End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning

Pérot, Etienne; Jaritz, Maximilian; Toromanoff, Marin; Charette, Raoul de

doi:10.1109/cvprw.2017.64

Cited by 71 publications

(38 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We propose a method ( fig. 1) benefiting from recent asynchronous learning [13] and building on our preliminary work [17] to train an end-to-end agent in World Rally Championship 6 (WRC6), a realistic car racing game with stochastic behavior (animations, light). In addition to remain close to real driving conditions we rely only on image and speed to predict the full longitudinal and lateral control of the car.…”

Section: Introductionmentioning

confidence: 99%

End-to-End Race Driving with Deep Reinforcement Learning

Jaritz

Charette

Toromanoff

et al. 2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

172

118

View full text Add to dashboard Cite

We present research using the latest reinforcement learning algorithm for end-to-end driving without any mediated perception (object recognition, scene understanding). The newly proposed reward and learning strategies lead together to faster convergence and more robust driving using only RGB image from a forward facing camera. An Asynchronous Actor Critic (A3C) framework is used to learn the car control in a physically and graphically realistic rally game, with the agents evolving simultaneously on tracks with a variety of road structures (turns, hills), graphics (seasons, location) and physics (road adherence). A thorough evaluation is conducted and generalization is proven on unseen tracks and using legal speed limits. Open loop tests on real sequences of images show some domain adaption capability of our method.

show abstract

Section: Introductionmentioning

confidence: 99%

End-to-End Race Driving with Deep Reinforcement Learning

Jaritz

Charette

Toromanoff

et al. 2018

2018 IEEE International Conference on Robotics and Automation (ICRA)

Self Cite

172

118

View full text Add to dashboard Cite

show abstract

“…End2End control papers mainly employ either deep neural networks trained offline on real‐world and/or synthetic data (Bechtel et al, ; Bojarski et al, ; C. Chen, Seff, Kornhauser, & Xiao, ; Eraqi et al, ; Fridman et al, ; Hecker et al, ; Rausch et al, ; Xu et al, ; S. Yang et al, ), or DRL systems trained and evaluated in simulation (Jaritz et al, ; Perot, Jaritz, Toromanoff, & Charette, ; Sallab et al, 2017b). Methods for porting simulation trained DRL models to real‐world driving have also been reported (Wayve, 2018), as well as DRL systems trained directly on real‐world image data (Pan et al, , ).…”

Section: Motion Controllers For Ai‐based Self‐driving Carsmentioning

confidence: 99%

“…Chen, Seff, Kornhauser, & Xiao, 2015;Eraqi et al, 2017;Fridman et al, 2017;Hecker et al, 2018;Rausch et al, 2017;Xu et al, 2017;S. Yang et al, 2017a), or DRL systems trained and evaluated in simulation(Jaritz et al, 2018;Perot, Jaritz, Toromanoff, & Charette, 2017;Sallab et al, 2017b). Methods for porting simulation trained DRL models to real-world driving have also been reported (Wayve, 2018), as well as DRL systems trained directly on real-world image data(Pan et al, 2017(Pan et al, , 2018.End2End methods have been popularized in the last couple of years by NVIDIA ® , as part of the PilotNet architecture.…”

mentioning

confidence: 99%

A survey of deep learning techniques for autonomous driving

Grigorescu

Trasnea

Cocias

et al. 2019

Journal of Field Robotics

1,214

495

View full text Add to dashboard Cite

The last decade witnessed increasingly rapid progress in self‐driving vehicle technology, mainly backed up by advances in the area of deep learning and artificial intelligence (AI). The objective of this paper is to survey the current state‐of‐the‐art on deep learning technologies used in autonomous driving. We start by presenting AI‐based self‐driving architectures, convolutional and recurrent neural networks, as well as the deep reinforcement learning paradigm. These methodologies form a base for the surveyed driving scene perception, path planning, behavior arbitration, and motion control algorithms. We investigate both the modular perception‐planning‐action pipeline, where each module is built using deep learning methods, as well as End2End systems, which directly map sensory information to steering commands. Additionally, we tackle current challenges encountered in designing AI architectures for autonomous driving, such as their safety, training data sources, and computational hardware. The comparison presented in this survey helps gain insight into the strengths and limitations of deep learning and AI approaches for autonomous driving and assist with design choices.

show abstract

“…With the paper ViZDoom: A Doom-based AI Research Platform for Visual Reinforcement Learning Kempka et al illustrated that an RL agent could successfully learn to play the game Doom, a first-person shooter game, with behavior similar to humans. [29] G. DeepMind Lab…”

Section: E Malmo Platformmentioning

confidence: 99%

Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games

Andersen

Goodwin

Granmo

2018

2018 IEEE Conference on Computational Intelligence and Games (CIG)

View full text Add to dashboard Cite

Reinforcement learning (RL) is an area of research that has blossomed tremendously in recent years and has shown remarkable potential for artificial intelligence based opponents in computer games. This success is primarily due to the vast capabilities of convolutional neural networks, that can extract useful features from noisy and complex data. Games are excellent tools to test and push the boundaries of novel RL algorithms because they give valuable insight into how well an algorithm can perform in isolated environments without the real-life consequences. Real-time strategy games (RTS) is a genre that has tremendous complexity and challenges the player in short and long-term planning. There is much research that focuses on applied RL in RTS games, and novel advances are therefore anticipated in the not too distant future. However, there are to date few environments for testing RTS AIs. Environments in the literature are often either overly simplistic, such as microRTS, or complex and without the possibility for accelerated learning on consumer hardware like StarCraft II. This paper introduces the Deep RTS game environment for testing cutting-edge artificial intelligence algorithms for RTS games. Deep RTS is a highperformance RTS game made specifically for artificial intelligence research. It supports accelerated learning, meaning that it can learn at a magnitude of 50 000 times faster compared to existing RTS games. Deep RTS has a flexible configuration, enabling research in several different RTS scenarios, including partially observable state-spaces and map complexity. We show that Deep RTS lives up to our promises by comparing its performance with microRTS, ELF, and StarCraft II on high-end consumer hardware. Using Deep RTS, we show that a Deep Q-Network agent beats random-play agents over 70% of the time. Deep RTS is publicly available at https://github.com/cair/DeepRTS.

show abstract

End-to-End Driving in a Realistic Racing Game with Deep Reinforcement Learning

Cited by 71 publications

References 3 publications

End-to-End Race Driving with Deep Reinforcement Learning

End-to-End Race Driving with Deep Reinforcement Learning

A survey of deep learning techniques for autonomous driving

Deep RTS: A Game Environment for Deep Reinforcement Learning in Real-Time Strategy Games

Contact Info

Product

Resources

About