Courteous Anticipation: Improving Long-Lived Task Planning in Persistent Shared Environments

Courteous anticipatory planning reduces multi-robot task costs in shared persistent environments

A new arXiv paper introduces courteous anticipatory planning, a model-based approach for robots sharing a persistent environment to minimize both immediate and expected future task costs across all agents. The method uses factored per-robot learned cost estimators to avoid combinatorial joint rollouts, enabling modular deployment. Evaluated in PDDL-based home and restaurant domains, the approach reduces total cost by up to 17.41% versus myopic planning and 13.24% versus selfish anticipatory planning in multi-robot settings.