The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.
The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.
Patent No.:
Date of Patent:
Jan. 13, 2026
Filed:
Oct. 10, 2023
Toyota Research Institute, Inc., Los Altos, CA (US);
Carnegie Mellon University, Pittsburgh, PA (US);
The Regents of the University of California, Oakland, CA (US);
Junyu Nan, Pittsburgh, PA (US);
Xinshuo Weng, Toronto, CA;
Jean Mercat, Mountain View, CA (US);
Blake Warren Wulfe, San Francisco, CA (US);
Rowan Thomas Mcallister, San Jose, CA (US);
Adrien David Gaidon, Mountain View, CA (US);
Nicholas Andrew Rhinehart, Berkeley, CA (US);
Kris Makoto Kitani, Pittsburgh, PA (US);
TOYOTA RESEARCH INSTITUTE, INC., Los Altos, CA (US);
TOYOTA JIDOSHA KABUSHIKI KAISHA, Aichi-Ken, JP;
CARNEGIE MELLON UNIVERSITY, Pittsburgh, PA (US);
THE REGENTS OF THE UNIVERSITY OF CALIFORNIA, Oakland, CA (US);
Abstract
A method for sequential point cloud forecasting is described. The method includes training a vector-quantized conditional variational autoencoder (VQ-CVAE) framework to map an output to a closest vector in a discrete latent space to obtain a future latent space. The method also includes outputting, by a trained VQ-CVAE, a categorical distribution of a probability of V vectors in a discrete latent space in response to an input previously sampled latent space and past point cloud sequences. The method further includes sampling an inferred future latent space from the categorical distribution of the probability of the V vectors in the discrete latent space. The method also includes predicting a future point cloud sequence according to the inferred future latent space and the past point cloud sequences. The method further includes denoising, by a denoising diffusion probabilistic model (DDPM), the predicted future point cloud sequences according to an added noise.