Grounding Language Attributes to Objects using Bayesian Eigenobjects

@article{Cohen2019GroundingLA,
  title={Grounding Language Attributes to Objects using Bayesian Eigenobjects},
  author={Vanya Cohen and Benjamin Burchfiel and Thao Nguyen and Nakul Gopalan and Stefanie Tellex and George Konidaris},
  journal={2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)},
  year={2019},
  pages={1187-1194}
}
We develop a system to disambiguate object instances within the same class based on simple physical descriptions. The system takes as input a natural language phrase and a depth image containing a segmented object and predicts how similar the observed object is to the object described by the phrase. Our system is designed to learn from only a small amount of human-labeled language data and generalize to viewpoints not represented in the language-annotated depth image training set. By decoupling… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 27 REFERENCES

Hybrid Bayesian Eigenobjects: Combining Linear Subspace and Deep Network Methods for 3D Robot Vision

VIEW 5 EXCERPTS

Variational principal components

VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL

Interactive Visual Grounding of Referring Expressions for Human-Robot Interaction

VIEW 3 EXCERPTS

Interactively Picking Real-World Objects with Unconstrained Spoken Language Instructions

VIEW 1 EXCERPT

Natural language object retrieval Burchfiel and G . Konidaris , “ Bayesian eigenobjects : A unified framework for 3 D robot perception , ” in

  • J. Feng, K. Saenko
  • Proceedings of Robotics : Science and Systems
  • 2017

Reducing errors in object-fetching interactions through social feedback

VIEW 2 EXCERPTS