Context-aware action recognition by dual attention networks

Q Fan, D Gutfreund, X Tete, B Zhou - US Patent 11,195,024, 2021 - Google Patents
Provided are embodiments including a computer-implemented method for performing
recognition. The computer-implemented method includes receiving video data, and …

Top-down scene generation

G Bagschik, AS Crego, G Garimella… - US Patent …, 2023 - Google Patents
Techniques for top-down scene generation are discussed. A generator component may
receive multi-dimensional input data associated with an environment. The generator …

Top-down scene discrimination

G Bagschik, AS Crego, G Garimella… - US Patent …, 2024 - Google Patents
Techniques for top-down scene discrimination are discussed. A system receives scene data
associated with an environment proximate a vehicle. The scene data is input to a …

Method for controlling a robot device and robot device controller

KSA Abdou - US Patent 11,759,947, 2023 - Google Patents
A method for controlling a robot device. The method includes performing an initial training of
an actor neural network by imitation learning of demonstrations, controlling the robot device …

Predictive motion planning system and method

K Rezaee, P Yadmellat - US Patent 11,835,958, 2023 - Google Patents
Methods and systems for training a motion planner for an autonomous vehicle are
described. A trajectory evaluator agent of the motion planner receives state data defining a …