I have just completed implementing a data viewer for the OSCAR (http://github.com/jrkwon/oscar).
It can show the labeled steering angles and corresponding predictions to visually perform a neural network’s inference.
I have just completed implementing a data viewer for the OSCAR (http://github.com/jrkwon/oscar).
It can show the labeled steering angles and corresponding predictions to visually perform a neural network’s inference.
The OSCAR is Open-Source Car Architecture for Research and education. This platform supports two vehicle models that are ready to be used in behavior cloning study.
Here are some demo videos.
The first one shows the fusion
drives by itself after training a Deep Neural Network in a different track.
The second one is an example of a ‘fusion’ controlled remotely.
The third one shows the rover
driven by a driving simulator that consists of a wheel with pedals and a gear shift.
The fourth video is a test mavros/setpoint_velocity/cmd_vel
.
Self-Supervised Learning and World Models by LeCun
Artificial General Intelligence (AGI) vs. Artificial Narrow Intelligence (ANI)
Self-awareness in machines can lead to more autonomous machines and ultimately into machines with consciousness.
https://medium.com/intuitionmachine/ego-motion-in-self-aware-deep-learning-91457213cfc4
Biological systems learn from interacting with the environment.