In this paper, we propose a reinforcement learning-based algorithm for trajectory optimization for constrained dynamical systems. This problem is motivated by the fact that for most robotic systems, the dynamics may not always be known. Generating smooth, dynamically feasible trajectories could be difficult for such systems. Using samplingbased algorithms for motion planning may result in trajectories that are prone to undesirable control jumps. However, they can usually provide a good reference trajectory which a model-free reinforcement learning algorithm can then exploit by limiting the search domain and quickly finding a dynamically smooth trajectory. We use this idea to train a reinforcement learning agent to learn a dynamically smooth trajectory in a curriculum learning setting. Furthermore, for generalization, we parameterize the policies with goal locations, so that the agent can be trained for multiple goals simultaneously. We show result in both simulated environments as well as real experiments, for a 6-DoF manipulator arm operated in position-controlled mode to validate the proposed idea. We compare the proposed ideas against a PID controller which is used to track a designed trajectory in configuration space. Our experiments show that our RL agent trained with a reference path outperformed a model-free PID controller of the type commonly used on many robotic platforms for trajectory tracking.

This study reports a new simulation paradigm devised to simulate manufacturing systems in its real operational stage. The objective manufacturing system is supposed to be under ubiquitous environment; in other words, all machines and equipments constituting a real manufacturing system are all equipped with intelligent devices and are connected to an information network. In the framework of the proposed simulation method, the simulation model is not built on one computer as is done in the conventional simulation, but is built on the network by integrating the intelligent devices. Each devise with properly embedded simulation functions plays as a simulation agent representing a resource or an entity in the conventional simulation model. This paper discusses the simulation functions required to each device to form a discrete event simulation system. The time management of the simulation and the event processes in the new simulation paradigm are described.

In this paper, we propose Petri net decomposition approach for bi-objective optimization of conflict-free routing for AGV systems. The objective is minimizing total traveling time and equalizing delivery time simultaneously. The dispatching and conflictfree routing problem for AGVs is represented as a bi-objective optimal firing sequence problem for Petri Net. A Petri net decomposition approach is proposed to solve the bi-objective optimization problem efficiently. The convergence of the proposed algorithm is improved reducing search region by the proposed coordination method. The effectiveness of the proposed method is compared with that of a nearest neighborhood dispatching method. Computational results are provided to show the effectiveness of the proposed method.

No abstract

No abstract