莱迪思博客

人形机器人已进入到大型物流仓库中搬运货物、在汽车装配线上排列零部件，并在全球一些最大的订单履行中心开展试点运营。可以说人形机器人的第一波浪潮已经到来，其并非停留在实验室或演示中，而是在真实的生产环境中承担实际工作。高盛预测到2035年，该市场规模将达到380亿美元。而今天正在设计的人形机器人平台，正是未来随这一增长实现规模化扩张的关键。 但制造人形机器人与制造传统机器截然不同。人形机器人是一个分布式计算平台，不仅需要行走、感知环境、在现场进行自我更新，还必须满足监管要求，而这一切都必须在有限的电池功耗预算下完成。这意味着其内部芯片必须同时具备实时控制、超低功耗、异构协议桥接和硬件级安全等能力。没有哪一款MCU、分立式安全芯片或应用级SoC能够独自包揽这一切。 莱迪思低功耗FPGA正是为此而设计。单个莱迪思FPGA即可充当人形机器人平台“始终在线的神经系统”——从电源接通的瞬间起，甚至在任何应用处理器启动之前，便开始管理电源时序、桥接传感器与执行器、保障物理安全和加固网络安全。 为何人形机器人将芯片性能推向极限 现代人形机器人并非一...

Present-day edge AI systems rely heavily on multi-modal sensor fusion, such as camera, lidar, and radar, to enable accurate, real-time decision-making. Existing platforms, such as NVIDIA® Jetson Orin NX, are equipped to adequately support multi-camera use cases. To advance this further, NVIDIA’s latest Jetson Thor series modules have been combined with the Holoscan Sensor Bridge board – running on a Lattice FPGA – to address the increase in sensor counts and synchronization...

Interest in edge computing has surged as organizations across industries seek smarter ways to automate processes, enhance productivity, and optimize labor. By processing data closer to its source, edge systems can provide benefits like reduced transmission and storage costs and strengthened security. They can also enable the development of advanced machines and devices, from autonomous mobile robots (AMRs) and humanoids to smart medical devices, which can operate with precision and speed. Thes...

Across industries and use cases, computing capacity is shifting away from centralized servers and towards the edge. Whether in the form of autonomous vehicles, smart sensors, or other technological solutions, today's intelligent applications demand faster decision-making and increased autonomy. This shift is especially prevalent in the Industrial, defense, and aerospace industries. The unmanned aerial vehicles (UAVs) and drones used in defense applications rely heavily on edge intelligence to...