publication . Preprint . 2018

Active Neural Localization

Chaplot, Devendra Singh; Parisotto, Emilio; Salakhutdinov, Ruslan;
Open Access English
  • Published: 24 Jan 2018
Localization is the problem of estimating the location of an autonomous agent from an observation and a map of the environment. Traditional methods of localization, which filter the belief based on the observations, are sub-optimal in the number of steps required, as they do not decide the actions taken by the agent. We propose "Active Neural Localizer", a fully differentiable neural network that learns to localize accurately and efficiently. The proposed model incorporates ideas of traditional filtering-based localization methods, by using a structured belief of the state with multiplicative interactions to propagate belief, and combines it with a policy model ...
free text keywords: Computer Science - Learning, Computer Science - Artificial Intelligence, Computer Science - Robotics
Download from
45 references, page 1 of 3

Andrew G Barto, Richard S Sutton, and Charles W Anderson. Neuronlike adaptive elements that can solve difficult learning control problems. IEEE transactions on systems, man, and cybernetics, pp. 834-846, 1983.

Johann Borenstein, H. R. Everett, and Liqiang Feng. Navigating Mobile Robots: Systems and Techniques. A. K. Peters, Ltd., Natick, MA, USA, 1996. ISBN 1568810660.

Wolfram Burgard, Dieter Fox, Daniel Hennig, and Timo Schmidt. Estimating the absolute position of a mobile robot using position probability grids. In Proceedings of the national conference on artificial intelligence, pp. 896-901, 1996. [OpenAIRE]

Wolfram Burgard, Andrcas Derr, Dieter Fox, and Armin B Cremers. Integrating global position estimation and position tracking for mobile robots: the dynamic markov localization approach. In Intelligent Robots and Systems, 1998. Proceedings., 1998 IEEE/RSJ International Conference on, volume 2, pp. 730-735. IEEE, 1998. [OpenAIRE]

Devendra Singh Chaplot and Guillaume Lample. Arnold: An autonomous agent to play fps games. In AAAI, pp. 5085-5086, 2017.

Devendra Singh Chaplot, Guillaume Lample, Kanthashree Mysore Sathyendra, and Ruslan Salakhutdinov. Transfer deep reinforcement learning in 3d environments: An empirical study. In NIPS Deep Reinforcemente Leaning Workshop, 2016.

Luo Chunjie, Yang Qiang, et al. Cosine normalization: Using cosine similarity instead of dot product in neural networks. arXiv preprint arXiv:1702.05870, 2017. [OpenAIRE]

Ronald Clark, Sen Wang, Andrew Markham, Niki Trigoni, and Hongkai Wen. Vidloc: 6-dof video-clip relocalization. arXiv preprint arXiv:1702.06521, 2017a.

Ronald Clark, Sen Wang, Hongkai Wen, Andrew Markham, and Niki Trigoni. Vinet: Visual-inertial odometry as a sequence-to-sequence learning problem. In AAAI, pp. 3995-4001, 2017b.

Ingemar J Cox and John J Leonard. Modeling a dynamic environment using a bayesian multiple hypothesis approach. Artificial Intelligence, 66(2):311-344, 1994.

Ingemar J. Cox and Gordon T. Wilfong (eds.). Autonomous Robot Vehicles. Springer-Verlag New York, Inc., New York, NY, USA, 1990. ISBN 0-387-97240-4.

Dieter Fox. Markov localization-a probabilistic framework for mobile robot localization and navigation. PhD thesis, Universita¨t Bonn, 1998.

Dieter Fox, Wolfram Burgard, and Sebastian Thrun. Active markov localization for mobile robots. Robotics and Autonomous Systems, 25(3-4):195-207, 1998.

V Fox, Jeffrey Hightower, Lin Liao, Dirk Schulz, and Gaetano Borriello. Bayesian filtering for location estimation. IEEE pervasive computing, 2(3):24-33, 2003.

Ivo Grondman, Lucian Busoniu, Gabriel AD Lopes, and Robert Babuska. A survey of actor-critic reinforcement learning: Standard and natural policy gradients. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews), 42(6):1291-1307, 2012. [OpenAIRE]

45 references, page 1 of 3
Powered by OpenAIRE Open Research Graph
Any information missing or wrong?Report an Issue