CoChat
Sign Up
Cited by 19Robot Manipulation and LearningRobotic Mechanisms and DynamicsFault Detection and Control Systems

Hybrid Fault-Tolerant Control in Cooperative Robotics: Advances in Resilience and Scalability

Open access
Urrea, Claudio·2025·Actuators
DOI 10.3390/act14040177
Open this paper in CoChat — free accountOpen PDF

Abstract

Cooperative robotics relies on robust fault-tolerant control (FTC) to maintain resilience in dynamic environments, where actuators are pivotal to system reliability. This review synthesizes advancements in hybrid FTC, integrating mechanical redundancy with electronic adaptability and learning-based techniques like deep reinforcement learning and swarm-optimized control, drawing from interdisciplinary evidence across manufacturing, healthcare, agriculture, space exploration, and underwater robotics. It examines how these approaches enhance uptime, precision, and coordination in multi-robot systems, reporting significant improvements despite physical validation being limited to approximately one-quarter of strategies. Addressing gaps in prior work by overcoming limitations of traditional methods, it extends to Construction 5.0, supporting human–robot collaboration (HRC) through scalability and adaptability. Future efforts will prioritize broader testing, standardized benchmarks, safety considerations, and optimization under uncertainty to align theoretical gains with practical outcomes, enhancing resilient automation across domains.

AI snapshot

Written from the paper’s full text.

TL;DR

This review synthesizes hybrid fault-tolerant control for cooperative robotics, combining passive robustness, active fault detection/diagnosis, and learning-based methods across manufacturing, healthcare, agriculture, space, and underwater domains. It reports strong simulation-based gains in resilience, precision, and scalability, but physical validation remains limited to roughly 23% of reported strategies.

Key findings

  • Hybrid FTC integrates mechanical redundancy with electronic adaptability and learning-based techniques, with reported outcomes including sub-0.017 s recovery, 98% resilience, neural-adaptive control at ~94% accuracy, gain scheduling at ≥90% accuracy, and hybrid AI at 95% efficiency with 20–30% overhead.
  • Physical validation is a major gap: only approximately 23% of reported strategies are tested beyond simulations, limiting generalizability of reported resilience and efficiency gains.
  • Scalability is constrained: centralized architectures drop in performance beyond 100 robots, decentralized control can handle up to 200 agents, distributed control manages fleets of 5–50 robots, and latency increases beyond 50 units.
  • Applications span manufacturing, healthcare, agriculture, space exploration, underwater robotics, and Construction 5.0/human-robot collaboration, with examples such as 85% uptime in uneven environments, 92% capacity for dual actuators, and 95% efficiency in some hybrid systems.

Methods

  • This is a review/synthesis of existing literature on hybrid fault-tolerant control in cooperative robotics, drawing evidence from manufacturing, healthcare, agriculture, space exploration, underwater robotics, and Construction 5.0.
  • No new experimental data were generated; the paper states that data are contained within the article and that it synthesizes existing literature.
  • The main analysis is qualitative and tabular, comparing passive FTC, active FTC, redundancy strategies, learning-based fault tolerance, hybrid mechanical-electronic systems, scalability architectures, and future directions.

Limitations

  • The paper explicitly states that physical validation remains limited to approximately 23% of reported strategies tested beyond simulations, undermining generalizability and leaving a simulation-to-practice gap.
  • It also identifies scalability limits beyond small fleets, high computational demands from neural/learning-based methods, and the need for standardized benchmarks, safety considerations, and optimization under uncertainty.
  • Evident from the text: as a review, it does not independently validate the cited quantitative results; the manuscript also contains duplicated/garbled passages and inconsistent citation formatting, which may affect reliability.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.3390/act14040177

Cites

58 of 59 references verified0 citation errors · 1 not checkable

Statistics

Nothing to recompute.

Claims the paper makes

21 of 98 cited sources checked · 2 supported · 0 flagged · accuracy not yet measured

  • Premisecitation

    Approximately 23% of reported fault-tolerant strategies have been physically validated.

    “The field remains constrained by limited physical validation-approximately 23% of reported strategies [3]-prompting a need for future efforts to bridge simulation and practice.”
    Quote in the paperSubstantial claim1 of 2 sources checked
    • cites [3] Iriarte, 2024, An Overactuated Aerial Robot Based on Cooperative Quadrotors Attached Through Passive Universal Joints: Modeling, Control and 6-DoF Trajectory Tracking, Robot. Auton. Syst. source
    • cites [45] Gedeon, 2024, Cognitive Digital Twin-Based Internet of Robotic Things, Multi-Sensory Extended Reality and Simulation Modeling Technologies, and Generative Artificial Intelligence and Cyber-Physical Manufacturing Systems in the Immersive Industrial Metaverse, Equilibrium. Q. J. Econ. Econ. Policy source

      The Introduction discusses digital-twin modeling and simulation, and the section on interconnected IoRT discusses monitoring and predictive maintenance, but neither addresses physical validation of fault-tolerant strategies. Searches for the claimed 23% figure, fault-tolerant strategies, and physical validation found no supporting passage in our copy; the retrieved passages have no page numbers. (LLM, conf=0.76)

      Experimental — accuracy not yet measured
  • Premisecitation

    Manufacturing benefits from hybrid systems reducing downtime through parallel kinematics and adaptive control.

    “Manufacturing benefits from hybrid systems reducing downtime through parallel kinematics and adaptive control [38,41]”
    Quote in the paperNot a substantial claim1 of 2 sources checked
    • cites [38] Liu, 2024, Blockchain-Based Cloud-Edge Collaborative Data Management for Human-Robot Collaboration Digital Twin System, J. Manuf. Syst. source
    • cites [41] Zhang, J., Jiang, W., and Ge, S.S. (2025). Adaptive Fuzzy Fault-Tolerant Control via Integral Terminal Sliding Mode of Robotic Systems with Prescribed Performance. Asian J. Control, 1–11. in press. source

      The Introduction (page not provided) places robotic control in a manufacturing context and says adaptive fault-tolerant control helps robots operate reliably when faults occur. The paper does not address hybrid systems, parallel kinematics, or reduced downtime, so it supports only the adaptive-control portion of the claim. (LLM, conf=0.84)

      Experimental — accuracy not yet measured
  • Interpretationcitation

    Hybrid and bioinspired methods outperform isolated approaches by balancing stiffness and flexibility.

    “These methods outperform isolated approaches by balancing stiffness and flexibility [46].”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [46] Ferrari, 2024, Hybrid Cooperative Control of Functional Electrical Stimulation and Robot Assistance for Upper Extremity Rehabilitation, IEEE Trans. Biomed. Eng. source

      The Introduction and Discussion (pages unavailable in our copy) support a narrower advantage for hybrid FES–robot assistance: better tracking than FES alone while using less motor torque than motor-only assistance. The Discussion also reports worse tracking than motor-only assistance. The paper does not describe a bioinspired method or attribute these trade-offs to balancing stiffness and flexibility. (LLM, conf=0.86)

      Experimental — accuracy not yet measured
  • Premisecitation

    Hybrid AI methods integrating fuzzy logic, neural networks, and reinforcement learning with a three-layer fusion model improve efficiency in multi-agent human-robot collaboration with moderate overhead.

    “Hybrid Artificial Intelligence (AI) methods integrate fuzzy logic, neural networks, and RL with a three-layer fusion model, improving efficiency in multi-agent HRC [8,41], with moderate overhead [42].”
    Quote in the paperNot a substantial claim1 of 3 sources checked
    • cites [8] Gong, 2025, An Adaptive Fault-Tolerant Control Scheme for Heterogeneous Multiagent Systems, IEEE Trans. Syst. Man Cybern. Syst. source
    • cites [41] Zhang, J., Jiang, W., and Ge, S.S. (2025). Adaptive Fuzzy Fault-Tolerant Control via Integral Terminal Sliding Mode of Robotic Systems with Prescribed Performance. Asian J. Control, 1–11. in press. source

      The Introduction discusses fuzzy logic and neural networks for handling uncertainty in robotic control, while the Simulation Results examine a two-link robot. Neither passage addresses reinforcement learning, a three-layer fusion model, multi-agent human–robot collaboration, efficiency gains, or overhead. Searches for those terms found no supporting passage in our copy. (LLM, conf=0.76)

      Experimental — accuracy not yet measured
    • cites [42] Sandini, 2024, Collaborative Robots with Cognitive Capabilities for Industry 4.0 and Beyond, AI source
  • Premisecitation

    Integration of mechanical and electronic components increases costs.

    “However, integration increases costs [41]”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [41] Zhang, J., Jiang, W., and Ge, S.S. (2025). Adaptive Fuzzy Fault-Tolerant Control via Integral Terminal Sliding Mode of Robotic Systems with Prescribed Performance. Asian J. Control, 1–11. in press. source

      The Introduction discusses robotic control challenges and controller design, but does not address the cost of integrating mechanical and electronic components. Searches for integration and cost-related terms found no passage supporting or contradicting the claim. (LLM, conf=0.76)

      Experimental — accuracy not yet measured
  • May combine two claims. 33
  • Classified as probably not a substantial claim. 25

  • May combine two claims.

    Premisecitation

    Neural-adaptive systems achieve high accuracy under actuator faults, demonstrated in multi-joint tracking with up to 94% accuracy.

    “leverage neural networks with architectures detailed in Section Key Technical Methods in Hybrid FTC to achieve high accuracy under actuator faults, as demonstrated in multi-joint tracking with up to 94% accuracy [11].”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [11] Le, Q.D., and Yang, E. (2024). Adaptive Fault-Tolerant Tracking Control for Multi-Joint Robot Manipulators via Neural Network-Based Synchronization. Sensors, 24. source

      Section 4.2 (page unavailable) reports that the neural-network controller outperformed comparison controllers in simulated multi-joint tracking with actuator faults. It reports tracking errors in radians, not accuracy as a percentage; the claimed 94% accuracy is unsupported. (LLM, conf=0.86)

      Experimental — accuracy not yet measured

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Educational applications show improved outcomes through robotic training.

    “Educational applications show improved outcomes through robotic training [48]”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [48] Acvi, 2024, Effects of robotic module-supported experimental activities with the cooperative learning method on student achievement, 21st-century skills, and students’ opinions, J. Comput. Assist. Learn. source

  • May combine two claims.

    Premisecitation

    Digital Twins operating at a 10 Hz simulation rate reduce testing cycles and improve human-robot collaboration planning accuracy, despite minor synchronization lags.

    “Digital Twins, operating at a 10 Hz simulation rate, reduce testing cycles and improve HRC planning accuracy [45], despite minor synchronization lags [11].”
    Quote in the paperNot a substantial claim2 of 2 sources checked
    • cites [45] Gedeon, 2024, Cognitive Digital Twin-Based Internet of Robotic Things, Multi-Sensory Extended Reality and Simulation Modeling Technologies, and Generative Artificial Intelligence and Cyber-Physical Manufacturing Systems in the Immersive Industrial Metaverse, Equilibrium. Q. J. Econ. Econ. Policy source

      The section on interconnected IoRT and cloud-connected devices describes digital-twin simulation for robotic manufacturing and integrated process planning. It does not report a 10 Hz simulation rate, shorter testing cycles, or improved human–robot collaboration planning accuracy. The synchronization-lag clause is cited to [11], not this source. (LLM, conf=0.78)

      Experimental — accuracy not yet measured
    • cites [11] Le, Q.D., and Yang, E. (2024). Adaptive Fault-Tolerant Tracking Control for Multi-Joint Robot Manipulators via Neural Network-Based Synchronization. Sensors, 24. source

      The citation to this source, [11], is attached to “despite minor synchronization lags,” not to the preceding claims cited to [45]. Section 4.2 reports delayed feedback from a fault estimator in a robot-controller simulation, but does not address synchronization lags in a Digital Twin. Searches for Digital Twins, a 10 Hz rate, and synchronization latency found no passage supporting that qualifier. (LLM, conf=0.76)

      Experimental — accuracy not yet measured

  • May combine two claims.

    Premisecitation

    Neural-adaptive control utilizing a 128-node recurrent neural network delivers rapid responses in surgery and UAV swarms and achieves high accuracy in construction human-robot collaboration, despite significant computational demands.

    “Neural-adaptive control, utilizing a 128-node RNN, delivers rapid responses in surgery [11] and UAV swarms [27], achieving high accuracy in construction HRC [40], despite significant computational demands [10].”
    Quote in the paperNot a substantial claim1 of 3 sources checked
    • cites [11] Le, Q.D., and Yang, E. (2024). Adaptive Fault-Tolerant Tracking Control for Multi-Joint Robot Manipulators via Neural Network-Based Synchronization. Sensors, 24. source
    • cites [27] Wang, 2024, Distributed Observer-Based Close Formation Control for UAV Swarm under Outside Disturbances and Wake Interferences, J. Frankl. Inst. source
    • cites [40] Mahmud, 2025, A Knowledge-Driven Framework for Robotic Odor Source Localization Using Large Language Models, Robot. Auton. Syst. source

  • May combine two claims.

    Premisecitation

    Swarm-based and bioinspired approaches enhance connectivity and sustain operations, as evidenced in agricultural systems with improved uptime.

    “Swarm-based and bioinspired approaches enhance connectivity, leveraging distributed coordination to sustain operations, as evidenced in agricultural systems with improved uptime [14].”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [14] Moshayedi, 2025, Advancing Agricultural Practices: Analyzing the Role of Robotics in Corn Farming, Int. J. Eng. Trans. A Basics source

      The Swarm Robotics section says multiple robots can collaborate and communicate, and projects that improved autonomy could enable 24/7 operation. The Communication Systems section also describes connectivity for autonomous operation. Neither passage establishes a bioinspired approach or reports improved uptime in an agricultural system; the sustained operation is a future prospect, not a demonstrated result. (LLM, conf=0.88)

      Experimental — accuracy not yet measured

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Tensegrity-enhanced designs using a 0.5 stiffness coefficient improve energy efficiency in corn farming.

    “with tensegrityenhanced designs using a 0.5 stiffness coefficient improving energy efficiency in corn farming [14].”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [14] Moshayedi, 2025, Advancing Agricultural Practices: Analyzing the Role of Robotics in Corn Farming, Int. J. Eng. Trans. A Basics source

      The Power Source section discusses fuel efficiency in hybrid systems, but does not connect it to tensegrity designs. Searches for tensegrity and a 0.5 stiffness coefficient found no passage in our copy addressing the claimed design or its effect on energy efficiency in corn farming. (LLM, conf=0.73)

      Experimental — accuracy not yet measured

  • May combine two claims.

    Interpretationcitation

    Fault-tolerant cooperative robotics faces significant barriers in scalability, computational complexity, and real-world validation.

    “Fault-tolerant cooperative robotics faces significant barriers in scalability, computational complexity, and real-world validation, as highlighted across the literature.”
    • Also stated in: § 7. Discussion · plain
      “Key challenges persist in scalability, computational complexity, and validation, as noted across the literature.”
    Quote in the paperSubstantial claim1 of 3 sources checked
    • cites [9] Tian, 2025, Research on Kiwifruit Harvesting Robot Worldwide: A Solution for Sustainable Development of Kiwifruit Industry, Smart Agric. Technol. source
    • cites [12] Zhao, 2025, Safety-Efficiency Integrated Assembly: The Next-Stage Adaptive Task Allocation and Planning Framework for Human–Robot Collaboration, Robot. Comput. Integr. Manuf. source
    • cites [14] Moshayedi, 2025, Advancing Agricultural Practices: Analyzing the Role of Robotics in Corn Farming, Int. J. Eng. Trans. A Basics source

      The Discussion and Table 2 in the Conclusion identify scalability across different farm sizes as a challenge for corn-farming robots. They do not establish barriers in computational complexity or real-world validation for fault-tolerant cooperative robotics; the Case Studies section instead describes field tests of individual robots. Page numbers were not provided in our copy. (LLM, conf=0.86)

      Experimental — accuracy not yet measured

  • May combine two claims.

    Premisecitation

    Mechanical redundancy approaches face limitations such as a 20% mass increase affecting mobility or complex fabrication needs.

    “These approaches, while effective in predictable settings, face limitations such as a 20% mass increase affecting mobility [3] or complex fabrication needs [14].”
    Quote in the paperNot a substantial claim1 of 2 sources checked
    • cites [3] Iriarte, 2024, An Overactuated Aerial Robot Based on Cooperative Quadrotors Attached Through Passive Universal Joints: Modeling, Control and 6-DoF Trajectory Tracking, Robot. Auton. Syst. source
    • cites [14] Moshayedi, 2025, Advancing Agricultural Practices: Analyzing the Role of Robotics in Corn Farming, Int. J. Eng. Trans. A Basics source

      The paper’s ‘Common Structure and Parts of Robot’ section discusses chassis materials, payloads, and mobility, but does not report a 20% mass increase or link one to reduced mobility. Searches for ‘20% mass increase affecting mobility’ and ‘mechanical redundancy mass weight mobility fabrication’ found no passage addressing that claim. The fabrication clause is attributed to [14], not this source. (LLM, conf=0.74)

      Experimental — accuracy not yet measured

  • May combine two claims.

    Premisecitation

    Hybrid mechanical-electronic systems offer a synergistic advantage over purely mechanical systems, which lack adaptability, and electronic-only approaches prone to hardware limits.

    “Compared to purely mechanical systems, which lack adaptability, or electronic-only approaches prone to hardware limits, hybrid systems offer a synergistic advantage, as seen in manufacturing with dual-drive redundancy reducing motor power [41] and surgery with efficient laparoscopic outcomes [31].”
    Quote in the paperSubstantial claim1 of 2 sources checked
    • cites [41] Zhang, J., Jiang, W., and Ge, S.S. (2025). Adaptive Fuzzy Fault-Tolerant Control via Integral Terminal Sliding Mode of Robotic Systems with Prescribed Performance. Asian J. Control, 1–11. in press. source

      The Introduction discusses adaptive fault-tolerant control for robotic systems, and the Simulation Results concern a two-link robot. Neither section addresses hybrid mechanical-electronic systems, their comparison with purely mechanical or electronic-only approaches, or laparoscopic outcomes (searched: laparoscopic surgery, hybrid mechanical-electronic systems, and hardware limits). (LLM, conf=0.76)

      Experimental — accuracy not yet measured
    • cites [31] Yamamoto, 2024, RoboLap Cooperative Technique for Lymphadenectomy in Robotic Surgery for Right-Sided Colon Cancer—A Video Vignette, Color. Dis. source

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Healthcare leverages neural synchronization for reliable surgical outcomes.

    “and healthcare leverages neural synchronization for reliable surgical outcomes [11,13].”
    Quote in the paperNot a substantial claim1 of 2 sources checked
    • cites [11] Le, Q.D., and Yang, E. (2024). Adaptive Fault-Tolerant Tracking Control for Multi-Joint Robot Manipulators via Neural Network-Based Synchronization. Sensors, 24. source

      The Introduction describes a controller combining neural networks and synchronization for fault-tolerant robot manipulators, and Section 4.2 reports improved performance in simulation. The paper does not establish that healthcare uses this approach or that it produces reliable surgical outcomes; Section 5 says its practical viability in real-world robotic systems remains to be verified. (LLM, conf=0.84)

      Experimental — accuracy not yet measured
    • cites [13] Du, 2024, Analyzing Surgeon–Robot Cooperative Performance in Robot-Assisted Intravascular Catheterization, IEEE Trans. Hum. Mach. Syst. source

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Digital Twins with a 10 Hz simulation rate improve maintenance planning in manufacturing.

    “Digital Twins with a 10 Hz simulation rate improve maintenance planning in manufacturing [45]”
    Quote in the paperNot a substantial claim1 of 1 sources checked
    • cites [45] Gedeon, 2024, Cognitive Digital Twin-Based Internet of Robotic Things, Multi-Sensory Extended Reality and Simulation Modeling Technologies, and Generative Artificial Intelligence and Cyber-Physical Manufacturing Systems in the Immersive Industrial Metaverse, Equilibrium. Q. J. Econ. Econ. Policy source

      The manufacturing-systems section links digital twins with simulation, production planning, and predictive maintenance, and another passage links industrial robot digital twins with predictive-maintenance accuracy. Neither passage specifies a 10 Hz simulation rate or shows that operating at that rate improves maintenance planning. (LLM, conf=0.83)

      Experimental — accuracy not yet measured

  • May combine two claims.

    Interpretationcitation

    Scalability is limited by coordination overhead in large fleets, with distributed optimization reducing latency in swarms, yet efficiency drops remain a concern.

    “Scalability is limited by coordination overhead in large fleets, with distributed optimization reducing latency in swarms [51], yet efficiency drops remain a concern [4].”
    Quote in the paperNot a substantial claim1 of 2 sources checked
    • cites [51] Carnevale, 2024, Nonconvex Distributed Feedback Optimization for Aggregative Cooperative Robotics, Automatica source

      The Abstract describes a distributed optimization law for cooperating robots, and Section V applies it to a six-robot surveillance network. Our copy does not report reduced latency in swarms or establish that coordination overhead limits scalability in large fleets. The efficiency concern is attached to a different citation and is not assessed here. (LLM, conf=0.82)

      Experimental — accuracy not yet measured
    • cites [4] Cai, 2024, A Survey on Collaborative Hunting with Robotic Swarm: Key Technologies and Application Scenarios, Neurocomputing source

  • May combine two claims.

    Premisecitation

    Adaptive collaborative control using algorithms with a 0.1 gain adjustment enhances robustness in human-robot collaboration, reducing task times in construction.

    “Adaptive collaborative control, using algorithms with a 0.1 gain adjustment, enhances robustness in human-robot collaboration, reducing task times in construction [12,43].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [12] Zhao, 2025, Safety-Efficiency Integrated Assembly: The Next-Stage Adaptive Task Allocation and Planning Framework for Human–Robot Collaboration, Robot. Comput. Integr. Manuf. source
    • cites [43] Jiang, 2024, Fault-Tolerant Trajectory Tracking Control of Underwater Salvage Robots Based on Super-Twisting Sliding Mode, Ocean Eng. source

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Magnetic valve systems with a 0.5 T field optimize energy efficiency in simulations.

    “while magnetic valve systems with a 0.5 T field optimize energy efficiency in simulations [15].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [15] Yoo, J., Chung, G., and Park, Y. (2025). Bio-Inspired Miniaturized Magnetic Heart Valve System for Superior Performance. Adv. Mater., 2419504. in press. source

  • May combine two claims.

    Premisecitation

    Hybrid FTC strategies integrate passive fault-tolerant control's durability with active fault-tolerant control's responsiveness, addressing complex fault profiles across cooperative robotics.

    “Hybrid FTC strategies integrate PFTC's durability with AFTC's responsiveness, addressing complex fault profiles across cooperative robotics [3,29,30].”
    Quote in the paperSubstantial claim0 of 3 sources checked
    • cites [3] Iriarte, 2024, An Overactuated Aerial Robot Based on Cooperative Quadrotors Attached Through Passive Universal Joints: Modeling, Control and 6-DoF Trajectory Tracking, Robot. Auton. Syst. source
    • cites [29] Ma, 2024, Adaptive Neural Cooperative Control of Multirobot Systems with Input Quantization, IEEE Trans. Cybern. source
    • cites [30] Xia, 2025, A New Fault Tolerant Strategy Using Adaptive Time Delay Estimation for Robot Manipulators with Actuator Faults, Nonlinear Dyn. source

  • May combine two claims.

    Premisecitation

    Bioinspired techniques enhance adaptability in swarms and refine precision in manipulators, while supporting uptime in agriculture.

    “Bioinspired techniques, detailed in Section Key Technical Methods in Hybrid FTC, enhance adaptability in swarms [6] and refine precision in manipulators [18], while supporting uptime in agriculture [8].”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites [6] Barth, 2024, Cooperative Behavior of a Heterogeneous Robot Team for Planetary Exploration Using Deep Reinforcement Learning, Acta Astronaut. source
    • cites [18] Zhang, R., Choi, H.-S., Jung, D., Cho, H., Anh, P.H.N., and Vu, M.T. (2024). Fixed-Time Control with an Improved Sparrow Search Algorithm for Robotic Arm Performance Optimization. Appl. Sci., 14. source
    • cites [8] Gong, 2025, An Adaptive Fault-Tolerant Control Scheme for Heterogeneous Multiagent Systems, IEEE Trans. Syst. Man Cybern. Syst. source

  • May combine two claims.

    Premisereasoning

    Active fault-tolerant control dynamically compensates faults using sensor-driven fault detection and diagnosis and excels in unpredictable multi-robot contexts.

    “In contrast, Active Fault-Tolerant Control (AFTC) dynamically compensates faults using sensor-driven Fault Detection and Diagnosis (FDD), excelling in unpredictable multi-robot contexts.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Premisecitation

    Reinforcement learning with a 0.1 learning rate stabilizes systems in harvesting and minimizes construction errors, though exploration risks persist.

    “Reinforcement learning with a 0.1 learning rate stabilizes systems in harvesting [28] and minimizes construction errors [34], though exploration risks persist [13].”
    Quote in the paperNot a substantial claim0 of 3 sources checked
    • cites [28] Wang, 2024, Adaptive Fault-Tolerant Control for Uncalibrated Camera–Robot System with Multiple Uncertainties, J. Frankl. Inst. source
    • cites [34] Lou, 2024, A Human-Cyber-Physical System Enabled Sequential Disassembly Planning Approach for a Human-Robot Collaboration Cell in Industry 5.0, Robot. Comput. Integr. Manuf. source
    • cites [13] Du, 2024, Analyzing Surgeon–Robot Cooperative Performance in Robot-Assisted Intravascular Catheterization, IEEE Trans. Hum. Mach. Syst. source

  • May combine two claims.

    Premisecitation

    Hybrid approaches outperform in versatility, validated by a sub-0.017s recovery and 98% resilience.

    “Table 1 summarizes PFTC and AFTC trade-offs, with hybrid approaches outperforming in versatility, validated by a sub-0.017s recovery [18] and 98% resilience [17].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [18] Zhang, R., Choi, H.-S., Jung, D., Cho, H., Anh, P.H.N., and Vu, M.T. (2024). Fixed-Time Control with an Improved Sparrow Search Algorithm for Robotic Arm Performance Optimization. Appl. Sci., 14. source
    • cites [17] Hameed, 2025, Deep Reinforcement Learning Enabling a BCFbot to Learn Various Undulatory Patterns, Ocean Eng. source

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Premisenone given

    Decentralized control paradigms reduce latency using distributed tuning, as seen in UAV swarms.

    “while decentralized control paradigms reduce latency using distributed tuning, as seen in UAV swarms with rapid”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationcitation

    Scalability is a critical challenge for multi-robot systems as they grow beyond small fleets, with efficiency often declining due to coordination overhead and fault propagation.

    “Scalability poses a critical challenge as multi-robot systems grow beyond small fleets, with efficiency often declining due to coordination overhead and fault propagation [4].”
    Quote in the paperSubstantial claim0 of 1 sources checked
    • cites [4] Cai, 2024, A Survey on Collaborative Hunting with Robotic Swarm: Key Technologies and Application Scenarios, Neurocomputing source

  • May combine two claims.

    Interpretationreasoning

    Hybrid FTC integrates mechanical and electronic strategies to enhance fault tolerance, with practical outcomes validated across diverse contexts.

    “Hybrid FTC integrates mechanical and electronic strategies to enhance fault tolerance, with practical outcomes validated across diverse contexts.”
    • Also stated in: § 8. Conclusions and Future Perspectives · plain
      “Hybrid fault-tolerant control systems combine mechanical redundancy with electronic adaptability to address faults effectively.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Premisereasoning

    Hybrid strategies offer greater adaptability than passive or active fault-tolerant control alone, though often at the cost of increased complexity.

    “Table 1 summarizes the trade-offs between PFTC and AFTC, with hybrid strategies offering greater adaptability, though often at the cost of increased complexity.”
    Quote in the paperSubstantial claim

  • May combine two claims.

    Premisecitation

    Radial Basis Function networks with a 0.01 learning rate approximate uncertainties with Lyapunov stability, excelling in UAV swarms with rapid recovery.

    “Radial Basis Function (RBF) networks with a 0.01 learning rate approximate uncertainties with Lyapunov stability, excelling in UAV swarms with rapid recovery [10,27].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [10] Wang, 2024, A Fault Diagnosis Method for Quadruped Robot Based on Hybrid Deep Neural Networks, IEEE Trans. Ind. Inform. source
    • cites [27] Wang, 2024, Distributed Observer-Based Close Formation Control for UAV Swarm under Outside Disturbances and Wake Interferences, J. Frankl. Inst. source

  • May combine two claims.

    Premisecitation

    Neural-adaptive methods better handle unpredictable conditions than traditional static controllers like PID, though their reliance on GPU-intensive training limits edge deployment.

    “Compared to traditional static controllers like Proportional-Integral-Derivative (PID), which struggle with nonlinearity, neural-adaptive methods better handle unpredictable conditions, though their reliance on GPU-intensive training limits edge deployment [29].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [29] Ma, 2024, Adaptive Neural Cooperative Control of Multirobot Systems with Input Quantization, IEEE Trans. Cybern. source

  • May combine two claims.

    Premisecitation

    Gain scheduling has broad applicability with at least 90% accuracy.

    “highlighting neural-adaptive control's precision (up to 94% accuracy [11]) and gain scheduling's broad applicability (≥90% accuracy [33]).”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [33] Pan, 2024, Design and Experimental Verification: Health Indicator-Based Decentralized Optimal Fault-Tolerant Control for Modular Robot Manipulators via Adjustable Event-Triggered Mechanism, Expert Syst. Appl. source

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Premisenone given

    Hybrid FTC's data-driven nature better handles nonlinearity than traditional model-based methods such as fault-tolerant observers for linear systems, albeit with higher resource demands.

    “Compared to traditional model-based methods, such as fault-tolerant observers for linear systems (e.g., IJSS), hybrid FTC's data-driven nature better handles nonlinearity, albeit with higher resource demands.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Premisecitation

    Distributed control manages fleets of 5-50 robots with efficiency and achieves rapid coordination in UAV swarms.

    “Distributed control manages fleets of 5-50 robots with efficiency [4], achieving rapid coordination in UAV swarms [27]”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [4] Cai, 2024, A Survey on Collaborative Hunting with Robotic Swarm: Key Technologies and Application Scenarios, Neurocomputing source
    • cites [27] Wang, 2024, Distributed Observer-Based Close Formation Control for UAV Swarm under Outside Disturbances and Wake Interferences, J. Frankl. Inst. source

  • May combine two claims.

    Premisecitation

    Distributed self-tuning with a 0.05 tuning step supports multi-agent coordination, minimizing latency in fleets of up to 50 robots.

    “Distributed self-tuning with a 0.05 tuning step further supports multi-agent coordination, minimizing latency in fleets of up to 50 robots [4].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [4] Cai, 2024, A Survey on Collaborative Hunting with Robotic Swarm: Key Technologies and Application Scenarios, Neurocomputing source

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Premisenone given

    Construction contexts show reliable performance under varying conditions with modular designs, supported by bioinspired methods like deep reinforcement learning with multi-layer perceptrons for adaptability, optimization algorithms with particle swarms for precision, and multibody dynamics models for uptime in challenging terrains.

    “Construction contexts show reliable performance under varying conditions with modular designs, supported by bioinspired methods like deep reinforcement learning with multi-layer perceptrons for adaptability, optimization algorithms with particle swarms for precision, and multibody dynamics models for uptime in challenging terrains.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationnone given

    Scalability is hindered by coordination overhead in large fleets, where decentralized and swarm-based architectures help maintain performance.

    “Scalability is hindered by coordination overhead in large fleets, where decentralized and swarm-based architectures help maintain performance.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationnone given

    These approaches outperform isolated strategies by preventing fault cascades and enhancing coordination, offering dependable fault tolerance in healthcare and improved training outcomes in education.

    “These approaches outperform isolated strategies by preventing fault cascades and enhancing coordination, offering dependable fault tolerance in healthcare and improved training outcomes in education.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based).

    Interpretationnone given

    Hybrid approaches that integrate passive robustness, active detection, and learning-based adaptability have demonstrated potential to sustain multi-robot performance under diverse conditions.

    “Hybrid approaches that integrate passive robustness, active detection, and learning-based adaptability have demonstrated potential to sustain multi-robot performance under diverse conditions.”
    Quote in the paperNot a substantial claim

  • May combine two claims.

    Interpretationcitation

    Computational demands escalate with neural processing, posing deployment challenges, though optimization techniques like ISSA's adaptive mutation mitigate overhead.

    “Computational demands escalate with neural processing, posing deployment challenges [56], though optimization techniques like ISSA's adaptive mutation mitigate overhead [18].”
    Quote in the paperNot a substantial claim0 of 2 sources checked
    • cites [56] Fang, 2024, Nonsingular Fixed-Time Fault-Tolerant Sliding Mode Control of Robot Manipulator with Disturbance Observer, Int. J. Control Autom. Syst. source
    • cites [18] Zhang, R., Choi, H.-S., Jung, D., Cho, H., Anh, P.H.N., and Vu, M.T. (2024). Fixed-Time Control with an Improved Sparrow Search Algorithm for Robotic Arm Performance Optimization. Appl. Sci., 14. source

  • May combine two claims.

    Interpretationcitation

    The literature suggests a shift toward integrated validation frameworks and benchmarks to align simulation-based gains with physical outcomes, addressing the current 23% validation limit.

    “The literature suggests a shift toward integrated validation frameworks and benchmarks to align simulation-based gains-like those in Construction 5.0 [12]-with physical outcomes, addressing the current 23% validation limit [3].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [3] Iriarte, 2024, An Overactuated Aerial Robot Based on Cooperative Quadrotors Attached Through Passive Universal Joints: Modeling, Control and 6-DoF Trajectory Tracking, Robot. Auton. Syst. source

  • Probably not a substantial claim: may not pass S2 (checkable). May combine two claims.

    Interpretationreasoning

    These perspectives highlight a path toward integrated frameworks that balance efficiency, resilience, and validation, providing a foundation for advancing cooperative robotics in critical applications.

    “These perspectives highlight a path toward integrated frameworks that balance efficiency, resilience, and validation, providing a foundation for advancing cooperative robotics in critical applications.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Standardized testing protocols at similar rates increase reliability across domains.

    “and standardized testing protocols at similar rates increase reliability across domains [50].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [50] Yang, 2024, Adaptive Neural Fault-Tolerant Prescribed Performance Control of a Rehabilitation Exoskeleton for Lower Limb Passive Training, ISA Trans. source

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Efficient algorithms enhance energy use in construction.

    “while efficient algorithms enhance energy use in construction [12].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [12] Zhao, 2025, Safety-Efficiency Integrated Assembly: The Next-Stage Adaptive Task Allocation and Planning Framework for Human–Robot Collaboration, Robot. Comput. Integr. Manuf. source

  • Probably not a substantial claim: may not pass S3 (load-bearing). May combine two claims.

    Interpretationcitation

    Clarity in performance metrics is a hurdle, with rapid benchmarks improving reliability in construction, yet broader standardization is needed.

    “Clarity in performance metrics is another hurdle, with rapid benchmarks improving reliability in construction [12], yet broader standardization is needed.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [12] Zhao, 2025, Safety-Efficiency Integrated Assembly: The Next-Stage Adaptive Task Allocation and Planning Framework for Human–Robot Collaboration, Robot. Comput. Integr. Manuf. source

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Premisenone given

    In manufacturing, dual-drive configurations and parallel kinematics minimize downtime, while event-triggered mechanisms support swift recoveries in manipulators.

    “In manufacturing, dual-drive configurations and parallel kinematics minimize downtime, while event-triggered mechanisms support swift recoveries in manipulators.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    FT-NCBFs ensure diagnostic accuracy in surgery.

    “In surgery, fail-safe operation is critical to prevent harm, with FT-NCBFs ensuring diagnostic accuracy [49].”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [49] Song, 2023, Digital Twin-Assisted Fault Diagnosis System for Robot Joints with Insufficient Data, J. Field Robot. source

  • Probably not a substantial claim: may not pass S2 (checkable), S4 (based).

    Interpretationnone given

    The gap between simulation and physical validation underscores the importance of expanded testing to ensure real-world reliability.

    “The gap between simulation and physical validation underscores the importance of expanded testing to ensure real-world reliability.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Interpretationreasoning

    Hybrid FTC's deployment in high-stakes domains like healthcare and Construction 5.0 raises safety and ethical concerns.

    “Hybrid FTC's deployment in high-stakes domains like healthcare and Construction 5.0 raises safety and ethical concerns.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based).

    Premisenone given

    Blockchain-enhanced data flow further improves multiagent efficiency.

    “Blockchain-enhanced data flow further improves multiagent efficiency, illustrating how hybrid systems broaden resilience across applications.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing).

    Premisecitation

    Bioinspired actuators, such as tensegrity designs with a 0.5 stiffness ratio, reduce downtime in agriculture.

    “Bioinspired actuators, such as tensegrity designs with a 0.5 stiffness ratio, reduce downtime in agriculture [3]”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [3] Iriarte, 2024, An Overactuated Aerial Robot Based on Cooperative Quadrotors Attached Through Passive Universal Joints: Modeling, Control and 6-DoF Trajectory Tracking, Robot. Auton. Syst. source

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing), S4 (based).

    Interpretationreasoning

    Standardized benchmarks could align simulation-based gains with practical outcomes, enhancing adoption across domains like Construction 5.0.

    “Standardized benchmarks could align simulation-based gains with practical outcomes, enhancing adoption across domains like Construction 5.0.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S3 (load-bearing), S4 (based). May combine two claims.

    Premisenone given

    Agricultural applications benefit from optimized harvesting through neural techniques, and space exploration gains efficiency from reinforcement learning in swarm operations.

    “Agricultural applications benefit from optimized harvesting through neural techniques, and space exploration gains efficiency from reinforcement learning in swarm operations.”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S4 (based). May combine two claims.

    Interpretationreasoning

    These systems enable rapid recoveries in industrial settings, consistent uptime in dynamic environments, and efficient coordination in large fleets.

    “These systems enable rapid recoveries in industrial settings, consistent uptime in dynamic environments, and efficient coordination in large fleets”
    Quote in the paperNot a substantial claim

  • Probably not a substantial claim: may not pass S2 (checkable), S3 (load-bearing).

    Interpretationcitation

    These considerations, integrated with standardized testing, ensure safe and ethical adoption across applications.

    “These considerations, integrated with standardized testing [50], ensure safe and ethical adoption across applications.”
    Quote in the paperNot a substantial claim0 of 1 sources checked
    • cites [50] Yang, 2024, Adaptive Neural Fault-Tolerant Prescribed Performance Control of a Rehabilitation Exoskeleton for Lower Limb Passive Training, ISA Trans. source
49 of 49

  • The paper relies on this without support.

    A gap exists in the understanding of multi-robot resilience across domains that this review addresses.

    “addressing a gap in understanding multi-robot resilience across domains.”

  • The paper relies on this without support.

    The performance figures and outcomes reported in the cited literature are accurate and reliable.

    “This review synthesizes advancements in hybrid FTC, integrating mechanical redundancy with electronic adaptability and learning-based techniques like deep reinforcement learning and swarm-optimized control, drawing from interdisciplinary evidence across manufacturing, healthcare, agriculture, space exploration, and underwater robotics.”
2 of 2

Cites

Flagged first, then by citations

Cited by

Sorted by citations

Related

Authors
Urrea, C.
Affiliations
Universidad de Santiago de Chile (CL)
Corresponding author
Urrea, Claudio
ORCID
Urrea, Claudio
Venue
Actuators
Publisher
MDPI AG
Published
2025-04-04
Volume
14
Issue
4
Pages
177
ISSN
2076-0825 (ISSN-L)
DOI
10.3390/act14040177
OpenAlex
W4409147288
Semantic Scholar
58557a9e40288703aaf1b0cb85b70c8ffb92d77e
Cited by
19
References
57
Citations by year
2026: 14 · 2025: 5
FWCI
7.04
Type
journal article
Language
en
Open access
Licence
Locations
  • Actuators (publishedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
Universidad de Santiago de Chile
Topics
  • Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
  • Physical Sciences › Engineering › Control and Systems Engineering › Robotic Mechanisms and Dynamics
  • Physical Sciences › Engineering › Control and Systems Engineering › Fault Detection and Control Systems
Keywords
fault-tolerant control, cooperative robotics, multi-robot systems, actuator faults, deep reinforcement learning, human-robot collaboration, scalability, resilience engineering, underwater robotics, space robotics, agricultural robotics, healthcare robotics

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Claims read by deepseek-v4.1-flash under definition version 3 (extract-v3) on 2026-10-27.

Classified by jev-1.13-20260917 (gold-guideline-v0.2) on 2026-10-27.

Cited sources are checked by gpt-6-sol.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review