Tiny-PULP-Dronets: Squeezing Neural Networks for Faster and Lighter Inference on Multi-Tasking Autonomous Nano-Drones

Author:

Lamberti Lorenzo1,Niculescu Vlad2,Barcis Michal3,Bellone Lorenzo3,Natalizio Enrico3,Benini Luca1,Palossi Daniele2

Affiliation:

1. University of Bologna,Department of Electrical, Electronic and Information Engineering,Italy

2. ETH Zürich,Integrated Systems Laboratory,Switzerland

3. Technology Innovation Institute,Autonomous Robotics Research Center,UAE

Publisher

IEEE

Reference13 articles.

1. Automated Tuning of End-to-end Neural Flight Controllers for Autonomous Nano-drones

2. Deep Residual Learning for Image Recognition

3. Sparsity in Deep Learning: Pruning and growth for efficient inference and training in neural networks;hoefler;Journal of Machine Learning Research,2021

4. RocketLogger

5. Mitigating latency problems in vision-based autonomous UAVs

Cited by 15 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. BatDeck: Advancing Nano-Drone Navigation with Low-Power Ultrasound-Based Obstacle Avoidance;2024 IEEE Sensors Applications Symposium (SAS);2024-07-23

2. Complete Coverage of Mobile Targets in Backscatter-Aided IoT Networks;IEEE Internet of Things Journal;2024-06-15

3. Stargate: Multimodal Sensor Fusion for Autonomous Navigation on Miniaturized UAVs;IEEE Internet of Things Journal;2024-06-15

4. On-device Self-supervised Learning of Visual Perception Tasks aboard Hardware-limited Nano-quadrotors;2024 IEEE International Conference on Robotics and Automation (ICRA);2024-05-13

5. A Heterogeneous RISC-V Based SoC for Secure Nano-UAV Navigation;IEEE Transactions on Circuits and Systems I: Regular Papers;2024-05

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3