Organizations: National Engineering Research Center of Mobile Network Technologies, Beijing University of Posts and Telecommunications, Beijing 100876, China · Department of Electrical Engineering, University of South Florida, Tampa, FL 33620 USA · School of Information and Communication Engineering, Beijing University of Posts and Telecommunications, Beijing 100876, China
Achieving agile and reconfigurable production flows in smart factories depends on online multi-robot task assignment (MRTA), which requires online collision-free and congestion-free route scheduling of transportation multi-robot systems (T-MRS), e.g., collaborative automatic guided vehicles (AGVs). Due to the real-time operational requirements and dynamic interactions between T-MRS and production MRS, online scheduling under partial observability in dynamic factory environments remains a significant and under-explored challenge. This paper proposes a novel communication-enabled online scheduling framework that explicitly couples wireless machine-to-machine (M2M) networking with route scheduling, enabling AGVs to exchange intention information, e.g., planned routes, to overcome partial observations and assist complex computation of online scheduling. Specifically, we determine intelligent AGVs' intention and sensor data as new M2M traffic and tailor the retransmission-free multi-link transmission networking to meet real-time operation demands. This scheduling-oriented networking is then integrated with a simulated annealing-based MRTA scheme and a congestion-aware A*-based route scheduling method. The integrated communication and scheduling scheme allows AGVs to dynamically adjust collision-free and congestion-free routes with reduced computational overhead. Numerical experiments shows the impacts from wireless communication on the performance of T-MRS and suggest that the proposed integrated scheme significantly enhances scheduling efficiency compared to other baselines, even under high AGV load conditions and limited channel resources. Moreover, the results reveal that the scheduling-oriented wireless M2M communication design fundamentally differs from human-to-human communications, implying new technological opportunities in a wireless networked smart factory.
Figures & tables
Figure 1: Online scheduling for MRS in a smart factory. The edge server performs MRTA to the production MRS and thus T-MRS. (① → ②). Without wireless networking, multi-AGV operating in a distributed manner with partial observations lead to collisions and congestion. With wireless networking, AGVs collaboratively execute pick-up and delivery tasks on time by real-time adjusting routes (③), which significantly relies on AI operational intention and sensor data exchange via wireless networking (④).
Notation
Definition
Notation
Definition
K
The set of AGVs
Rk , Pk
Task routes, and navigation routes of AGV k
C , S , D
The number of available channels, selected channels, and communication interval
B
Decision matrix of MRTA
okt , o~kt , okt , st
Local partial observation, additional observation, enhanced fusion observation, and global state
W
Makespan based on local observations
xm+ , xm− , dm+t , dm−t , tmddl , μλm
Task nodes for pick-up and delivery, quantity of production at task nodes, task’s due time, task’s priority
Mt
the number of new tasks at time t
ATk,e
Reach time of AGV k at task node
A
Route decision matrix
WTk,e
waiting time of AGV k at task node
PTk,e
preparation time at task node
Table 1: Main Notations
Figure 2: The decomposition of the online scheduling problem and the coupling between the MRTA and MRRSP algorithms.
Figure 3: The proposed communication-enabled online scheduling framework.
Figure 4: Comparison of the performances of transmission probability and throughput under different numbers of AGVs. (a) Throughput vs. the number of AGVs for different D values when C=S=1 ; (b) Transmission success probability vs. the number of AGVs for different selected number of channels S when D=2 ; (c) Throughput vs. the number of AGVs for different selected number of channels S when D=2 .
Figure 5: The number of AGVs vs. makespan
Figure 6: Communication interval vs. makespan
Figure 7: Makespan W vs. the number of selected channels S and the number of AGVs K
Figure 8: Makespan W vs. the available number of channels C and the number of AGVs K
Cooperative task scheduling in communication-constrained distributed multi-agent systems is challenging because each agent must make decisions from partial and dynamic observations while satisfying complex practical constraints. Existing heuristics rely on handcrafted bidding rules and repeated consensus, whereas many learning-based methods assume global observations and lack explicit communication-based coordination. To address these limitations, this paper proposes a neural scheduling framework for distributed multi-robot task allocation (MRTA), consisting of a multi-decoder graph attention model (MDGAM) policy model and a critic-free group relative multi-agent policy gradient (GRMAPG) training algorithm. MDGAM uses an extended graph attention mechanism to jointly update node and edge features, and employs multiple decoders to generate task-selection decisions and communication messages. GRMAPG constructs group-relative advantages from equivalent task-planning instances to replace the critic network used in conventional MARL algorithms, thereby reducing training difficulty and improving convergence performance. Experiments under different problem scales and communication ranges show that the proposed method improves task-completion performance over existing heuristic and learning-based methods, while ablation, complexity, and generalization tests further validate the proposed innovations.
Licheng Wang, Mingtao Huang, Yuan Shen
Department of Electronic Engineering, and Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing 100084, China
In structured multi-agent transportation systems, agents often must follow predefined routes, making spatial rerouting undesirable or impossible. This paper addresses route-constrained multi-agent coordination by optimizing waypoint passage times while preserving each agent's assigned waypoint order and nominal route assignment. A differentiable surrogate trajectory model maps waypoint timings to smooth position profiles and captures first-order tracking lag, enabling pairwise safety to be encoded through distance-based penalties evaluated on a dense temporal grid spanning the mission horizon. The resulting nonlinear and nonconvex velocity-scheduling problem is solved using an inexact-projection Alternating Direction Method of Multipliers (ADMM) algorithm that combines structured timing updates with gradient-based collision-correction steps and avoids explicit integer sequencing variables. Numerical experiments on random-crossing, bottleneck, and graph-based network scenarios show that the proposed method computes feasible and time-efficient schedules across a range of congestion levels and yields shorter mission completion times than a representative hierarchical baseline in the tested bottleneck cases.
Seungyeop Lee, Jong-Han Kim
Department of Aerospace Engineering and the Program in Aerospace Systems Convergence, Inha University, Incheon, South Korea. · Aerospace Systems Research Institute, Inha University, Incheon, South Korea.
Coordinating heterogeneous multi-robot systems (MRS) for complex, long-horizon tasks requires both flexible high-level reasoning and efficient execution-time scheduling. Existing LLM-based approaches struggle to balance reasoning efficiency and execution flexibility. Flat sequential plans are efficient to generate but overlook parallel execution opportunities, while repeated LLM reasoning introduces high latency, and offline schedules may unnecessarily keep robots idle due to fixed execution orders. This paper presents OSDAG, a novel framework that resolves this trade-off by employing a Directed Acyclic Graph (DAG) as the central representation for multi-robot coordination, coupled with constraint-aware online scheduling. The LLM is typically invoked once as a semantic parser that decomposes a natural-language instruction into a dependency-annotated task graph encoding precedence relations, together with robot capability and resource-feasibility constraints. A lightweight online scheduler then dynamically dispatches dependency-ready tasks to their assigned robots as soon as they become idle, exposing available parallelism while preserving correctness. Experiments across five benchmark scenarios demonstrate that OSDAG achieves 5−15× faster reasoning time than dialogue-based methods, reduces makespan by up to 38% over sequential baselines, and maintains competitive success rates. Both simulation and real-world experiments on human-robot collaboration tasks validate the effectiveness and practicality of the proposed approach for efficient multi-robot coordination. The website and resources are available at http://thanhnguyencanh.github.io/LLM_DAG4MultiRobot
Thanh Nguyen Canh, Thang Tran Viet, Phuc Van Dinh +2
School of Information Science, Japan Advanced Institute of Science and Technology, Nomi, 923-1211, Ishikawa, Japan. · University of Engineering and Technology, Vietnam National University, 10000, Hanoi, Vietnam. · Department of Robotics, Hanyang University, Ansan, 15588, Gyeonggi, Korea.