Evolving large-scale neural networks for vision-based TORCS

25 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving (2015, background): “More recently, [11] train a large recurrent neural network using a reinforcement learning approach.”
A Survey of State-Action Representations for Autonomous Driving (2018, methodology): “The most commonly-occuring setting is the front-view camera, used in (Pomerleau, 1989; Cardamone et al., 2009; Ross et al., 2011; Koutník et al., 2013; Bojarski et al., 2016; Yu et al., 2016; Xu et al., 2016; Sallab et al., 2016; Eraqi et al., 2017; Koppula, 2017; Sallab et al., 2017; Codevilla et a”
Research Advances and Challenges of Autonomous and Connected Ground Vehicles (2019, methodology): “The behavior reflex approach is implemented in a TORCS (The Open Racing Car Simulator)-simulated vehicle for autonomous driving in a racetrack, which tries to optimize acceleration and braking maneuver using only images as input [335].”
Deep Steering: Learning End-to-End Driving Model from Spatial and Temporal Visual Cues (2017, methodology): “The work in [21] trained a “large”, recurrent neural networks (with over 1 million weights) using a reinforcement learning method.”
Internet of vehicles in big data era (2018, methodology): “An end-to-end self-driving system that directly maps the image to the steering control can be found in [13], [129], [130], where a mediate method between the two, mapping images to”