Ultra low-power visual odometry for nano-scale unmanned aerial vehicles
By Daniele Palossi, Andrea Marongiu, Luca Benini. 2017
16 citations recorded by the source corpus.
One of the fundamental functionalities for autonomous navigation of Unmanned Aerial Vehicles (UAVs) is the hovering capability. State-of-the-art techniques for implementing hovering on standard-size UAVs process camera stream to determine position and orientation (visual odometry). Similar techniques are considered unaffordable in the context of nano-scale UAVs (i.e. few centimeters of diameter), where the ultra-constrained power-envelopes of tiny rotor-crafts limit the onboard computational capabilities to those of low-power microcontrollers. In this work we study how the emerging ultra-low-power parallel computing paradigm could enable the execution of complex hovering algorithmic flows onto nano-scale UAVs. We provide insight on the software pipeline, the parallelization opportunities and the impact of several algorithmic enhancements. Results demonstrate that the proposed software flow and architecture can deliver unprecedented GOPS/W, achieving 117 frame-per-second within a power envelope of 10 mW.
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
- Daniele Palossi
- Antonio Loquercio
- Davide Scaramuzza
- Francesco Conti
- Luca Benini
- Eric Flamand
- Jaskirat Singh
- Michele Magno
Citations in the corpus
- A 64-mW DNN-Based Visual Navigation Engine for Autonomous Nano-Drones (2018, background): “Instead, the down-looking camera configuration is usually chosen for stabilization tasks like distance estimation [43], way-point tracking, and positioning [44], etc.”
- Extending the Lifetime of Nano-Blimps via Dynamic Motor Control (2018, unknown): “The popularity of nano-size unmanned aerial vehicles (nUAVs), typically weighing ∼50 g, has increased significantly in the past few years [30, 31].”
- Target following on nano-scale Unmanned Aerial Vehicles (2017, methodology): “Thus, an ultralow-power parallel platform [2] is a promising solution to push autonomous navigation functions beyond the current limits.”