swarm algorithm,

    Y . Yuan, P. Yang, H. Jiang, and T. Shi, “A multi-robot task allocation method based on the synergy of the k-means++ algorithm and the particle swarm algorithm,”Biomimetics, vol. 9, no. 11, p. 694, 2024

    work page 2024

  61. [61]

    Integer programming formulation of traveling salesman problems,

    C. E. Miller, A. W. Tucker, and R. A. Zemlin, “Integer programming formulation of traveling salesman problems,”Journal of the ACM (JACM), vol. 7, no. 4, pp. 326–329, 1960

    work page 1960

  62. [62]

    Fast ltl to b ¨uchi automata translation,

    P. Gastin and D. Oddoux, “Fast ltl to b ¨uchi automata translation,” in International Conference on Computer Aided Verification. Springer, 2001, pp. 53–65

    work page 2001

  63. [63]

    Ltl-d*: Incrementally optimal replanning for feasible and infeasible tasks in linear temporal logic specifications,

    J. Ren, H. Miller, K. M. Feigh, S. Coogan, and Y . Zhao, “Ltl-d*: Incrementally optimal replanning for feasible and infeasible tasks in linear temporal logic specifications,” in2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE, 2024, pp. 4495–4502

    work page 2024

  64. [64]

    Fast replanning for navigation in unknown terrain,

    S. Koenig and M. Likhachev, “Fast replanning for navigation in unknown terrain,”IEEE transactions on robotics, vol. 21, no. 3, pp. 354–363, 2005

    work page 2005

  65. [65]

    Nvidia isaac sim,

    NVIDIA, “Nvidia isaac sim,” https://developer.nvidia.com/isaac/sim, 2025, accessed: 2025-10-09

    work page 2025

  66. [66]

    Integrated task and motion planning for safe legged navigation in partially observ- able environments,

    A. Shamsah, Z. Gu, J. Warnke, S. Hutchinson, and Y . Zhao, “Integrated task and motion planning for safe legged navigation in partially observ- able environments,”IEEE Transactions on Robotics, vol. 39, no. 6, pp. 4913–4934, 2023

    work page 2023

  67. [67]

    Accelerating signal-temporal-logic-based task and motion planning of bipedal navigation using benders decomposition,

    J. Ren, X. Lin, R. Mineyev, K. M. Feigh, S. Coogan, and Y . Zhao, “Accelerating signal-temporal-logic-based task and motion planning of bipedal navigation using benders decomposition,”arXiv preprint arXiv:2508.13407, 2025

    work page arXiv 2025