Multi-robot teams learn task assignments without preset rules
MORPH: Self-Organising Multi-Robot Task Allocation via Neuroplasticity-Inspired Adaptive Topology
Robotics
Summary
Coordinating robots to do tasks in changing environments is hard because they need to learn how to work together but also adapt quickly when things change. The authors created MORPH, a method that lets robots figure out which tasks to take based only on their experience, without any pre-training or fixed rules. Instead of just choosing tasks by how close they are, robots learn preferences based on what tasks happen together and how well they complete them. This makes their coordination more flexible and efficient, especially when conditions shift unexpectedly.
What this means in practice
- •For warehouse automation teams: Coordinate large fleets of robots more efficiently without upfront task modeling, improving throughput even when task locations change unexpectedly.
- •For robotics system integrators: Develop flexible control systems for multi-robot setups that self-adapt task allocations online without requiring predefined cost functions or training data.
Authors
Xuezhi Niu, Didem Gürdür Broo
Abstract
Multi-robot task allocation (MRTA) in dynamic environments faces a fundamental tension: effective coordination requires learned structure, but that structure must adapt when conditions change. Existing methods resolve this by assuming prior task knowledge, a utility function, a cost matrix, or a trained policy making them brittle when deployed without such knowledge or when task distributions shift. We present MORPH(Multi-agent Online Rewiring through Plasticity-guided Hierarchy), a training-free MRTA framework where global allocation quality emerges from 4 local plasticity rules (synaptic, homeostatic, structural, and metaplasticity) applied to a directed pairwise preference matrix updated from runtime co-occurrence and task-completion feedback. MORPH requires no task model, no bid computation, and no offline training; response decisions use learned AGV-to-Picker preferences rather than a fixed proximity rule. Within the Gerkey-Mataric MRTA taxonomy, MORPH is the first method in the single-task, single-robot, instantaneous-assignment class to learn directed pairwise allocation preferences online. Evaluated on the TA-RWARE warehouse benchmark (8-24 agents, 4 maps, 800 steps per episode, 5 seeds), MORPH achieves 110% of all-to-all throughput at N=24 while using only 21% of possible coordination links as an efficiency advantage that grows monotonically with fleet size. Under spatial task distribution shift, MORPH degrades 3x less than proximity-based methods while its learned preferences remain uncorrelated with Manhattan distance. Systematic ablation confirms all four plasticity rules contribute measurably. Two allocation properties emerge without programming: cross-type preference dominance and progressive preference sparsification, mirroring the developmental refinement of biological neural circuits. Learned preferences are driven by task co-occurrence history, not spatial proximity.