Corpus ID: 211532491

Technical Report: Reactive Semantic Planning in Unexplored Semantic Environments Using Deep Perceptual Feedback

@article{Vasilopoulos2020TechnicalRR,
  title={Technical Report: Reactive Semantic Planning in Unexplored Semantic Environments Using Deep Perceptual Feedback},
  author={Vasileios Vasilopoulos and Georgios Pavlakos and Sean L. Bowman and J. Diego Caporale and Kostas Daniilidis and George J. Pappas and Daniel E. Koditschek},
  journal={ArXiv},
  year={2020},
  volume={abs/2002.12349}
}
  • Vasileios Vasilopoulos, Georgios Pavlakos, +4 authors Daniel E. Koditschek
  • Published in ArXiv 2020
  • Engineering, Computer Science
  • This paper presents a reactive planning system that enriches the topological representation of an environment with a tightly integrated semantic representation, achieved by incorporating and exploiting advances in deep perceptual learning and probabilistic semantic reasoning. Our architecture combines object detection with semantic SLAM, affording robust, reactive logical as well as geometric planning in unexplored environments. Moreover, by incorporating a human mesh estimation algorithm, our… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 35 REFERENCES

    Sensor-based reactive navigation in unknown convex sphere worlds

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Probabilistic data association for semantic SLAM

    VIEW 5 EXCERPTS

    RRTX: Asymptotically optimal single-query sampling-based motion planning with quick replanning

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Ghost Robotics Spirit 40

    • Ghost Robotics
    • 2020. [Online]. Available: http://www.ghostrobotics.io
    • 2020
    VIEW 3 EXCERPTS
    HIGHLY INFLUENTIAL

    6-DoF object pose from semantic keypoints

    VIEW 5 EXCERPTS

    Cognitive Mapping and Planning for Visual Navigation

    VIEW 1 EXCERPT

    Learning to Reconstruct 3D Human Pose and Shape via Model-Fitting in the Loop

    VIEW 3 EXCERPTS