This paper addresses a multi-AGV flow-shop scheduling problem with a reinforcement learning method. Each AGV equipped with a robotic manipulator, operates on the fixed tracks, transporting semi-finished products between successive machines. The objectives dealt with here is to obtain a AGV schedule that minimize the average job delay and total makespan. After formulating such schedule problem as a Markov problem by defining state features, actions space and reward function, a new scheduling method is proposed, based on reinforcement learning. In this new method AGVs share full information on each machine's instant state and job being executed, making decisions thorough understanding of the entire flow shop. Simulation results demonstrate that this new method learns optimal or near-optimal solution from the past experience and provides better performance than multi-agent scheduling method in a dynamic environment.
As vision and language processing techniques have made great progress, mapless-visual navigation is occupying uppermost position in domestic robot field. However, most current end-to-end navigation models tend to be strictly trained and tested on identical datasets with stationary structure, which leads to great performance degradation when dealing with unseen targets and environments. Since the targets of same category could possess quite diverse features, generalization ability of these models is also limited by their visualized task description. In this paper we propose a model-agnostic metalearning based textdriven visual navigation model to achieve generalization to untrained tasks. Based on meta-reinforcement learning approach, the agent is capable of accumulating navigation experience from existing targets and environments. When applied to finding a new object or exploring in a new scene, the agent will quickly learn how to fulfill this unfamiliar task through relatively few recursive trials. To improve learning efficiency and accuracy, we introduce fully convolutional instance-aware semantic segmentation and Word2vec into our DRL network to respectively extract visual and semantic features according to object class, creating more direct and concise linkage between targets and their surroundings. Several experiments have been conducted on realistic dataset Matterport3D to evaluate its target-driven navigation performance and generalization ability. The results demonstrate that our adaptive navigation model could navigate to text-defined targets and achieve fast adaption to untrained tasks, outperforming other state-of-the-art navigation approaches.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.