Andrew F. Burke

Artificial intelligence (AI) is influencing battery research and life-cycle management, spanning materials discovery, electrode and cell design, manufacturing optimization, diagnostics, safety monitoring, recycling, and certification. These advances are enabled by growing battery datasets and learning methods that extract patterns from complex electrochemical systems. Yet most current models remain task-specific and are trained on fragmented datasets, limiting transferability across chemistries, cell formats, operating conditions, and life-cycle stages. Battery foundation models (BFMs) offer a promising but emerging paradigm for battery intelligence. They may be formulated as large, pre-trained, and adaptable architectures that integrate multimodal battery data with physics-informed priors to represent electrochemical structures, states, and dynamics. Unlike direct analogues of general large language models, BFMs should be understood as physics-aware foundation models designed for scientific reasoning under multiscale physical constraints, heterogeneous and incomplete data, and stringent safety and reliability requirements. By combining self-supervised learning with mechanistic electrochemical models, BFMs may learn more interpretable and transferable representations across materials, formats, and duty cycles. If sufficiently validated, such representations could support materials discovery, manufacturing, diagnostics, recycling, and certification. This Review discusses challenges in data fragmentation, validation, interpretability, and computational sustainability, and outlines a roadmap toward responsible BFMs and integrated battery-domain ecosystems across the lifecycle.

Autonomous driving represents a significant advancement in the transportation industry, enhancing vehicle intelligence, optimizing traffic management, and improving user experiences. Central to these innovations is deep learning, which enables systems to handle complex data and make informed decisions. Our survey explores critical applications of deep learning in autonomous driving, such as perception and detection, localization and mapping, and decision-making and control. We investigate specialized deep learning techniques, including convolutional neural networks, recurrent neural networks, self-attention transformers, and their variants, among others. These methods are applied within various learning paradigms—supervised, unsupervised, and reinforcement learning—to suit the specific needs of autonomous driving. Our analysis evaluates the effectiveness, benefits, and limitations of these technologies, focusing on their integration with other intelligent algorithms to enhance system performance. Furthermore, we examine the architectures of autonomous systems, analyzing how knowledge and information are organized from modular, pipeline-based frameworks to comprehensive end-to-end models. By presenting an exhaustive overview of the progressing domain of autonomous driving and bridging various research areas, our survey aims to synthesize diverse research threads into a unified narrative. This effort not only aims to enhance our understanding but also pushes the boundaries of what is achievable in this interdisciplinary field.

In autonomous systems, path planning and control are critical for ensuring safety, efficiency, and comfort. Deep learning has significantly enhanced these aspects by introducing adaptability and real-time responsiveness into autonomous operations. Reinforcement learning-based motion planning algorithms, for example, are adept at devising optimal navigation paths even within intricate environments. Moreover, trajectory prediction models, particularly those employing recurrent neural networks, excel in anticipating the movements of nearby objects accurately. Furthermore, the integration of end-to-end methodologies has augmented the capabilities of autonomous control systems, providing a more streamlined approach to decision-making processes. The application of explainable AI techniques brings a layer of transparency to these technologies, elucidating the reasoning behind decisions and fostering trust among users. Herein, we explore these technological advancements and examine their impact on the development of autonomous vehicle technology.

Ensuring the reliability, safety, and efficiency of electric vehicles (EVs) necessitates precise diagnostics of battery life, as the degradation of batteries directly influences both performance and sustainability. The transformative role of artificial intelligence (AI) in advancing EV battery diagnostics is explored herein, with an emphasis placed on the complexities of predicting and managing battery health. Initially, we provide an overview of the challenges associated with battery lifetime diagnostics, such as issues with accuracy, generalization, and model training. The following sections delve into advanced AI methodologies that enhance diagnostic capabilities. These methods include extensive time-series AI, which improves predictive accuracy; end-to-end AI, which simplifies system complexity; multi-model AI, which ensures generalization across varied operating conditions; and adaptable AI strategies for dynamic environments. In addition, we explore the use of federated learning for decentralized, privacy-preserving diagnostics and discuss the role of automated machine learning in streamlining the development of AI-based models. By integrating these sophisticated AI techniques, we present a comprehensive roadmap for the future of AI-driven battery prognostics and health management. This roadmap underscores the critical importance of accuracy, scalability, and sustainability in fostering advancement. Our interdisciplinary framework offers valuable insights that can accelerate the electrification of transportation and advance the evolution of energy storage systems, tackling key challenges at the intersection of battery technology and AI.

In the Industry 4.0 era, integrating artificial intelligence (AI) with battery prognostics and health management (PHM) offers transformative solutions to the challenges posed by the complex nature of battery systems. These systems, known for their dynamic and nonl*-inear behavior, often exceed the capabilities of traditional PHM approaches, which struggle to account for the interplay of multiple physical domains and scales. By harnessing technologies such as big data analytics, cloud computing, the Internet of Things (IoT), and deep learning, AI provides robust, data-driven solutions for capturing and predicting battery degradation. These advancements address long-standing limitations in battery prognostics, enabling more accurate and reliable performance assessments. The convergence of AI with Industry 4.0 technologies not only resolves existing challenges but also introduces innovative approaches that enhance the adaptability and precision of battery health management. This perspective highlights recent progress in battery PHM and explores the shift from traditional methods to AI-powered, data-centric frameworks. By enabling more precise and scalable monitoring and prediction of battery health, this transition marks a significant step forward in advancing the field.