Target-driven visual navigation in indoor scenes using deep reinforcement learning

@article{Zhu2016TargetdrivenVN,
  title={Target-driven visual navigation in indoor scenes using deep reinforcement learning},
  author={Yuke Zhu and Roozbeh Mottaghi and Eric Kolve and Joseph J. Lim and Abhinav Gupta and Li Fei-Fei and Ali Farhadi},
  journal={2017 IEEE International Conference on Robotics and Automation (ICRA)},
  year={2016},
  pages={3357-3364}
}
Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new goals, and (2) data inefficiency, i.e., the model requires several (and often costly) episodes of trial and error to converge, which makes it impractical to be applied to real-world scenarios. In this paper, we address these two issues and apply our model to target-driven visual navigation. To address the first issue, we propose an actor-critic model whose policy is a function of the goal… CONTINUE READING

Citations

Publications citing this paper.
SHOWING 1-10 OF 449 CITATIONS

Learning Your Way Without Map or Compass: Panoramic Target Driven Visual Navigation

VIEW 12 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Memory-Based Parameterized Skills Learning for Mapless Visual Navigation

  • Yuyang Liu, Yang Cong, Gan Sun
  • Computer Science
  • 2019 IEEE International Conference on Image Processing (ICIP)
  • 2019
VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

NeoNav: Improving the Generalization of Visual Navigation via Generating Next Expected Observations.

VIEW 14 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Reinforcement Learning based Visual Navigation with Information-Theoretic Regularization

VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Vision-based Navigation Using Deep Reinforcement Learning

VIEW 10 EXCERPTS
CITES METHODS, BACKGROUND & RESULTS
HIGHLY INFLUENCED

Active Object Perceiver: Recognition-Guided Policy Learning for Object Searching on Mobile Robots

VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

GAPLE: Generalizable Approaching Policy LEarning for Robotic Object Searching in Indoor Environment

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2000
2020

CITATION STATISTICS

  • 55 Highly Influenced Citations

  • Averaged 141 Citations per year from 2017 through 2019

  • 24% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 50 REFERENCES

Asynchronous Methods for Deep Reinforcement Learning

VIEW 12 EXCERPTS
HIGHLY INFLUENTIAL

Human-level control through deep reinforcement learning

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Autonomous question answering with mobile robots in human-populated environments

VIEW 1 EXCERPT

Building Machines That Learn and Think Like People

VIEW 1 EXCERPT

Fast, robust, continuous monocular egomotion computation

Made to measure: Bespoke landmarks for 24-hour, all-weather localisation with a camera

Policy Distillation

VIEW 1 EXCERPT