2020

BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

Kahn, Gregory, Abbeel, Pieter, Levine, Sergey

Understand

Mobile robot navigation is typically regarded as a geometric problem, in which the robot's objective is to perceive the geometry of the environment in order to plan collision-free paths towards a desired goal.

However, a purely geometric view of the world can can be insufficient for many navigation problems.
For example, a robot navigating based on geometry may avoid a field of tall grass because it believes it is untraversable, and will therefore fail to reach its desired goal.
In this work, we investigate how to move beyond these purely geometric-based approaches using a method that learns about physical navigational affordances from experience.

Built on

Application of intelligent automata to reconnaissance
C Rosen and N Nilsson · 1968
Earlier work this paper cites.
Vision and navigation for the Carnegie-Mellon Navlab
Charles Thorpe, Martial H Hebert, Takeo Kanade, and Steven A Shafer · 1988
Earlier work this paper cites.
Long short-term memory
Sepp Hochreiter and Jürgen Schmidhuber · 1997
Earlier work this paper cites.
High speed obstacle avoidance using monocular vision and reinforcement learning
Jeff Michels, Ashutosh Saxena, and Andrew Y Ng · 2005
Earlier work this paper cites.
Stanley: The robot that won the darpa grand challenge
Sebastian Thrun, Mike Montemerlo, Hendrik Dahlkamp, David Stavens, Andrei Aron, James Diebel, Philip Fong, John Gale, Morgan Halpenny, Gabriel Hoffmann, et al · 2006
Earlier work this paper cites.
Learning to drive a real car in 20 minutes
Martin Riedmiller, Mike Montemerlo, and Hendrik Dahlkamp · 2007
Earlier work this paper cites.
Probabilistic Robotics
S. Thrun, W. Burgard, and D. Fox · 2008
Earlier work this paper cites.
Real-time indoor autonomous vehicle test environment
Jonathan P How, Brett Behihke, Adrian Frank, Daniel Dale, and John Vian · 2008
Earlier work this paper cites.
Flying fast and low among obstacles: Methodology and experiments
Sebastian Scherer, Sanjiv Singh, Lyle Chamberlain, and Mike Elgersma · 2008
Earlier work this paper cites.
Autonomous driving in urban environments: Boss and the urban challenge
Chris Urmson and et. al · 2008
Earlier work this paper cites.
Learning long-range vision for autonomous off-road driving
Raia Hadsell, Pierre Sermanet, Jan Ben, Ayse Erkan, Marco Scoffier, Koray Kavukcuoglu, Urs Muller, and Yann LeCun · 2009
Earlier work this paper cites.
Imagenet: A large-scale hierarchical image database
Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei · 2009
Earlier work this paper cites.
Visual teach and repeat for long-range rover autonomy
Paul Furgale and Timothy D Barfoot · 2010
Earlier work this paper cites.

Similar

Autonomous multi-floor indoor navigation with a computationally constrained MAV
Shaojie Shen, Nathan Michael, and Vijay Kumar · 2011
Cited alongside, same era.
Learning monocular reactive uav control in cluttered natural environments
Original
Stéphane Ross, Narek Melik-Barkhudarov, Kumar Shaurya Shankar, Andreas Wendel, Debadeepta Dey, J Andrew Bagnell, and Martial Hebert · 2013
Cited alongside, same era.
The cross-entropy method: a unified approach to combinatorial optimization, Monte-Carlo simulation and machine learning
Reuven Y Rubinstein and Dirk P Kroese · 2013
Cited alongside, same era.
Visual simultaneous localization and mapping: a survey
Jorge Fuentes-Pacheco, Jose Ruiz-Ascencio, and Juan Manuel Rendon-Mancha · 2015
Cited alongside, same era.
End to end learning for self-driving cars
Original
Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal, Lawrence D Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, et al · 2016
Cited alongside, same era.
Adapnet: Adaptive semantic segmentation in adverse environmental conditions
Abhinav Valada, Johan Vertens, Ankit Dhall, and Wolfram Burgard · 2017
Cited alongside, same era.
Duckietown: an open, inexpensive and flexible platform for autonomy education and research
Liam Paull, Jacopo Tani, Heejin Ahn, Javier Alonso-Mora, Luca Carlone, Michal Cap, Yu Fan Chen, Changhyun Choi, Jeff Dusek, Yajun Fang, et al · 2017
Cited alongside, same era.
Safe Visual Navigation via Deep Learning and Novelty Detection
Charles Richter and Nick Roy · 2017
Cited alongside, same era.
(CAD)2 RL: Real Single-Image Flight without a Single Real Image
Original
Fereshteh Sadeghi and Sergey Levine · 2017
Cited alongside, same era.
Learning to fly by crashing
Original
Dhiraj Gandhi, Lerrel Pinto, and Abhinav Gupta · 2017
Cited alongside, same era.
Gonet: A semi-supervised deep learning approach for traversability estimation
Original
Noriaki Hirose, Amir Sadeghian, Marynel Vázquez, Patrick Goebel, and Silvio Savarese · 2018
Cited alongside, same era.
Deep ordinal regression network for monocular depth estimation
Original
Huan Fu, Mingming Gong, Chaohui Wang, Kayhan Batmanghelich, and Dacheng Tao · 2018
Cited alongside, same era.

Then

End-to-end driving via conditional imitation learning
Felipe Codevilla, Matthias Miiller, Antonio López, Vladlen Koltun, and Alexey Dosovitskiy · 2018
Later among the works it cites.
Semi-parametric topological memory for navigation
Original
Nikolay Savinov, Alexey Dosovitskiy, and Vladlen Koltun · 2018
Later among the works it cites.
Learning deployable navigation policies at kilometer scale from a single traversal
Original
Jake Bruce, Niko Sünderhauf, Piotr Mirowski, Raia Hadsell, and Michael Milford · 2018
Later among the works it cites.
Dronet: Learning to fly by driving
Antonio Loquercio, Ana I Maqueda, Carlos R Del-Blanco, and Davide Scaramuzza · 2018
Later among the works it cites.
Benchmarking reinforcement learning algorithms on real-world robots
A Rupam Mahmood, Dmytro Korenkevych, Gautham Vasan, William Ma, and James Bergstra · 2018
Later among the works it cites.
Rainbow: Combining improvements in deep reinforcement learning
Original
Matteo Hessel, Joseph Modayil, Hado Van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horgan, Bilal Piot, Mohammad Azar, and David Silver · 2018
Later among the works it cites.
Pseudo-lidar from visual depth estimation: Bridging the gap in 3d object detection for autonomous driving
Original
Yan Wang, Wei-Lun Chao, Divyansh Garg, Bharath Hariharan, Mark Campbell, and Kilian Q Weinberger · 2019
Later among the works it cites.
Where should I walk? Predicting terrain properties from images via self-supervised learning
Lorenz Wellhausen, Alexey Dosovitskiy, René Ranftl, Krzysztof Walas, Cesar Cadena, and Marco Hutter · 2019
Later among the works it cites.
Neural Autonomous Navigation with Riemannian Motion Policy
Original
Xiangyun Meng, Nathan Ratliff, Yu Xiang, and Dieter Fox · 2019
Later among the works it cites.
Learning navigation behaviors end-to-end with autorl
Original
Hao-Tien Lewis Chiang, Aleksandra Faust, Marek Fiser, and Anthony Francis · 2019
Later among the works it cites.
Deep Visual MPC-Policy Learning for Navigation
Original
Noriaki Hirose, Fei Xia, Roberto Martín-Martín, Amir Sadeghian, and Silvio Savarese · 2019
Later among the works it cites.
Learning to drive in a day
Original
Alex Kendall, Jeffrey Hawke, David Janz, Przemyslaw Mazur, Daniele Reda, John-Mark Allen, Vinh-Dieu Lam, Alex Bewley, and Amar Shah · 2019
Later among the works it cites.
Deep Dynamics Models for Learning Dexterous Manipulation
Original
Anusha Nagabandi, Kurt Konoglie, Sergey Levine, and Vikash Kumar · 2019
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…

Reading the bibliography…