Efficient operation of control systems in robotics or autonomous driving targeting real-world navigation scenarios requires perception methods that allow them to understand and adapt to unstructured environments with good accuracy, adaptation, and generality, similar to humans. To address this need, we present a memristor-based differential neuromorphic computing, perceptual signal processing, and online adaptation method providing neuromorphic style adaptation to external sensory stimuli. The adaptation ability and generality of this method are confirmed in two application scenarios: object grasping and autonomous driving. In the former, a robot hand realizes safe and stable grasping through fast ( ~ 1 ms) adaptation based on the tactile object features with a single memristor. In the latter, decision-making information of 10 unstructured environments in autonomous driving is extracted with an accuracy of 94% with a 40×25 memristor array. By mimicking human low-level perception mechanisms, the electronic neuromorphic circuit-based method achieves real-time adaptation and high-level reactions to unstructured environments.

The demand for efficient edge computer vision has spurred the development of stochastic computing for image processing. Memristors, by introducing their inherent switching stochasticity into computation, readily enable stochastic image processing. Here, we present a lightweight, error-tolerant edge detection approach based on memristor-enabled stochastic computing. By integrating memristors into compact logic circuits, we realise lightweight stochastic logics for stochastic number encoding and processing with well-regulated probabilities and correlations. This stochastic and probabilistic computational nature allows the stochastic logics to perform edge detection in edge visual scenarios characterised by high-level errors. As a demonstration, we implement a hardware edge detection operator using the stochastic logics, and prove its exceptional performance with 95% less energy consumption while withstanding 50% bit-flips. The results underscore the potential of our stochastic edge detection approach for developing efficient edge visual hardware for autonomous driving, virtual and augmented reality, medical imaging diagnosis, and beyond.

Wearable silent speech systems hold significant potential for restoring communication in patients with speech impairments. However, seamless, coherent speech remains elusive, and clinical efficacy is still unproven. Here, we present an AI-driven intelligent throat (IT) system that integrates throat muscle vibrations and carotid pulse signal sensors with large language model (LLM) processing to enable fluent, emotionally expressive communication. The system utilizes ultrasensitive textile strain sensors to capture high-quality signals from the neck area and supports token-level processing for real-time, continuous speech decoding, enabling seamless, delay-free communication. In tests with five stroke patients with dysarthria, IT’s LLM agents intelligently corrected token errors and enriched sentence-level emotional and logical coherence, achieving low error rates (4.2% word error rate, 2.9% sentence error rate) and a 55% increase in user satisfaction. This work establishes a portable, intuitive communication platform for patients with dysarthria with the potential to be applied broadly across different neurological conditions and in multi-language support systems.

An effective and highly accurate strabismus screening method is expected to identify potential patients and provide timely treatment to prevent further deterioration, such as amblyopia and even permanent vision loss. To satisfy this need, this work showcases a novel strabismus screening method based on a wearable eye-tracking device combined with an artificial intelligence (AI) algorithm. To identify the minor and occasional inconsistencies in strabismus patients during the binocular coordination process, which are usually seen in early-stage patients and rarely recognized in current studies, the system captures temporally and spatially continuous high-definition infrared images of the eye during wide-angle continuous motion, and is effective in inducing intermittent strabismus. Based on the collected eye motion information, 16 features of the oculomotor process with strong physiological interpretations, which help biomedical staff understand and evaluate results generated later, are calculated through the introduction of pupil-canthus vectors. These features can be normalized, and reflect individual differences. After these features are processed by the random forest (RF) algorithm, this method experimentally yields 97.1% accuracy in strabismus detection in 70 people under diverse indoor testing conditions, validating the high accuracy and robustness of the method, and implying that the method has strong potential to support widespread and highly accurate strabismus screening.

Drone-based rapid and accurate environmental edge detection is highly advantageous for tasks such as disaster relief and autonomous navigation. Current methods, using radar or cameras, raise deployment costs and burden lightweight drones with high computational demands. In this paper, we propose AirTouch, a system that transforms the ground effect from a stability "foe" in traditional flight control views, into a "friend" for accurate and efficient edge detection. Our key insight is that analyzing drone sensor readings and flight commands allows us to detect ground effect changes. Such changes typically indicate the drone flying over an edge, making this information valuable for edge detection. We approach this insight through theoretical analysis, algorithm design, and implementation, fully leveraging the ground effect as a new sensing modality without compromising drone flight stability, thereby achieving accurate and efficient scene edge detection. Extensive evaluations demonstrate that our system achieves a high detection accuracy with mean detection distance errors of 0.051m, outperforming the baseline performance by 86%.

At-home rehabilitation for post-stroke patients presents significant challenges, as continuous, personalized care is often limited outside clinical settings. Moreover, the lack of integrated solutions capable of simultaneously monitoring motor recovery and providing intelligent assistance in home environments hampers rehabilitation outcomes. Here, we present a multimodal smart home platform designed for continuous, at-home rehabilitation of post-stroke patients, integrating wearable sensing, ambient monitoring, and adaptive automation. A plantar pressure insole equipped with a machine learning pipeline classifies users into motor recovery stages with up to 94% accuracy, enabling quantitative tracking of walking patterns during daily activities. An optional head-mounted eye-tracking module, together with ambient sensors such as cameras and microphones, supports seamless hands-free control of household devices with an average latency under 1 s with consistent operation. These data streams are fused locally via a hierarchical Internet of Things (IoT) architecture, ensuring low latency and data privacy. An embedded large language model (LLM) agent, Auto-Care, continuously interprets multimodal data to provide real-time interventions—issuing personalized reminders, adjusting environmental conditions, and notifying caregivers. Implemented in a post-stroke context, this integrated smart home platform increased mean user satisfaction from $3.9~\pm ~0.8$ in conventional home environments to $8.4~\pm ~0.6$ with the full system (n = 20). Beyond stroke, the system offers a scalable, patient-centered framework with potential for long-term use in broader neurorehabilitation and aging-in-place applications.