Search

In large-scale industrial applications, goods must be continuously transported between locations, which in the absence of conveyor systems is by a fleet of individual vehicles. This article introduces flow-achieving scheduling tree (FAST), an online dispatching algorithm that allows vehicles to efficiently operate as a team to maximize the system's throughput while meeting a production schedule. A high-performance model is developed for high-fidelity prediction of vehicle interactions and system performance. It is subsequently optimized using a self-tuning variant of Monte Carlo tree search (MCTS) to make agile dispatch decisions in real time. The method is validated using an open-cut mine site and is shown to outperform a commonly used algorithm in this domain. Note to Practitioners - This article was motivated by the problem of dispatching autonomous haul trucks on open-cut mine sites. The proposed method is suited to any industrial transportation system where a continuous stream of goods must be efficiently transported between the load and unload stations by a potentially heterogeneous fleet of automated vehicles. The system makes decisions in real time while reacting to performance variations and disturbances by using a receding horizon approach. Off-the-shelf software commonly used in this domain is based on heuristics with limited ability to optimize, leading to myopic decision making without taking vehicle interactions into account. Here, flow-achieving scheduling tree (FAST) overcomes this by optimizing over possible schedules and thereby implicitly accounting for knock-on effects. Future work will incorporate additional constraints into the optimization process and validate FAST in other industrial domains.

© 2019 Taylor & Francis Group, London. Truck dispatching systems have been widely used since the 1970s for truck assignments in open pit mines, in order to coordinate material movement from diggers to process plants and stockpiles. Existing commercial solutions are commonly plan-driven systems, which operate by making real-time truck assignments while maintaining conformance to an established haulage allocation plan. Such systems typically comprise programming models to deter-mine the allocation plan as a set of material flow rates. A significant limitation of these methods is that they optimise flow rates only for instantaneous production. These approaches ignore upcoming events and changes in availability and performance, limiting the ability to optimise flows around such events. The method proposed in this paper extends existing approaches by modelling material flows over a future time-horizon, incorporating upcoming events, disrup-tions, and changes in resources. Results are presented comparing an established algorithm with the proposed method, showing improved handling of disruption events.

In this paper we develop an algorithmic framework allowing for fast and elegant path correction exploiting Lie group symmetries and operating without the need for explicit control strategies such as cross-track regulation. These systems occur across the gamut of robotics, notably in locomotion, be it ground, underwater, airborne, or surgical domains. Instead of reintegrating an entire trajectory, the method selectively alters small key segments of an initial trajectory in a consistent way so as to transform it via symmetry operations. The algorithm is formulated for arbitrary Lie groups and applied in the context of the special Euclidean group and subgroups thereof. A sampling-based motion planner is developed that uses this method to create paths for underactuated systems with differential constraints. It is also shown how the path correction method acts as a controller within a feedback control loop for real-time path correction. These approaches are demonstrated for ground vehicles in the plane and for flexible bevel tip needle steering in space. The results show that using symmetry-based path correction for motion planning provides a prudent and simple, yet computationally tractable, integrated planning and control strategy.

For agile, accurate autonomous robotics, it is desirable to plan motion in the presence of uncertainty. The Partially Observable Markov Decision Process (POMDP) provides a principled framework for this. Despite the tremendous advances of POMDP-based planning, most can only solve problems with a small and discrete set of actions. This paper presents General Pattern Search in Adaptive Belief Tree (GPS-ABT), an approximate and online POMDP solver for problems with continuous action spaces. Generalized Pattern Search (GPS) is used as a search strategy for action selection. Under certain conditions, GPS-ABT converges to the optimal solution in probability. Results on a box pushing and an extended Tag benchmark problem are promising.