The pressure on today's factories to boost output is becoming steadily stronger. Automation of mundane tasks that wear people out is necessary to reach the new productivity heights. Self-driving mobile robots have been shown to increase output in a variety of material-handling, transportation, manipulation, and packaging tasks. When many mobile robots are used for these purposes, the question of how to divide up the work becomes more complicated. System efficiency might be enhanced by effectively assigning the robots to the job. The term "Multi-Robot Task Allocation" (MRTA) refers to the challenge of figuring out how to distribute work among several robots. Multiple robots must work together to complete the task under consideration in this study. Optimal utilisation of the robots is crucial to the success of the job completion. When multiple goals must be met at once, optimising the tasks assigned to these robots is essential. This study discovers how to optimise the distribution of work among several robots while satisfying multiple objectives at once.
In cellular communication systems, radio resources are allocated to users by the MAC scheduler, that typically runs at the base station (BS). The task of the scheduler is to meet the quality of service (QoS) requirements of each data flow while maximizing the system throughput and achieving a desired level of fairness amongst users. Traditional schedulers use handcrafted metrics and are meticulously tuned to achieve a delicate balance between multiple, often conflicting objectives. Diverse QoS requirements of 5G networks further complicate traditional schedulers. In this paper, we propose a novel reinforcement learning based scheduler that learns an allocation policy to simultaneously optimize multiple objectives. Our approach allows network operators to customize their requirements, by assigning priority values to QoS classes. In addition, we adopt a flexible neural-network architecture that can easily adapt to varying number of flows, drastically simplifying training, thus rendering it viable for practical implementation in constrained systems. We demonstrate, via simulations, that our algorithm outperforms conventional heuristics such as M-LWDF, EXP-RULE and LOG-RULE and is robust to changes in radio environment and traffic patterns.
Article Some Novel Aspects of the Electron Transfer Reaction between Thiosulfate Ion and Methylene Blue in Acidic Medium was published on January 1, 1999 in the journal Zeitschrift für Physikalische Chemie (volume 211, issue 1).