Tackling Real-World Autonomous Driving using Deep Reinforcement Learning

no code implementations • 5 Jul 2022 • Paolo Maramotti, Alessandro Paolo Capasso, Giulio Bacchiani, Alberto Broggi

In this work, we propose a model-free Deep Reinforcement Learning Planner training a neural network that predicts both acceleration and steering angle, thus obtaining a single module able to drive the vehicle using the data processed by localization and perception algorithms on board of the self-driving car.

Autonomous Driving reinforcement-learning +1

From Simulation to Real World Maneuver Execution using Deep Reinforcement Learning

no code implementations • 13 May 2020 • Alessandro Paolo Capasso, Giulio Bacchiani, Alberto Broggi

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.

Autonomous Driving Domain Adaptation +2

Intelligent Roundabout Insertion using Deep Reinforcement Learning

no code implementations • 3 Jan 2020 • Alessandro Paolo Capasso, Giulio Bacchiani, Daniele Molinari

An important topic in the autonomous driving research is the development of maneuver planning systems.

Autonomous Driving reinforcement-learning +1

Microscopic Traffic Simulation by Cooperative Multi-agent Deep Reinforcement Learning

no code implementations • 4 Mar 2019 • Giulio Bacchiani, Daniele Molinari, Marco Patander

Expert human drivers perform actions relying on traffic laws and their previous experience.

reinforcement-learning Reinforcement Learning (RL)