End to end collision avoidance based on optical flow and neural networks

11/06/2019
by   Jan Blumenkamp, et al.
0

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.

READ FULL TEXT
research
03/17/2022

Collision Avoidance of 3-Dimensional Objects in Dynamic Environments

Achieving collision avoidance between moving objects is an important obj...
research
07/07/2022

Flow Synthesis Based Visual Servoing Frameworks for Monocular Obstacle Avoidance Amidst High-Rises

We propose a novel flow synthesis based visual servoing framework enabli...
research
05/13/2019

Leveraging synthetic imagery for collision-at-sea avoidance

Maritime collisions involving multiple ships are considered rare, but in...
research
06/03/2021

Formally Verified Next-Generation Airborne Collision Avoidance Games in ACAS X

The design of aircraft collision avoidance algorithms is a subtle but im...
research
03/02/2019

Verifying Aircraft Collision Avoidance Neural Networks Through Linear Approximations of Safe Regions

The next generation of aircraft collision avoidance systems frame the pr...
research
10/09/2018

Deep Neural Network Compression for Aircraft Collision Avoidance Systems

One approach to designing decision making logic for an aircraft collisio...
research
09/27/2016

Reactive Collision Avoidance using Evolutionary Neural Networks

Collision avoidance systems can play a vital role in reducing the number...

Please sign up or login with your details

Forgot password? Click here to reset