SADCHER: Scheduling using Attention-based Dynamic Coalitions of Heterogeneous Robots in Real-Time

TL;DR

Sadcher tackles real-time scheduling for heterogeneous multi-robot teams with dynamic coalitions and precedence constraints. It introduces a graph-attention and transformer-based reward predictor trained via imitation learning, followed by a relaxed bipartite matching step to yield feasible task assignments. By explicitly modeling robot/task positions, task durations, and remaining workloads, the approach achieves strong spatiotemporal generalization and real-time operation on small to medium problem sizes. A public dataset of 250,000 optimal schedules is released to support benchmarking and further research.

Abstract

We present Sadcher, a real-time task assignment framework for heterogeneous multi-robot teams that incorporates dynamic coalition formation and task precedence constraints. Sadcher is trained through Imitation Learning and combines graph attention and transformers to predict assignment rewards between robots and tasks. Based on the predicted rewards, a relaxed bipartite matching step generates high-quality schedules with feasibility guarantees. We explicitly model robot and task positions, task durations, and robots' remaining processing times, enabling advanced temporal and spatial reasoning and generalization to environments with different spatiotemporal distributions compared to training. Trained on optimally solved small-scale instances, our method can scale to larger task sets and team sizes. Sadcher outperforms other learning-based and heuristic baselines on randomized, unseen problems for small and medium-sized teams with computation times suitable for real-time operation. We also explore sampling-based variants and evaluate scalability across robot and task counts. In addition, we release our dataset of 250,000 optimal schedules: https://autonomousrobots.nl/paper_websites/sadcher_MRTA/

Figures (5)

• Figure 1: Illustrative use case of autonomous construction on Mars. Circles represent tasks, color indicates required skills. Robot skills are shown as colored squares. Tasks requiring skills no single robot has (e.g., search for material in top left) must be executed by a synchronized coalition of robots.
• Figure 2: Sadcher architecture overview. Robot and task graphs are processed by graph attention and transformer encoders and concatenated with distance features. The reward matrix is estimated by the Idle and Reward MLPs and final task assignments are extracted using relaxed bipartite matching. $B$: batch size, $N$: number of robots, $M$: number of tasks, $d_r$: robot input dimension, $d_t$: task input dimension, $d$: latent dimension.
• Figure 3: Comparison on 500 unseen, randomized problem instances (8 tasks, 3 robots, 3 precedence constraints) for makespan (left), and computation time (right). Lower means better performance. Wilcoxon significance levels are annotated for Sadcher compared to HeteroMRTA variants. All other pairwise differences are statistically significant ($p < 0.05$), except between S-HeteroMRTA and Greedy ($p = 0.21$). For algorithms requiring full solution construction, total computation time is reported; for methods returning instantaneous assignments, both time per decision and total time are shown.
• Figure 4: Pairwise makespan comparison of HeteroMRTA vs. Sadcher (left) and S-HeteroMRTA vs. S-Sadcher (right). Each point is one solved instance; points below the diagonal indicate better performance by (S-)Sadcher.
• Figure 5: Relative makespan gap to Sadcher for 3, 5, and 20 robots (top left to bottom left). Bottom right: Computation time for 3 robots (for algorithms requiring full solution construction (Sample-HeteroMRTA, Sample-Sadcher, MILP), total computation time is reported, for methods returning instantaneous assignments (HeteroMRTA, Sadcher, Greedy), time per decision is reported). Task counts $M \in [6, 250]$, with $S = 3$ skills and $M/5$ precedence constraints. Each point shows the mean over 100 runs.