Oct 2026· IEEE Robotics and Automation Letters· Vol 11, pp. 11346-11353· 0 citations· 21 references
Abstract
Coordinating a team of robots in aircraft skin fabrication requires allocating and sequencing tightly coupled subtasks under spatio-temporal constraints, while the fleet must react to runtime disturbances such as robot failures and urgent task arrivals. Mixed-Integer Linear Programming (MILP) yields provably optimal coordination, but a disturbance often introduces new constraint logic rather than a mere parameter change, leaving the existing formulation structurally inadequate and requiring expert-led reformulation to accommodate the new logic. This letter proposes a Large Language Model (LLM)-based framework that automates the path from natural-language scheduling requirements to MILP formulation, executable solver code, and event-driven rescheduling, so that the optimization model can be restructured online without expert intervention. Two compact LLMs are specialized for complementary roles: a modeling LLM, empowered via knowledge augmentation, supervised fine-tuning on industrial constraint descriptions, and direct preference optimization on self-generated negatives; and a code LLM, trained via sandbox-validated knowledge distillation. On ten industrial constraint classes, the 8B modeling LLM reaches 100% constraint-level accuracy, exceeding cloud-scale general-purpose LLMs equipped with retrieval over the same knowledge base, while the 8B code LLM attains 86% under fully on-premises deployment. When a disturbance occurs, an event-triggered mechanism regenerates only the affected constraints. A case study on multi-robot scheduling for aircraft skin fabrication shows that the framework matches the schedule quality of baselines while shifting adaptation cost from offline expert labour to a bounded online inference budget.
Efficient task allocation for large-scale Heterogeneous Multi-Robot Systems (HMRS) is critical, yet dealing with complex temporal logic tasks in partially known environment (PKE) remains a computational bottleneck. Existing approaches often struggle to balance exploring uncertain regions and exploiting known resources, while also suffering from exponential computational complexity. To address these issues, this paper presents a robust planning framework that simultaneously handles high-level logical constraints and environmental uncertainty without sacrificing scalability. We formulate the problem as a min-max regret optimization, proposing a Region-Binding Atomic Proposition (RbAP) to capture resource uncertainty within the automaton structure. To solve this, we propose the Extended Planning Decision Tree (E-PDT) equipped with a novel Regret-based Branch-and-Bound (BnB) strategy. Unlike traditional methods that rely on prior probabilities or worst-case analysis, our approach dynamically prunes suboptimal policies, effectively balancing the need for information gathering (exploration) and task completion (exploitation). Theoretical analysis confirms the feasibility and completeness of our approach. Extensive numerical and physical experiments demonstrate that the proposed framework achieves near-linear scalability with respect to the number of robots and types, significantly outperforming MILP-based baselines in both solution quality and computational efficiency. Note to Practitioners—Task allocation for large-scale heterogeneous multi-robot systems is critical in applications like warehouse logistics and disaster response. However, existing planning methods often struggle with environmental uncertainty, relying on unavailable probability data or failing to scale. This work presents a fast, robust planning framework that uses a regret-minimization strategy to balance exploring uncertain areas with completing tasks. Unlike optimization-based approaches that can be computationally prohibitive, our E-PDT method achieves near-linear scalability, coordinating thousands of robots in seconds. This allows practitioners to deploy large robot fleets that adaptively search for resources without needing precise prior knowledge. Current limitations assume a known static map topology with uncertain resource locations; future extensions will address fully dynamic and unknown environments.
Xinkai Liang, Hui-Xuan Chan, Ying Liu et al.· IEEE Transactions on Automat...· 0 citations
CoMuRoS enables runtime, event-driven replanning on physical robots and supports flexible multi-robot and human-robot collaboration across diverse scenarios.
Suraj S. Borate, Bhavish Rai B, Vipul Pardeshi et al.· Frontiers in Robotics and AI· 0 citations
Building disassembly is critical for circular economy material reuse, yet remains rare due to cost and safety constraints, leading to demolition and material downcycling. Automation could improve both efficiency and safety, but currently available technology does not yet enable full automation. We propose a human–robot collaboration system architecture that uses agentic large language models. We test this approach in building disassembly—an unstructured, safety–critical domain where conventional pre-programmed robotics are inadequate. The agentic architecture combines curated domain knowledge, physics simulation for stability validation, and natural language interfaces, enabling the robot to participate through proactive reasoning rather than follow control commands. We evaluated the architecture through three progressively complex scenarios: collaborative spatial adaptation, collaborative decision-making, and learning. The main contribution is a modular, data-grounded HRC methodology in which specialized LLM agents perform agentic reasoning: the robot assesses situations, retrieves relevant procedural knowledge, validates decisions through simulation, and negotiates solutions with human operators. This proof of concept demonstrates that agentic multi-agent LLM systems can enable adaptive human–robot collaboration under uncertainty, beyond natural language interfaces through integrated domain knowledge, physics validation, and agentic reasoning.
Samuel Slezák, Shirin Shevidi, Zahra Shakeri et al.· Construction Robotics· 0 citations
Agent-based modeling and simulation (ABMS) has been widely employed to study emergent processes in collective robotic construction (CRC), where global architectural structures arise from local agent interactions. While these approaches reveal how complex assemblies can emerge without centralized control, they remain limited when an architectural goal is known but the behaviors required to achieve it are not. Most CRC workflows still depend on handcrafted heuristics. This paper presents a hybrid CRC workflow that integrates large language models (LLM) into the ABMS behavior design process. The system enables human–AI co-creation of robot behaviors, allowing an LLM agent to generate and negotiate behavioral strategies toward user-defined construction goals under partial observability. The approach is evaluated in simulation, comparing an LLM–heuristic hybrid against a heuristic-only baseline behavior. For well-documented swarm patterns, the LLM matches heuristic performance; for geometrically novel tasks, handcrafted heuristics retain an advantage. By embedding language-based reasoning within ABMS, this work expands participation in CRC behavior design and demonstrates a pathway for translating high-level design intent into adaptive, goal-oriented multiagent construction processes.
Samuel Slezák, Lasath Siriwardena, S. Leder et al.· Construction Robotics· 0 citations
Robotic industrial panel operation requires not only accurate control localization but also compliance with operating procedures, safety rules, and device-state constraints distributed across heterogeneous manuals. This study presents MaCoPlanner, a task-planning framework built on knowledge compiled from equipment manuals that converts equipment manuals into a typed intermediate representation, retrieves task- and state-relevant evidence, and uses it to support plan generation. Before actuation, candidate plans are symbolically rolled out and checked against procedural and state-transition constraints; detected violations are localized and returned for targeted repair, while unresolved plans are rejected. A separate execution interface grounds verified symbolic actions to physical controls and updates the device state. Under an independent evaluation oracle, MaCoPlanner achieves a final violation rate of 2.7%, and 26.3% of the runs in the repair analysis are rejected after exhausting the refinement budget. Compared with Raw-Manual, task success increases from 62.8% to 84.4% on Level-2 tasks and from 25.9% to 43.2% on Level-3 tasks. Experiments on a controller-panel simulator without an attached industrial load further demonstrate integrated execution feasibility under representative interaction conditions, without claiming industrial deployment readiness.
Gui-Peng Xin, Jiahe Xua, Mohammad Deghat et al.· 0 citations
Multi-robot systems provide the parallelism and redundancy necessary for long-horizon tasks, while Large Language Models (LLMs) offer the reasoning capabilities to decompose these objectives into actionable plans. However, effectively grounding this high-level reasoning in physical multi-robot execution remains an open challenge. Existing LLM-based approaches fall mainly into two categories: Single-robot methods achieve robust contact-rich manipulation but lack the coordination mechanisms required for tasks spanning multiple workspaces. Current multi-robot frameworks focus on high-level planning, often treating manipulation as an idealized primitive that fails to account for real-world execution uncertainties. To address this, we propose a hierarchical closed-loop agentic LLM-based framework to ensure robust multi-robot manipulation. Our system consists of three specialized agents: the Planning Agent decomposes instructions into allocated sub-tasks, the Manipulation Agent for each robot executes actions via adaptive tool use, and the Verification Agent closes the loop by monitoring physical outcomes and feeding back semantic corrections. Extensive real-world experiments demonstrate that our framework achieves superior success rates, ensures robust adaptability ranging from single to cross workspace manipulation, and offers a generalizable approach for diverse manipulation tasks.
Yi-Xiang He, Lan Wei, Haoming Cen et al.· Robotics· 0 citations