Dear self-driving car, how do you deal with uncertainties?

Reinforcement learning optimization under uncertainties. Here I present research with Lucas Vogt, Jan Dohmen and Christoph Friebel.

Here I present research with Lucas Vogt, Jan Dohmen and Christoph Friebel.

TL;DR: Controls for technical systems can be optimized in the simulation. In reality, however, numerous unknowns are waiting for us. In this post, we show how the addition of noise and sensor errors affects the optimization result of a Reinforcement Learning agent.

Motivation

“Better safe than sorry!”

The most car drivers are following this idea because in the long run, it is more advantageous to sometimes obtain a suboptimal result than to push for an optimal result every time. For example, motorists seldom push the performance of their vehicle to the limit, preferring to minimize the possibility of misjudgment, which could lead to accidents, and accepting that they will reach their destination later than is theoretically possible. During the development towards autonomous driving, this observation raises the question of how control algorithms of autonomous vehicles behave under consideration of uncertainties, especially since uncertainties can lead to misjudgments and thus to misbehavior, which could end in accidents

artificial-intelligence uncertainty reinforcement-learning self-driving-cars machine-learning deep learning

Artificial Intelligence (AI) will and is currently taking over an important role in our lives — not necessarily through intelligent robots.

Foundational Concepts in the field of Deep Learning and Machine Learning. We’ll focus on TensorFlow because if one becomes a machine learning expert, these are the tools that people in the trade use everyday.

Tesla CEO Elon Musk believes level 5 self-driving cars will be completed by the end of 2020. But the limits of deep learning will make it unlikely.

Enroll now at CETPA, the best Institute in India for Artificial Intelligence Online Training Course and Certification for students & working professionals & avail 50% instant discount.

Current algorithms lean more towards narrow learning, meaning they are good at learning and solving specific types of problems under specific conditions.