An Open Source and Open Hardware Deep Learning-Powered Visual Navigation Engine for Autonomous Nano-UAVs

@article{Palossi2019AnOS,
  title={An Open Source and Open Hardware Deep Learning-Powered Visual Navigation Engine for Autonomous Nano-UAVs},
  author={D. Palossi and Francesco Conti and L. Benini},
  journal={2019 15th International Conference on Distributed Computing in Sensor Systems (DCOSS)},
  year={2019},
  pages={604-611}
}
Nano-size unmanned aerial vehicles (UAVs), with few centimeters of diameter and sub-10 Watts of total power budget, have so far been considered incapable of running sophisticated visual-based autonomous navigation software without external aid from base-stations, ad-hoc local positioning infrastructure, and powerful external computation servers. [...] Key Method Our visual navigation engine is enabled by the combination of an ultra-low power computing device (the GAP8 system-on-chip) with a novel methodology…Expand
Automated Tuning of End-to-end Neural Flight Controllers for Autonomous Nano-drones
Proximity Estimation Using Vision Features Computed On Sensor
A Flexible, Low-Power Platform for UAV-Based Data Collection From Remote Sensors
Latency-aware and -predictable Communication with Open Protocol Stacks for Remote Drone Control
Technical Report: NEMO DNN Quantization for Deployment Model
Heterogeneous Knowledge Distillation Using Information Flow Modeling

References

SHOWING 1-10 OF 24 REFERENCES
Ultra low-power visual odometry for nano-scale unmanned aerial vehicles
Target following on nano-scale Unmanned Aerial Vehicles
An 879GOPS 243mW 80fps VGA Fully Visual CNN-SLAM Processor for Wide-Range Autonomous Exploration
Navion: A Fully Integrated Energy-Efficient Visual-Inertial Odometry Accelerator for Autonomous Navigation of Nano Drones
Autonomous aerial navigation using monocular visual-inertial fusion
DroNet: Learning to Fly by Driving
A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots
Generalization through Simulation: Integrating Simulated and Real Data into Deep Reinforcement Learning for Vision-Based Autonomous Flight
Optic-Flow Based Control of a 46g Quadrotor
...
1
2
3
...