Towards a Multi-Pixel Time-of-Flight Indoor Navigation System for Nano-Drone Applications

Niculescu, Vlad; Muller, Hanna; Ostovar, Iman; Polonelli, Tommaso; Magno, Michele; Benini, Luca

doi:10.1109/i2mtc48687.2022.9806701

Cited by 18 publications

(7 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nano-drones can be equipped with small laser rangers [1,[18][19][20] or sonars [21] to avoid obstacles at short distances. Some research focused on optical flow estimation using a dedicated optical flow sensor [22] or cameras [23,24].…”

Section: Obstacle Avoidance Of Nano-dronesmentioning

confidence: 99%

End-to-End Nano-Drone Obstacle Avoidance for Indoor Exploration

Zhang,

Nex,

Vosselman

et al. 2024

Drones

View full text Add to dashboard Cite

Autonomous navigation of drones using computer vision has achieved promising performance. Nano-sized drones based on edge computing platforms are lightweight, flexible, and cheap; thus, they are suitable for exploring narrow spaces. However, due to their extremely limited computing power and storage, vision algorithms designed for high-performance GPU platforms cannot be used for nano-drones. To address this issue, this paper presents a lightweight CNN depth estimation network deployed on nano-drones for obstacle avoidance. Inspired by knowledge distillation (KD), a Channel-Aware Distillation Transformer (CADiT) is proposed to facilitate the small network to learn knowledge from a larger network. The proposed method is validated on the KITTI dataset and tested on a Crazyflie nano-drone with an ultra-low power microprocessor GAP8. This paper also implements a communication pipe so that the collected images can be streamed to a laptop through the on-board Wi-Fi module in real-time, enabling an offline reconstruction of the environment.

show abstract

Section: Obstacle Avoidance Of Nano-dronesmentioning

confidence: 99%

End-to-End Nano-Drone Obstacle Avoidance for Indoor Exploration

Zhang,

Nex,

Vosselman

et al. 2024

Drones

View full text Add to dashboard Cite

show abstract

“…Nano drones can be equipped with small laser rangers [1], [2], [17]- [19] or sonars [20] to avoid obstacles at short distances. Some research focused on optical flow estimation using a dedicated optical flow sensor [21] or cameras [22], [23].…”

Section: A Obstacle Avoidance Of Nano Dronesmentioning

confidence: 99%

Channel-Aware Distillation Transformer for Depth Estimation on Nano Drones

Zhang¹,

Nex²,

Vosselman³

et al. 2023

Preprint

View full text Add to dashboard Cite

Autonomous navigation of drones using computer vision has achieved promising performance. Nano-sized drones based on edge computing platforms are lightweight, flexible, and cheap, thus suitable for exploring narrow spaces. However, due to their extremely limited computing power and storage, vision algorithms designed for high-performance GPU platforms cannot be used for nano drones. To address this issue this paper presents a lightweight CNN depth estimation network deployed on nano drones for obstacle avoidance. Inspired by Knowledge Distillation (KD), a Channel-Aware Distillation Transformer (CADiT) is proposed to facilitate the small network to learn knowledge from a larger network. The proposed method is validated on the KITTI dataset and tested on a nano drone Crazyflie, with an ultra-low power microprocessor GAP8.

show abstract

“…Some recent researches use the latest 8x8 VL53L5CX sensor, which can produce an 8x8 depth image of the observed surface. This is a unique feature for a miniature ToF sensor and has previously been implemented for the purpose of indoor navigation [28] and obstacle avoidance [29] to improve autonomous navigation, but no classification of physical objects has been done based on a depth image of this sensor.…”

Section: Related Workmentioning

confidence: 99%

Miniature Mobile Robot Detection Using an Ultralow-Resolution Time-of-Flight Sensor

Pleterski,

Škulj,

Esnault

et al. 2023

IEEE Trans. Instrum. Meas.

View full text Add to dashboard Cite

Miniature mobile robots in multi-robotic systems require reliable environmental perception for successful navigation, especially when operating in the real-world environment. One of the sensors that have recently become accessible in microrobotics due to their size and cost-effectiveness is a multi-zone time-offlight (ToF) sensor. In this research, object classification using a convolutional neural network (CNN) based on an ultra-low resolution ToF sensor is implemented on a miniature mobile robot to distinguish the robot from other objects. The main contribution of this work is an accurate classification system implemented on low resolution, low processing power and low power consumption hardware. The developed system consists of a VL53L5CX ToF sensor with an 8x8 depth image and a low-power RP2040 microcontroller. The classification system is based on a customised CNN architecture to determine the presence of a miniature mobile robot within the observed terrain, primarily characterized by sand and rocks. The developed system trained on a custom dataset can detect a mobile robot with an accuracy of 91.8% when deployed on a microcontroller. The model implementation requires 7 kB of RAM, has an inference time of 34 ms, and an energy consumption during inference of 3.685 mJ.

show abstract

Towards a Multi-Pixel Time-of-Flight Indoor Navigation System for Nano-Drone Applications

Cited by 18 publications

References 63 publications

End-to-End Nano-Drone Obstacle Avoidance for Indoor Exploration

End-to-End Nano-Drone Obstacle Avoidance for Indoor Exploration

Channel-Aware Distillation Transformer for Depth Estimation on Nano Drones

Miniature Mobile Robot Detection Using an Ultralow-Resolution Time-of-Flight Sensor

Contact Info

Product

Resources

About