Nowadays, humanoid robots are expected to possess perception and interaction abilities that can be applied in social applications. In this paper, efforts are made to enable a humanoid robot to identify potentially interactive human groups while avoiding pedestrians in dynamic scenarios. To this end, an integrated framework is proposed. In this framework, a group identification module is first developed to classify individuals into groups and effectively infer the group behavioral trend by monitoring their temporal characteristics. Then, an interactive decision maker based on Laplacian dynamics is established to guide the humanoid robot in making interactive decisions to ensure the target groups. Based on the above perception and decision designs, a novel robot behavior planning algorithm is designed to both approach interactive targets in a socially compliant manner and avoid non-interactive ones. Simulation and experiments based on a humanoid robot have demonstrated that the framework can achieve higher social planning speed and better interaction quality while maintaining satisfactory avoidance performance. These findings indicate that the Laplacian-based decision-maker can enable humanoid robots to efficiently respond to groups with various behavior patterns.

Mobile edge computing significantly reduces the delay for smart city services by offloading the related datasets on the edge server. The correlation among smart city datasets regarding their location and functionality plays a crucial role in determining the data offloading strategy. The more closely related these datasets are, the higher the probability they will be requested simultaneously. However, most existing methods often ignore the impact of location-functionality correlation on the datasets' access frequencies. If datasets with high correlation are offloaded on separate edge servers, it will increase cross-server delay. Therefore, we proposed a method to analyze location-functionality correlation among smart city datasets and optimize data offloading strategy. Then, we formalize a data offloading model to optimize the total expected profits, which is an NP-hard problem. To solve this problem, we propose a pruned Q-learning for data offloading algorithm that learns the location-functionality correlation among the datasets. To validate its effectiveness, we first conduct simulation experiments to validate the offloading strategy under both complex service scenarios and large-scale datasets. Furthermore, we implement a data offloading architecture based on SuperMap iServer. The experimental results demonstrate that our algorithm reduces the delay and energy consumption by 34.65% and 25.54%, respectively, compared to the baseline algorithms.

In vehicular edge computing, the vehicular services are cached and replaced among Roadside Units (RSU) to minimize delay in delay-sensitive services. However, without prior knowledge of these service preferences, the cached services suffer a low hit ratio and a high network delay. Before the appearance of requests from vehicles, most existing vehicular service caching methods design the service-sharing mechanisms among RSUs to optimize the hit ratio, but they ignore the influence of vehicle mobility on service-sharing. Moreover, in vehicular services replacement, the differences between actual and historical vehicle trajectories negatively impact the service-sharing mechanisms constructed before, which existing methods ignored. Thus, this paper addresses the vehicular service caching problem based on the surrounding function-features of vehicles and transportation correlations. Firstly, we use the surrounding function-features of vehicles to estimate the service preference and ensure the hit ratio of cached services. Secondly, we formulate the vehicular service caching problem as a constrained optimization problem and design a cooperation mechanism between RSUs, which is based on transportation correlations of vehicle trajectories. Thirdly, we propose two vehicular service caching methods based on Gibbs sampling to optimize the network delay of vehicular services and deal with the negative influence of vehicle mobility. Simulation in real datasets from Shenzhen, China shows that our methods have a better network delay and hit ratio than existing baselines by 15.26% and 5.6%, respectively.

Considering the advantages of mobile edge computing (MEC), such as low latency, high bandwidth, etc., more and more mobile services are cached to mobile edge servers. However, due to limited computing resources and storage capacity of mobile edge servers, it is hard to guarantee that all services are cached and all computation offloading requests are satisfied. In this paper, we jointly optimize service caching and computation offloading to maximize system profits in mobile edge-cloud computing (MECC). The problem is formalized as a nonconvex optimization problem with discrete variables. We propose a Dynamic Joint computation Offloading and Service Caching algorithm (DJOSC) to solve the problem. Specifically, a regularization technique and Lyapunov optimization theory are used to transform the problem into two subproblems, which are solved by convex optimization techniques. Numerical evaluations show that the maximum system profits can be achieved under different computing resources, storage capacities and bandwidth capacities.