MCTS Based Dispatch of Autonomous Vehicles under Operational Constraints for Continuous Transportation

TL;DR

This paper introduces a Monte Carlo Tree Search-based dispatch planner called FAST for autonomous haul-trucks in mining, effectively integrating operational constraints into the planning process to improve efficiency and constraint satisfaction.

Contribution

It develops a novel MCTS-based dispatch planning method that explicitly incorporates operational constraints via opportunity costs, enhancing long-term optimality and scalability.

Findings

Successful constraint satisfaction using opportunity costs

Effective integration of operational constraints into dispatch planning

Demonstrated scalability across different constraint types

Abstract

Continuous transportation of material in the mining industry is achieved by the dispatch of autonomous haul-trucks with discrete haulage capacities. Recently, Monte Carlo Tree Search (MCTS) was successfully deployed in tackling challenges of long-run optimality, scalability and adaptability in haul-truck dispatch. Typically, operational constraints imposed on the mine site are satisfied by heuristic controllers or human operators independent of the dispatch planning. This article incorporates operational constraint satisfaction into the dispatch planning by utilising the MCTS based dispatch planner Flow-Achieving Scheduling Tree (FAST). Operational constraint violation and satisfaction are modelled as opportunity costs in the combinatorial optimisation problem of dispatch. Explicit cost formulations are avoided by utilising MCTS generator models to derive opportunity costs. Experimental studies with four types of operational constraints demonstrate the success of utilising opportunity costs for constraint satisfaction, and the effectiveness of integrating constraints into dispatch planning.