FutureMapping: The Computational Structure of Spatial AI Systems
read the original abstract
We discuss and predict the evolution of Simultaneous Localisation and Mapping (SLAM) into a general geometric and semantic `Spatial AI' perception capability for intelligent embodied devices. A big gap remains between the visual perception performance that devices such as augmented reality eyewear or comsumer robots will require and what is possible within the constraints imposed by real products. Co-design of algorithms, processors and sensors will be needed. We explore the computational structure of current and future Spatial AI algorithms and consider this within the landscape of ongoing hardware developments.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Training-free Spatially Grounded Geometric Shape Encoding (Technical Report)
XShapeEnc encodes arbitrary 2D spatially grounded shapes into compact invertible representations by decomposing them into unit-disk geometry and harmonic pose fields then applying Zernike bases with frequency propagation.
-
Training-free Spatially Grounded Geometric Shape Encoding (Technical Report)
XShapeEnc decomposes 2D shapes into unit-disk geometry and harmonic pose, encodes both with orthogonal Zernike bases, and applies frequency propagation to produce invertible, adaptive, frequency-rich representations.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.