Perceptive Automata Inc.

Till S Hartmann

Samuel English Anthony

Jeffrey D Zaremba

Jacob Reinier Maat

Kevin W Sylvestre

Dylan James Rose

A system uses a machine learning based model to determine attributes describing states of mind and behavior of traffic entities in video frames captured by an autonomous vehicle. The system classifies video frames according to traffic scenarios depicted, where each scenario is associated with a filter based on vehicle attributes, traffic attributes, and road attributes. The system identifies a set of video frames associated with ground truth scenarios for validating the accuracy of the machine learning based model and predicts attributes of traffic entities in the video frames. The system analyzes video frames captured after the set of video frames to determine actual attributes of the traffic entities. Based on a comparison of the predicted attributes and actual attributes, the system determines a likelihood of the machine learning based model making accurate predictions and uses the likelihood to generate a navigation action table for controlling the autonomous vehicle.

Scenario identification for validation and training of machine learning based models for autonomous vehicles

Ground truth based metrics for evaluation of machine learning based models for predicting attributes of traffic entities for navigating autonomous vehicles

An autonomous vehicle collects sensor data of an environment surrounding the autonomous vehicle including traffic entities such as pedestrians, bicyclists, or other vehicles. The sensor data is provided to a machine learning based model along with an expected turn direction of the autonomous vehicle to determine a hidden context attribute of a traffic entity given the expected turn direction of the autonomous vehicle. The hidden context attribute of the traffic entity represents factors that affect the behavior of the traffic entity, and the hidden context attribute is used to predict future behavior of the traffic entity. Instructions to control the autonomous vehicle are generated based on the hidden context attribute.

Navigation of autonomous vehicles using turn aware machine learning based models for prediction of behavior of a traffic entity

Growing community of inventors

Boston, MA, United States of America

Till S Hartmann