Mobile devices are becoming increasingly capable of delivering intelligent services by leveraging deep learning architectures such as deep neural networks (DNNs). However, due to the compute-intensive nature of these tasks, mobile devices often struggle to handle them independently, leading to the exploration of collaborative inference as a promising solution for achieving low-latency mobile intelligence. Despite its potential benefits, many challenges need to be addressed in realizing the full potential of inference acceleration. This article presents a collaborative device-edge inference optimization framework as a promising solution to inference acceleration. The framework comprises fundamental modules, including the parameters generator (PG), accuracy predictor (AP), delay calculator (DC), and optimizer (OP), which are specifically designed to identify the optimal set of parameters for model compression, DNN partition, and feature compression. To illustrate its implementation, an example of a deep CNN network is introduced, and the collaborative inference latency optimization is formulated as a mixed-integer programming problem. The implementation of a specific algorithm instance using a quantum-inspired OP within the optimization framework is then presented. A multiple regression-based inference accuracy prediction model is proposed to maintain inference accuracy close to that of the original network while significantly reducing the time consumption during the offline phase. Through various simulation scenarios involving inference tasks of AlexNet and RegNet on CIFAR-10, incorporating diverse hardware computation specifications and wireless communication link conditions, the proposed framework demonstrates superior performance in terms of inference acceleration compared to the compared methods.

Autonomous path planning in obstacle-dense environments remains challenging for swarm intelligence methods due to infeasible initialization, insufficient exploration–exploitation balance, and poor trajectory smoothness for real-robot execution. To address these issues, this paper proposes a Kinematic-Aware Improved Hippo Optimization algorithm (KA-IHO) for mobile robot path planning. The proposed method integrates four components: an elite safety pool initialization strategy to improve feasible solution generation in dense maps, a hierarchical elite-scout update mechanism to better balance global exploration and local exploitation, anti-stagnation mechanisms including a Population Stagnation Restart strategy and a 10-Direction Radial Micro-Search to guarantee high feasibility rates across all map complexities, and a late-stage Laplacian Line-of-Sight Ironing Operator to reduce path redundancy and improve trajectory smoothness. Comparative experiments are conducted on five reproducible grid maps with different complexity levels ($40\times 40$ and $80\times 80$), where KA-IHO is evaluated against six representative algorithms, including HO, SBOA, PSO, GWO, ARO, and INFO, over 20 independent runs. The results show that KA-IHO consistently achieves collision-free planning and obtains lower mean fitness values with smaller standard deviations than the compared methods, indicating improved robustness and solution quality. In addition, hardware closed-loop experiments on a differential-drive mobile robot demonstrate that the planned paths can be executed reliably in real environments, with trajectory tracking errors controlled within $\pm 4$ cm.

A quantum‐inspired optimisation algorithm with dynamic scale sampling is proposed for converging to the ground state efficiently to obtain the optimal solution. The proposed algorithm maintains diversity to discourage premature convergence through the niching method. Dynamic adjustment of sampling resolution is utilised to find a balance between exploration and exploitation. Energy level transition inside each niche and niches energy balance among niches improve the searching efficiency by guidance energy information of energy equilibrium point. The experimental results on benchmark function sets with compared algorithms show that the proposed scheme is dominant in accuracy and stability.

This letter addresses the issue of cooperative vehicle tracking in vehicular ad-hoc networks (VANETs) through the fusion of global navigation satellite system (GNSS) data and time-of-arrival (TOA) based ranging information. We propose a novel distributed improved Cubature Kalman Filter (CKF) to enhance the state estimation accuracy of all vehicles. This approach comprises two parts: local improved CKF processing and cooperative fusion tracking. Due to the nonlinearity of the ranging measurement function with respect to both local vehicle state and neighboring vehicle state, an augmented parameter vector is constructed in the improved CKF method to tackle this challenge. Then, we present the optimal cooperative fusion of the local vehicle state estimate and the estimates from its neighbors, in the sense of minimizing the fused mean squared error. Numerical examples demonstrate that the root of average mean squared error (RAMSE) of the proposed method can be significantly reduced.