End to end collision avoidance based on optical flow and neural networks
arXiv:1911.08582v12 citations
Originality Synthesis-oriented
AI Analysis
This work addresses collision avoidance for autonomous vehicles, but appears incremental as it applies existing methods to a new domain.
The paper tackled collision avoidance by implementing a neural network system based on optical flow, deploying and evaluating it on a refitted car.
Optical flow is believed to play an important role in the agile flight of birds and insects. Even though it is a very simple concept, it is rarely used in computer vision for collision avoidance. This work implements a neural network based collision avoidance which was deployed and evaluated on a solely for this purpose refitted car.