TinyDEVO compresses deep event-based visual odometry to run at 1.2 fps on a 9-core RISC-V MCU at 86 mW with only 19 cm higher trajectory error than the much larger DEVO model.
Distilling Tiny and Ultrafast Deep Neural Networks for Autonomous Navigation on Nano-Uavs.IEEE Internet of Things Journal, 11(20):33269–33281, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.IV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TinyDEVO: Deep Event-based Visual Odometry on Ultra-low-power Multi-core Microcontrollers
TinyDEVO compresses deep event-based visual odometry to run at 1.2 fps on a 9-core RISC-V MCU at 86 mW with only 19 cm higher trajectory error than the much larger DEVO model.