Artificial intelligence-powered pocket-sized air robots have the potential to revolutionize the Internet-of-Things ecosystem, acting as autonomous, unobtrusive, and ubiquitous smart sensors. With a few cm$^{2}$ form-factor, nano-sized unmanned aerial vehicles (UAVs) are the natural befit for indoor human-drone interaction missions, as the pose estimation task we address in this work. However, this scenario is challenged by the nano-UAVs' limited payload and computational power that severely relegates the onboard brain to the sub-100 mW microcontroller unit-class. Our work stands at the intersection of the novel parallel ultra-low-power (PULP) architectural paradigm and our general development methodology for deep neural network (DNN) visual pipelines, i.e., covering from perception to control. Addressing the DNN model design, from training and dataset augmentation to 8-bit quantization and deployment, we demonstrate how a PULP-based processor, aboard a nano-UAV, is sufficient for the real-time execution (up to 135 frame/s) of our novel DNN, called PULP-Frontnet. We showcase how, scaling our model's memory and computational requirement, we can significantly improve the onboard inference (top energy efficiency of 0.43 mJ/frame) with no compromise in the quality-of-result vs. a resource-unconstrained baseline (i.e., full-precision DNN). Field experiments demonstrate a closed-loop top-notch autonomous navigation capability, with a heavily resource-constrained 27-gram Crazyflie 2.1 nano-quadrotor. Compared against the control performance achieved using an ideal sensing setup, onboard relative pose inference yields excellent drone behavior in terms of median absolute errors, such as positional (onboard: 41 cm, ideal: 26 cm) and angular (onboard: 3.7$^{\circ}$, ideal: 4.1$^{\circ}$).
翻译:人工智能袖珍空格机器人(UAV)具有革命性能的智能智能智能传感器(Internet-house of Things)生态系统,作为自主、不受干扰和无处不在的智能传感器。我们的工作处于新颖的平行超低电(PULP)建筑范式和我们用于深神经网络(DNN)直观管道(即从感知到控制)的一般开发方法的交叉点。我们在工作中处理的构成估算任务。然而,这种情景受到纳米UAVs有限的有效载荷和计算能力的挑战,它严重地将机上大脑降至100 mW 微控制器单位级级。我们的工作处于新颖的平行超低电源(PULP)建筑模型的建筑模式范式交叉点,也就是从感知到控制。 DNNE模型设计,从培训和数据集成,到8比平方平面的盘化和部署,我们展示了基于全机型ULP的流程处理器:在纳米-UAVAV(N-I-deal-deal-dealalal del-deal-deal-deal-deal-modeal-deal ex-deal-deal-deal-deal-deal ex-deal-deal-deal-deal ex) ex ex ex ex ex ex ex ex ex ex ex ex ex-stututututal ex ex ex ex ex ex ex-deplutal-deplutus ex ex ex ex ex ex ex lautal lautus ex ex ex exputal lautal ex ex ex ex a ex ex ex-st ex ex ex-st ex-st ex-stal ex-stal ex-stal-stal laction-weal-stal-weal-stal-deal lautal-stal-stal-stal-st-st-st-weal-weal-deal-deal-weal-weal-weal-weal-pal-pal-pal-de