Learning long-range vision for autonomous off-road driving

By Raia Hadsell, Pierre Sermanet, Jan Ben, Ayse Erkan, Marco Scoffier, Koray Kavukcuoglu, Urs Muller, Yann LeCun. 2009

123 citations recorded by the source corpus.

Subfields: Aerospace Engineering, 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 Aerospace Engineering

In Computer Vision and Pattern Recognition

In Reinforcement Learning

Citations in the corpus

End-to-End Training of Deep Visuomotor Policies (2015, background): “Many prior robotic applications of CNNs do not directly consider control, but employ CNNs for the perception component of a larger robotic system (Hadsell et al., 2009; Sung et al., 2015; Lenz et al., 2015b; Pinto and Gupta, 2015).”
A Survey of Deep Network Solutions for Learning Control in Robotics: From Reinforcement to Imitation (2016, neutral): “ping task. The output of the deep-learning model is the grasp success probability. Besides visual servoing, several works used CNN models to realize outdoor scene segmentation (Sermanet et al., 2009; Hadsell et al., 2009) based on stereo vision. Multi-range traversability and moving cost-map were es”
Depth Map Prediction from a Single Image using a Multi-Scale Deep Network (2014, background): “In turn, such relations help provide richer representations of objects and their environment, often leading to improvements in existing recognition tasks [18], as well as enabling many further applications such as 3D modeling [16, 6], physics and support models [18], robotics [4, 14], and potentiall”
Driving Policy Transfer via Modularity and Abstraction (2018, background): “real vehicles has only been demonstrated in restricted environments [23]. Finally, some approaches have explored the space between traditional modular pipelines and endto-end learning. Hadsell et al. [17] train a perception system via self-supervised learning and use it in a standard navigation pipe”
Cognitive Mapping and Planning for Visual Navigation (2017, background): “e form of structure from motion and simultaneous localization and mapping [25,37,40,69] with a variety of sensing modalities such as range sensors, RGB cameras and approach. Learning based approaches [32,78] study the problem in isolation thus only learning generic task-independent maps. Path planni”
Safe Visual Navigation via Deep Learning and Novelty Detection (2017, methodology): “Deep learning has been shown to be well suited to extracting useful information for navigation from raw sensor data such as camera images [13, 27].”
Aggressive Deep Driving: Combining Convolutional Neural Networks and Model Predictive Control (2017, background): “[17] learns a neural network to predict far-field traversibility from images, which is then fed into a separate planning and control framework.”
Learning from Demonstration for Autonomous Navigation in Complex Unstructured Terrain (2010, background): “Examples of such approaches include learning to interpret monocular vision systems from shorter range LiDAR (Dahlkamp et al. 2006) or stereo (Hadsell et al. 2009) range data, learning to map near range traversability estimates to far-range estimates (Procopio et al. 2007; Bajracharya et al. 2008),…”
DaDianNao: A Machine-Learning Supercomputer (2014, background): “…have become ubiquitous in a very broad range of applications and cloud services; examples include speech recognition, e.g., Siri or Google Now, click-through prediction for placing ads [27], face identiﬁcation in Apple iPhoto or Google Picasa, robotics [20], pharmaceutical research [9] and so on.”
Deep Neural Networks for wireless localization in indoor and outdoor environments (2016, background): “Deep Neural Networks (DNNs) have been applied to tackle such kinds of problems with notable success, beating state-of-the-art techniques in certain areas such as vision [15] [16] [17] [18], audio [19] [20] [21] and robotics [22] [23].”
Using Non-invertible Data Transformations to Build Adversary-Resistant Deep Neural Networks (2016, background): “Recent interest has been to integrate it into critical fields like medical imaging [1], [37] and self-driving cars [13], [8].”
An Introduction to Deep Learning (2011, unknown): “Deep networks have been largely applied to visual classification databases such as handwritten digits1, object categories2 3 4, pedestrian detection [33] or offroad robot navigation [34], and also on acoustic signals to perform audio classification [35].”
Bayesian Learning for Safe High-Speed Navigation in Unknown Environments (2015, methodology): “One example from the DARPA LAGR program used deep learning to classify traversable terrain up to 100 m away [11].”
Joint Task-Recursive Learning for Semantic Segmentation and Depth Estimation (2018, background): “Recently, driven by deep learning techniques, the study on them has seen great progress and starts to benefit some potential applications such as scene understanding [1], robotics [2], autonomous driving [3] and simultaneous localization and mapping (SLAM) system [4].”