PRGFlow: Benchmarking SWAP-Aware Unified Deep Visual Inertial Odometry

Nitin J. Sanket
Chahat Deep Singh
Cornelia Fermüller
Yiannis Aloimonos

Perception and Robotics Group
University of Maryland, College Park


Odometry on aerial robots has to be of low latency and high robustness whilst also respecting the Size, Weight, Area and Power (SWAP) constraints as demanded by the size of the robot. A combination of visual sensors coupled with Inertial Measurement Units (IMUs) has proven to be the best combination to obtain robust and low latency odometry on resource-constrained aerial robots. Recently, deep learning approaches for Visual Inertial fusion have gained momentum due to their high accuracy and robustness. However, the remarkable advantages of these techniques are their inherent scalability (adaptation to different sized aerial robots) and unification (same method works on different sized aerial robots) by utilizing compression methods and hardware acceleration, which have been lacking from previous approaches. To this end, we present a deep learning approach for visual translation estimation and loosely fuse it with an Inertial sensor for full 6 DoF odometry estimation. We also present a detailed benchmark comparing different architectures, loss functions and compression methods to enable scalability. We evaluate our network on the MSCOCO dataset and evaluate the VI fusion on multiple real-flight trajectories

Figure: Size comparison of various components used on quadrotors. (a) Snapdragon Flight, (b) PixFalcon, (c) 120 mm quadrotor platform with NanoPi Neo Core 2, (d) MYNT EYE stereo camera, (e) Google Coral USB accelerator, (f) Sipeed Maix Bit, (g) PX4Flow, (h) 210 mm quadrotor platform with Coral Dev board, (i) 360 mm quadrotor platform with Intel Up board, (j) 500 mm quadrotor platform with NVIDIA Jetson TX2. Note that all components shown are to relative scale. All the images in this paper are best viewed in color.


Nitin J. Sanket, Chahat Deep Singh, Cornelia Fermüller, Yiannis Aloimonos.