DeepAI AI Chat
Log In Sign Up

From Simulation to Real World Maneuver Execution using Deep Reinforcement Learning

05/13/2020
by   Alessandro Paolo Capasso, et al.
UNIVERSITÀ DEGLI STUDI DI PARMA
0

Deep Reinforcement Learning has proved to be able to solve many control tasks in different fields, but the behavior of these systems is not always as expected when deployed in real-world scenarios. This is mainly due to the lack of domain adaptation between simulated and real-world data together with the absence of distinction between train and test datasets. In this work, we investigate these problems in the autonomous driving field, especially for a maneuver planning module for roundabout insertions. In particular, we present a system based on multiple environments in which agents are trained simultaneously, evaluating the behavior of the model in different scenarios. Finally, we analyze techniques aimed at reducing the gap between simulated and real-world data showing that this increased the generalization capabilities of the system both on unseen and real-world scenarios.

READ FULL TEXT

page 2

page 3

page 6

07/05/2022

Tackling Real-World Autonomous Driving using Deep Reinforcement Learning

In the typical autonomous driving stack, planning and control systems re...
07/25/2021

DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learning

How to explore corner cases as efficiently and thoroughly as possible ha...
10/20/2022

Deep reinforcement learning oriented for real world dynamic scenarios

Autonomous navigation in dynamic environments is a complex but essential...
09/24/2020

Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey

Deep reinforcement learning has recently seen huge success across multip...
01/03/2020

Intelligent Roundabout Insertion using Deep Reinforcement Learning

An important topic in the autonomous driving research is the development...
10/02/2021

Cycle-Consistent World Models for Domain Independent Latent Imagination

End-to-end autonomous driving seeks to solve the perception, decision, a...