Visual Semantic Planning Using Deep Successor Representations

@article{Zhu2017VisualSP,
  title={Visual Semantic Planning Using Deep Successor Representations},
  author={Yuke Zhu and Daniel Gordon and Eric Kolve and Dieter Fox and Li Fei-Fei and Abhinav Gupta and Roozbeh Mottaghi and Ali Farhadi},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={483-492}
}
A crucial capability of real-world intelligent agents is their ability to plan a sequence of actions to achieve their goals in the visual world. In this work, we address the problem of visual semantic planning: the task of predicting a sequence of actions from visual observations that transform a dynamic environment from an initial state to a goal state. Doing so entails knowledge about objects and their affordances, as well as actions and their preconditions and effects. We propose learning… CONTINUE READING

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 55 CITATIONS, ESTIMATED 96% COVERAGE

Vision Memory for Target Object Navigation Using Deep Reinforcement Learning: An Empirical Study

VIEW 12 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Explore, Approach, and Terminate: Evaluating Subtasks in Active Visual Object Search Based on Deep Reinforcement Learning

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Hierarchical Task Planning from Object Goal State for Human-Assist Robot

VIEW 4 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Embodied Question Answering

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Embodied Question Answering

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

Model primitives for hierarchical lifelong reinforcement learning

VIEW 1 EXCERPT
CITES BACKGROUND

ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks

VIEW 2 EXCERPTS
CITES BACKGROUND & METHODS

Audio-Visual Embodied Navigation

VIEW 2 EXCERPTS
CITES BACKGROUND

FILTER CITATIONS BY YEAR

2017
2020

CITATION STATISTICS

  • 5 Highly Influenced Citations

  • Averaged 18 Citations per year from 2017 through 2019

  • 47% Increase in citations per year in 2019 over 2018

References

Publications referenced by this paper.
SHOWING 1-10 OF 40 REFERENCES

Actions ̃ transformations

  • C. Dimitrakakis, A. Sumner, E. Espié, C. Guionneau
  • Torcs : The open racing car simulator .
  • 2016

Deep reinforcement learning for robotic manipulation with asynchronous off-policy updates

End - to - end training of deep visuomotor policies

  • C. Finn S. Levine, T. Darrell, P. Abbeel
  • JMLR
  • 2016