Deep Neural Network Architecture Search for Accurate Visual Pose Estimation aboard Nano-UAVs
This work addresses the challenge of enabling sophisticated onboard intelligence for cheap, low-power nano-UAVs, representing an incremental improvement in domain-specific robotics.
The authors tackled visual pose estimation for nano-UAVs by using neural architecture search to optimize CNNs for hardware constraints, resulting in a 32% reduction in control error and achieving real-time inference rates of ~10Hz at 10mW and ~50Hz at 90mW.
Miniaturized autonomous unmanned aerial vehicles (UAVs) are an emerging and trending topic. With their form factor as big as the palm of one hand, they can reach spots otherwise inaccessible to bigger robots and safely operate in human surroundings. The simple electronics aboard such robots (sub-100mW) make them particularly cheap and attractive but pose significant challenges in enabling onboard sophisticated intelligence. In this work, we leverage a novel neural architecture search (NAS) technique to automatically identify several Pareto-optimal convolutional neural networks (CNNs) for a visual pose estimation task. Our work demonstrates how real-life and field-tested robotics applications can concretely leverage NAS technologies to automatically and efficiently optimize CNNs for the specific hardware constraints of small UAVs. We deploy several NAS-optimized CNNs and run them in closed-loop aboard a 27-g Crazyflie nano-UAV equipped with a parallel ultra-low power System-on-Chip. Our results improve the State-of-the-Art by reducing the in-field control error of 32% while achieving a real-time onboard inference-rate of ~10Hz@10mW and ~50Hz@90mW.