Cloud manufacturing is an emerging paradigm of global manufacturing networks. Through centralized management and operation of distributed manufacturing services, it can deal with different requirement tasks submitted by multiple customers in parallel. Therefore, the cloud manufacturing multi-task scheduling problem has attracted increasing attention from researchers. This article proposes a new cloud manufacturing multi-task scheduling model based on game theory from the customer perspective. The optimal result for a cloud manufacturing platform is derived from the Nash equilibrium point in the game. As the cloud manufacturing multi-task scheduling problem is known as an NP-hard combinatorial optimization problem, an extended biogeography-based optimization algorithm that embeds three improvements is presented to solve the corresponding model. Compared with the basic biogeography-based optimization algorithm, genetic algorithm, and particle swarm optimization, the experimental simulation results demonstrate that the extended biogeography-based optimization algorithm finds a better schedule for the proposed model. Its benefit is to provide each customer with reliable services that fulfill the demanded manufacturing tasks at reasonable cost and time.

Multi-robot systems such as swarms of aerial robots are naturally suited to offer additional flexibility, resilience, and robustness in several tasks compared to a single robot by enabling cooperation among the agents. To enhance the autonomous robot decision-making process and situational awareness, multi-robot systems have to coordinate their perception capabilities to collect, share, and fuse environment information among the agents efficiently to obtain context-appropriate information or gain resilience to sensor noise or failures. In this paper, we propose a general-purpose Graph Neural Network (GNN) with the main goal to increase, in multi-robot perception tasks, single robots' inference perception accuracy as well as resilience to sensor failures and disturbances. We show that the proposed framework can address multi-view visual perception problems such as monocular depth estimation and semantic segmentation. Several experiments both using photo-realistic and real data gathered from multiple aerial robots' viewpoints show the effectiveness of the proposed approach in challenging inference conditions including images corrupted by heavy noise and camera occlusions or failures.

No abstract

No abstract

No abstract