RZ/A2M Microprocessor Datasheet for Embedded AI Imaging
RZ/A2M MPU for high-speed embedded AI image processing: hybrid DRP preprocessing tightly coupled with a Cortex-A9 CPU, up to 4MB SRAM and multiple PWM outputs.
RZ/A2M MPU for high-speed embedded AI image processing: hybrid DRP preprocessing tightly coupled with a Cortex-A9 CPU, up to 4MB SRAM and multiple PWM outputs.
Ferroelectric memory SF25C20/SF25C512: nonvolatile, low-power, high-endurance storage for AI model parameters in edge devices.
Intelligent Tongxing navigation glasses use YOLOv8 for real-time object detection and ROS2-based communication to deliver low-latency spoken navigation for visually impaired users.
RZ/V2M SoC with DRP-AI (≈1.0 TOPS/W), multi?stream ISP and face/human detection engine, dual Cortex?A53, H.265 codec and USB/PCIe/GigE I/O for low?power vision AI.
RZ/V2MA microprocessor with DRP-AI accelerator: low-power, real-time vision AI and OpenCV preprocessing on-chip, with CPU, DDR, PCIe, USB3, GigE and high-speed I/Os.
Technical overview of a modular, safety-focused bionic robotic hand integrating ROS, cable-driven mechanics, multi-modal sensing and AI-based control for adaptive manipulation.
Technical overview of AI agents: how they use machine learning and multimodal data to perform tasks, make decisions, and enable applications in healthcare and autonomy.
Hierarchical reinforcement learning framework where a vision-language model outputs intermediate instructions and low-level RL maps them to morphology-specific robot actions.
Overview of passive components for AI systems: material, architectural and process innovations for high-current power inductors and low-ESR polymer tantalum capacitors.
MAX78000 AI microcontroller with low-power CNN accelerator, Arm Cortex?M4 with FPU, 442 KB weight SRAM and 512 KB flash, optimized for edge inference.
LLM-driven system automates embodied intelligence skill generation for robotic arms, converting natural-language tasks into MuJoCo scenes, actions, and reward code.
12 strategies to improve GPU utilization and compute efficiency in AI/ML workloads, covering mixed precision, data pipelines, profiling and distributed training.
Autonomous chess robot integrating board recognition, manipulator control, voice interaction, and navigation on RDK X3 with TROS-based node architecture.
Analysis of LLM model scale, hardware and cost trade-offs, showing how smaller models and cloud-native CPUs improve inference efficiency and sustainability.
Practical ESD protection and circuit design guidance for electronic robots: PCB layout, TVS diodes, filtering, grounding, sensor and interface hardening.
Technical overview of voice recognition (ASR) in communications: development, mobile and smart home applications, assistive uses, and future trends with 5G.
Technical guide to scaling LLM training: analyzes memory usage, gradient accumulation, ZeRO, and tensor/data parallelism to improve throughput and GPU utilization.
AI-vision and autonomous navigation robot for detecting red imported fire ant nests and performing targeted bait deployment using LIO-SAM SLAM and YOLO-SRC detection.
Technical overview of data center power management: hybrid capacitors, low?ESR components, precision resistors and wireless monitoring to improve efficiency and reliability.
TDK's spin photodetector using MTJ magnetic elements enables wide-spectrum, ultra-fast optical detection and flexible PIC integration for high-speed links.