Network for multisweep 3D detection

US12354342B2 · kind B2 · utility

Assignees

• TOYOTA RESEARCH INSTITUTE, INC. · US
• TOYOTA JIDOSHA KABUSHIKI KAISHA · JP

Inventors

• Kuan-Hui Lee · San Jose, US
• Charles Christopher Ochoa · San Francisco, US
• Arjun Bhargava · San Francisco, US
• Chao Fang · Sunnyvale, US
• Kun-Hsin Chen · San Francisco, US

Key dates

• Filing date: Apr 29, 2022
• Grant date: Jul 8, 2025
• Expiry date: Jan 12, 2044

Classification

• Technology area (CPC G): Physics
• CPC primary: G01S13/867
• WIPO field: Measurement
• WIPO sector: Instruments

Abstract

Systems, methods, and other embodiments described herein relate to a multi-task model that integrates recurrent models to improve handling of multi-sweep inputs. In one embodiment, a method includes acquiring sensor data from multiple modalities. The method includes separately encoding respective segments of the sensor data according to an associated one of the different modalities to form encoded features using separate encoders of a network. The method includes accumulating, in a detector, sparse features associated with sparse sensor inputs of the multiple modalities to densify the sparse features into dense features. The method includes providing observations according to the encoded features and the sparse features using the network.