Abstract Traditional extended Kalman filter is a popular method in vehicle state parameters estimation. However, its performance undergoes significant degradation when encountering non-Gaussian noise or noise of uncertain statistical properties. The maximum correntropy extended Kalman filter (MCEKF) based on Gaussian kernel can handle some non-Gaussian noise scenarios, but it is still less effective in dealing with noise of uncertain statistical characteristics and is typically sensitive to manually selected kernel bandwidths. To overcome these constraints, this paper proposes a new adaptive extended Kalman filtering algorithm based on the Cauchy-kernel maximum correntropy criterion (CKMCC), referred to as the Cauchy-kernel maximum correntropy adaptive extended Kalman filter (CKMCAEKF). By integrating the CKMCC and an adaptive method, the proposed algorithm eliminates sensitivity to selection of kernel bandwidth and enhances robustness against non-Gaussian noise and noise of uncertain statistical characteristics. Moreover, the robustness of the proposed method is theoretically proven. The effectiveness of the proposed method is validated through co-simulations on the MATLAB/Simulink and CarSim platforms. CKMCAEKF achieves superior estimation accuracy for vehicle state parameters to other existing methods under non-Gaussian measurement noise scenarios and scenarios of changes in statistical characteristics of measurement noise caused by sudden events.

Abstract Physics-informed neural networks (PINNs) effectively integrate physical equation constraints into the model to simultaneously learn data distributions and underlying physical laws. However, conventional uniform sampling is computationally expensive and inefficient for complex systems. The residual-based adaptive refinement distribution (RARD) algorithm, proposed by Wang et al., improves sampling but relies heavily on residual estimation, neglecting higher-order derivatives and leading to potential suboptimal sampling distributions. To address these issues, this study proposes the Residual-based Adaptive Antiderivative Approximation (RA-ADAF) approach. Within a fully connected neural network (FCNN) framework, RA-ADAF introduces antiderivative approximation layers (ADAF) with integral structure modeling capability, enhancing the representation of both the target function and its derivatives. Unlike the RARD strategy that solely relies on residual estimation for adaptive sampling, RA-ADAF combines residual-driven adaptive sampling with derivative-informed structural modeling. This dual mechanism improves model fitting in error-concentrated regions and enhances the representation of higher-order derivative behavior. The effectiveness of the RA-ADAF method is validated through a series of numerical experiments, including comparisons on the Burgers equation, Allen–Cahn equation, and wave equation, as well as ablation studies. Experimental results demonstrate that RA-ADAF consistently achieves lower relative L2 error compared to the RARD method across multiple test cases. Moreover, it exhibits faster error convergence and more stable training behavior, providing a more reliable strategy for solving partial differential equations (PDEs) involving complex physical phenomena.

Biological intelligence is inherently adaptive-animals continually adjust their actions in response to environmental feedback. However, creating adaptive artificial intelligence (AI) remains a major challenge. The next frontier is to go beyond traditional AI to develop 'adaptive intelligence', defined here as harnessing insights from biological intelligence to build agents that can learn online, generalize and rapidly adapt to changes in their environment. Recent advances in neuroscience offer inspiration through studies that increasingly focus on how animals naturally learn and adapt their models of the world. This Perspective reviews the behavioral and neural foundations of adaptive biological intelligence, examines parallel progress in AI, and explores brain-inspired approaches for building more adaptive algorithms.

This study addresses the drone delivery problem with a unique focus on minimizing total customer waiting times, considering the heterogeneous nature of drones and the setup times required for loading customer demands. Unlike traditional routing problems that prioritize cost and route optimization, this research emphasizes timely deliveries, which are critical in both commercial and humanitarian applications. The study introduces two mathematical models and four versions of the coot optimization algorithm, including three modified variants and one classical version. These algorithms incorporate new movement mechanisms, enhanced leader selection strategies, and adaptations of the regenerating strategy to efficiently solve the drone delivery problem. Computational experiments reveal that one modified coot optimization algorithm significantly outperforms the classical version, offering valuable insights into both coot optimization literature and the drone delivery problem. By emphasizing the importance of timely deliveries, this research provides effective solution strategies applicable to both commercial and humanitarian contexts.

Adaptive multi-granularity graph attention fusion algorithm for autonomous amphibious aerial vehicle route optimization

Robust adaptive beamforming algorithm for multipath coherent reception based on iterative adaptive approach and covariance matrix reconstruction

Adaptive fuzzy PID search algorithm for global optimization with application to 3D UAV path planning

Adaptive neural pseudo-inverse control for time-delay nonlinear hysteretic systems considering output constraint and its application.

An adaptive virtual measurement STGP algorithm for self-occluded 3D extended object tracking with time-varying shapes

Identifiability Conditions for Acoustic Feedback Cancellation With the Two-Channel Adaptive Feedback Canceller Algorithm

An adaptive differential evolution algorithm with exponential crossover based on a learning strategy within the difference vector

A weakly supervised framework for automated biological assay assessment.

A Bayesian probabilistic approach for ship corrosion prediction using the Adaptive Metropolis-Hastings algorithm

Nonlinear integral sliding mode control of SPMSMs using a dual-layer adaptive super-twisting algorithm

IRFPA strong nonuniformity adaptive correction algorithm based on adjacent pixel differential statistics

Multi-objective optimization of distributed generation in electrical grids using an adaptive chaotic salp swarm algorithm

Neuroadaptive consensus learning for multi-agent systems: An incremental approach to nonstrict pure-feedback control.

Bias-compensated constrained adaptive filtering algorithm for noisy inputs

An adaptive pairwise testing algorithm based on deep reinforcement learning

High-precision parameter estimation of photovoltaic models via a novel adaptive elite-biased backtracking search algorithm