arXiv:2605.28312v1 Announce Type: cross 
Abstract: Event-based vision sensors offer asynchronous, high-temporal-resolution measurements that are attractive for low-latency robotic perception, but many event-based motion estimation methods are computationally intensive and difficult to map to FPGA hardware. We present a streaming velocity estimator that discretizes asynchronous events into fixed-duration time bins, constructs a 1-bit spatial occupancy grid, and evaluates multiple velocity hypotheses in parallel using only fixed-width integer logic - shift registers, counters, comparators, and small LUT-mapped multiplies - with no dividers and no DSP blocks. It requires no frame reconstruction, no floating-point arithmetic, and no iterative optimization. The method deliberately trades dense sub-pixel optical flow for a sparse, quantized velocity estimate at each active pixel, suited to low-latency tasks such as reactive obstacle avoidance on size-, weight-, and power-constrained platforms. On noisy synthetic data with known ground-truth velocities, the method recovers both magnitude and direction, with magnitude estimates being most challenged when objects of different velocities intersect. On a real event-camera sequence, directional accuracy reaches 99.5% across all four evaluated motion segments, with performance remaining robust across occupancy densities in the 10-40% range. We characterize the algorithm's density-dependent behavior, present a parameter sensitivity analysis, show that the proposed datapath requires less than 2 kB of storage, and implement a single-axis prototype on a low-cost Xilinx Artix-7.

تم تطوير مُقدِّر سرعة جديد يُدعى EventShiftFlow لتحسين تقدير التدفق باستخدام أجهزة FPGA، مُستهدفًا بشكل خاص الإدراك الروبوتي منخفض الكمون من خلال معالجة بيانات الأحداث غير المتزامنة دون الحاجة إلى حسابات معقدة أو تحسين تكراري.

Se ha desarrollado un nuevo estimador de velocidad en streaming llamado EventShiftFlow para mejorar la estimación de flujo utilizando hardware FPGA, dirigido específicamente a la percepción robótica de baja latencia al procesar datos de eventos asíncronos sin requerir aritmética compleja u optimización iterativa.

Un nouvel estimateur de vitesse en streaming, nommé EventShiftFlow, a été développé pour améliorer l'estimation du flux en utilisant du matériel FPGA, ciblant spécifiquement la perception robotique à faible latence en traitant des données d'événements asynchrones sans nécessiter d'arithmétique complexe ou d'optimisation itérative.

A new streaming velocity estimator named EventShiftFlow has been developed to enhance flow estimation using FPGA hardware, specifically targeting low-latency robotic perception by processing asynchronous event data without requiring complex arithmetic or iterative optimization.

EventShiftFlow: Towards Hardware-efficient FPGA-based Flow Estimation

arXiv:2602.08916v3 Announce Type: replace-cross 
Abstract: Objective: Acute mountain sickness (AMS) is the most prevalent altitude illness, affecting unacclimatized individuals ascending above 2,500 m and potentially escalating to life threatening cerebral or pulmonary edema. Conventional machine learning (ML) methods for AMS detection from wearable physiological signals often fail to meet real-time hardware efficiency requirements of continuous monitoring. Methods: We present AMS-HD, the first hyperdimensional computing (HDC)-based framework for real-time AMS detection, spanning high-level bipolar (-1/+1) computing for mobile platforms and low-level binary (0/1) computing for FPGA and ASIC targets. The framework integrates mutual information feature selection, hypervector encoding, and positional projection to enhance classification efficiency. Validation spans ARM, FPGA, and smartwatch-smartphone platforms using wearable-accessible SpO2 and heart rate signals. Results: AMS-HD matches or outperforms SVM and MLP baselines in both binary and multiclass classification, achieving up to 91% accuracy and 90% F1-score in binary classification, and up to 85% accuracy on external AMS-related datasets. On FPGA, AMS-HD reduces LUT and flip-flop usage by 7.3x and 5.8x, while consuming 3.9x less power than MLP. On mobile platforms, AMS-HD requires only 1% battery per session, 60 Bytes of memory, and 2.50 ms inference time -- approximately 2x and more than 3x lower energy consumption than SVM and MLP. Conclusion: AMS-HD provides a scalable, hardware-aware alternative to conventional ML for real-time AMS monitoring, achieving competitive performance with substantially lower resource consumption. Significance: This work presents the first complete HDC framework for altitude sickness detection, bridging wearable inference and low-level hardware deployment for resource-constrained health monitoring.

تم تطوير إطار عمل جديد يسمى AMS-HD للكشف عن مرض المرتفعات الحاد (AMS) في الوقت الحقيقي، مستفيدًا من الحوسبة متعددة الأبعاد لتحسين كفاءة مراقبة الإشارات الفسيولوجية من الأجهزة القابلة للارتداء. تتناول هذه الطريقة المبتكرة قيود أساليب التعلم الآلي التقليدية، التي غالبًا ما تكافح مع متطلبات المراقبة المستمرة في البيئات المرتفعة.

Se ha desarrollado un nuevo marco llamado AMS-HD para la detección en tiempo real del mal agudo de montaña (AMS), aprovechando la computación hiperdimensional para mejorar la eficiencia en el monitoreo de señales fisiológicas de dispositivos portátiles. Este enfoque innovador aborda las limitaciones de los métodos de aprendizaje automático tradicionales, que a menudo luchan con las demandas de monitoreo continuo en entornos de gran altitud.

Un nouveau cadre nommé AMS-HD a été développé pour la détection en temps réel du mal aigu des montagnes (AMS), utilisant l'informatique hyperdimensionnelle pour améliorer l'efficacité de la surveillance des signaux physiologiques provenant des dispositifs portables. Cette approche innovante répond aux limites des méthodes d'apprentissage automatique traditionnelles, qui peinent souvent à répondre aux exigences de surveillance continue dans des environnements en haute altitude.

A new framework named AMS-HD has been developed for the real-time detection of Acute Mountain Sickness (AMS), leveraging hyperdimensional computing to enhance the efficiency of monitoring physiological signals from wearables. This innovative approach addresses the limitations of traditional machine learning methods, which often struggle with the demands of continuous monitoring in high-altitude environments.

EventShiftFlow: Towards Hardware-efficient FPGA-based Flow Estimation

Was this article worth reading? Share it

Ready to build your own newsroom?