Mitsubishi Electric Research Laboratories, Inc.

Hughes Network Systems, LLC

Jun Wang

Channasandra S Ravishankar

James Jehong Jong

Alan Sullivan

Siheng Chen

Harish Ramchandran

Xiaolong Li

The present disclosure provides a system and a method for motion prediction for autonomous driving. The system disclosed herein provides an efficient deep-neural-network-based system to jointly perform perception and motion prediction from 3D point clouds. This system is able to take a pair of LiDAR sweeps as input and outputs for each point in the second sweep, both a classification of the point into one of a set of semantic classes, and a motion vector indicating the motion of the point within the world coordinate system. The system includes a spatiotemporal pyramid network, which extracts deep spatial and temporal features in a hierarchical fashion. The training of this system is regularized with spatial and temporal consistency losses. Thus providing an improved motion planner for autonomous driving applications.

System and method for motion prediction in autonomous driving

An approach is provided for high penetration alerting in a mobile satellite system. A message is generated for transmission to a wireless terminal. The message is partitioned into a number of symbols, each symbol composed of a portion of the message. The symbols are encoded via FEC coding to generate outer coded symbols, and each outer coded symbol is encoded based on a corresponding binary orthogonal sequence. The inner coded symbols are modulated based on a binary modulation scheme, and pulse shaped to generate message bursts for transmission to the wireless terminal. Each message burst reflects a group of the inner coded symbols, wherein the grouping of the inner coded symbols facilitates joint sequence detection by the wireless terminal, and each message burst exhibits relatively low peak-to-average power ratio.

System and method for improved waveform and enhanced receiver algorithm for high penetration alerting in a mobile satellite communications system

Growing community of inventors

Greenbelt, MD, United States of America

Jun Wang