Invention Grant
- Patent Title: Generative adversarial inverse trajectory optimization for probabilistic vehicle forecasting
-
Application No.: US16145649Application Date: 2018-09-28
-
Publication No.: US10705531B2Publication Date: 2020-07-07
- Inventor: Paul Vernaza , Wongun Choi , Nicholas Rhinehart
- Applicant: NEC Laboratories America, Inc.
- Applicant Address: JP Tokyo
- Assignee: NEC Corporation
- Current Assignee: NEC Corporation
- Current Assignee Address: JP Tokyo
- Agent Joseph Kolodka
- Main IPC: G06K9/00
- IPC: G06K9/00 ; G05D1/02 ; H04N7/18 ; G05D1/00 ; G08G1/00 ; G06K9/62 ; G01C21/00 ; B60Q9/00 ; G06K9/72 ; G06N3/04 ; G06N3/08

Abstract:
Systems and methods for predicting vehicle behavior includes capturing images of a vehicle in traffic using an imaging device. Future behavior of the vehicle is stochastically modeled using a processing device including an energy-based model stored in a memory of the processing device. The energy-based model includes generating a distribution of possible future trajectories of the vehicle using a generator, sampling the distribution of possible future trajectories according to an energy value of each trajectory in the distribution of possible future trajectories an energy model to determine probable future trajectories, and optimizing parameters of each of the generator and the energy model using an optimizer. A user is audibly alerted with a speaker upon an alert system recognizing hazardous trajectories of the probable future trajectories.
Public/Granted literature
- US20190094867A1 GENERATIVE ADVERSARIAL INVERSE TRAJECTORY OPTIMIZATION FOR PROBABILISTIC VEHICLE FORECASTING Public/Granted day:2019-03-28
Information query