ALVINN, an autonomous land vehicle in a neural network

By Dean A. Pomerleau. 2015

Subfields: Computer Vision and Pattern Recognition, Reinforcement Learning

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Reinforcement Learning

Citations in the corpus

Perceiver IO: A General Architecture for Structured Inputs & Outputs (2021, background): “Without tuning any additional parameters, we observed that the resulting agent reached the same level of performance as the original AlphaStar agent, reaching an 87% win-rate versus the Elite bot after behavioral cloning [61] on human data.”
End-to-End Training of Deep Visuomotor Policies (2015, methodology): “Pioneering early work on neural network control used small, simple networks [10, 33], and has largely been supplanted by methods that use carefully designed policies that can be learned efﬁciently with reinforcement learning [14].”
One-Shot Imitation Learning (2017, background): “, [41, 44]); and inverse reinforcement learning [37], where a reward function [1, 66, 29, 18, 22] is estimated that explains the demonstrations as (near) optimal behavior.”
Imitating Interactive Intelligence (2020, methodology): “Imitation learning has been successfully deployed to build agents for self-driving cars (Pomerleau, 1989), robotics and biomimetic motor control (Schaal, 1999), game play (Silver et al., 2016; Vinyals et al., 2019), and language modeling (Shannon, 1951).”
Learning to See by Moving (2015, background): “[33] trained neural networks for driving vehicles directly from visual input.”
End to End Learning for Self-Driving Cars (2016, methodology): “In many ways, DAVE-2 was inspired by the pioneering work of Pomerleau [6] who in 1989 built the Autonomous Land Vehicle in a Neural Network (ALVINN) system.”
Self-Driving Car Steering Angle Prediction Based on Image Recognition (2019, background): “earning helps to mitigate the amount of training data needed to create a high quality model. 2. Related Work Using a neural network for autonomous vehicle navigation was pioneered by Pomerleau (1989) [13] who built the Autonomous Land Vehicle in a Neural Network (ALVINN) system. The model structure ”
Deep Reinforcement Learning for Autonomous Driving: A Survey (2020, background): “Early work on Behavior Cloning (BC) for driving cars in [112], [113] presented agents that learn form demonstrations (LfD) that tries to mimic the behavior of an expert.”
Driving Policy Transfer via Modularity and Abstraction (2018, background): “ed in the range of environmental and trafﬁc conditions that can be handled. End-to-end deep learning methods aim to substitute laborious hand-engineering by training driving policies directly on data [37,25,3]. However, these solutions are difﬁcult to scale to realistic urban driving. A huge amount ”
Self-Supervised Deep Reinforcement Learning with Generalized Computation Graphs for Robot Navigation (2017, background): “dances [16], and end-to-end driving from demonstrations [17], [18].”
Learning to Generalize Across Long-Horizon Tasks from Human Demonstrations (2020, background): “Imitation Learning (IL) is a promising paradigm to train physical robots on complex manipulation skills by replicating behavior from expert demonstrations [32, 24].”
A Framework for Data-Driven Robotics (2019, background): “Demonstrations can also be incorporated through Behavioral Cloning (BC) [27], [28], but this requires high-quality consistent demonstrations of the target task.”
Composable Action-Conditioned Predictors: Flexible Off-Policy Learning for Robot Navigation (2018, background): “Much of the prior work on learning-based robot navigation has focused on imitation learning [19, 20, 21, 22, 23], which requires demonstrations.”
Deep Imitative Models for Flexible Inference, Planning, and Control (2018, neutral): “A common straightforward approach to IL is behavior-cloning: learning to predict the actions taken by a demonstrator (Pomerleau, 1989; Bojarski et al., 2016; Mahler & Goldberg, 2017; Codevilla et al., 2018).”
Learning to Drive in a Day (2018, methodology): “We compare to simple naive baselines, as well as imitation learning approaches [18].”