Corpus ID: 210064528

Learning to Move with Affordance Maps

@article{Qi2020LearningTM,
  title={Learning to Move with Affordance Maps},
  author={William Qi and R. T. Mullapudi and Saurabh Gupta and D. Ramanan},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.02364}
}
The ability to autonomously explore and navigate a physical space is a fundamental requirement for virtually any mobile autonomous agent, from household robotic vacuums to autonomous vehicles. Traditional SLAM-based approaches for exploration and navigation largely focus on leveraging scene geometry, but fail to model dynamic objects (such as other agents) or semantic constraints (such as wet floors or doorways). Learning-based RL agents are an attractive alternative because they can… Expand
5 Citations
Learning Affordance Landscapes forInteraction Exploration in 3D Environments
  • 4
  • PDF
Spatial Action Maps for Mobile Manipulation
  • 10
  • PDF
Embodied Visual Active Learning for Semantic Segmentation
  • PDF

References

SHOWING 1-10 OF 44 REFERENCES
Cognitive Mapping and Planning for Visual Navigation
  • 368
  • Highly Influential
Playing Doom with SLAM-Augmented Deep Reinforcement Learning
  • 54
  • PDF
Learned Map Prediction for Enhanced Mobile Robot Exploration
  • 22
  • PDF
Target-driven visual navigation in indoor scenes using deep reinforcement learning
  • 767
  • PDF
Building Generalizable Agents with a Realistic and Rich 3D Environment
  • 192
  • PDF
Learning to Navigate in Complex Environments
  • 524
  • PDF
Approximate Bayesian inference in spatial environments
  • 13
  • PDF
A robot exploration and mapping strategy based on a semantic hierarchy of spatial representations
  • 1,013
  • Highly Influential
  • PDF
Gibson Env: Real-World Perception for Embodied Agents
  • 223
  • PDF
...
1
2
3
4
5
...