Sensor Synchronization Unit for LiDAR and Camera Time Alignment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in motion planning and control due to the lack of efficient sensor processing units that can synchronize and process different types of sensors, such as LiDAR and cameras, leading to inaccuracies like 'ghost objects' from unsynchronized data.

Innovation Solution

A sensor unit is introduced that connects to a computer, expanding I/O capabilities, enabling synchronization and sensor fusion by using pulse per second (PPS) and GPRMC signals from GNSS receivers, and communicates through a PCI Express interface, allowing for timestamp generation and data processing to synchronize sensor operations.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If multiple sensors (LiDAR, cameras) are connected to a centralized computing chassis, then the vehicle can collect data from various sensors, but the sensors cannot be synchronized leading to ghost objects and location inaccuracies

Engineering Contradiction:
Improvesensor integration capabilityVSAvoidobject location accuracy
Core Design Contradiction:
Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

A dedicated sensor integration unit is introduced as an intermediary component between the sensors and the centralized computing chassis. This unit specifically handles synchronization of multiple sensors (LiDAR, cameras) using PPS signals from GNSS receivers, ensuring that data from different sensors are temporally aligned. The intermediary unit processes sensor data and manages timing coordination, preventing ghost objects and location inaccuracies while maintaining the versatility of multiple sensor connections.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Device complexity

If the maximum number of sensors is predetermined by the number of I/O ports, then the system structure is simple, but the sensor processing capability is limited and inefficient

Engineering Contradiction:
Improvesystem structureVSAvoidsensor processing efficiency
Core Design Contradiction:
Device complexityVSProductivity

Solution Approach 1:

The system is segmented into distinct functional units: a sensor integration unit dedicated to handling sensor connections and synchronization, and a centralized computing chassis for higher-level processing. The sensor integration unit contains multiple I/O ports specifically for sensor connections, separating the sensor interface functionality from the main computing system. This segmentation allows the system to support more sensors without increasing the overall system complexity, as the sensor integration unit encapsulates the complexity of sensor management.

Inventive Principle:
Principle #1Segmentation

3Ease of operation

If sensors are connected without synchronization, then the hardware resources are limited and easy to manage, but ghost objects appear and data accuracy deteriorates

Engineering Contradiction:
Improvehardware managementVSAvoidsensor data accuracy
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The sensor integration unit implements self-service synchronization by automatically generating timestamps and aligning sensor data using PPS (pulse per second) signals from GNSS receivers. The unit autonomously manages the synchronization process without requiring manual intervention or complex external coordination. Each sensor data packet is automatically time-stamped and correlated with other sensors based on the synchronized timing, ensuring data accuracy while maintaining ease of operation through automated processes.

Inventive Principle:
Principle #25Self-service

Data Source

PatentUS11029165B2Sensor integration and synchronization unit for an autonomous driving vehicle
Publication Date: 2021.06.08 BAIDU USA LLC
  • US11029165B2 patent drawing
  • US11029165B2 patent drawing
  • US11029165B2 patent drawing

AI summary

A sensor unit includes a sensor interface and a host interface. The sensor interface can be coupled to a number of sensors mounted on various locations of the ADV. The host interface can be coupled to a host system that is configured to perceive a driving environment surrounding the ADV based on sensor data obtained from the sensors and to plan a path to autonomously drive the ADV. The sensor unit further includes a sensor processing module and a sensor control module coupled to the sensor interface, and a time module coupled to the sensor processing module and the sensor control module. The sensor processing module is configured to process sensor data received from the sensors via the sensor interface. The sensor control module is configured to control operations of the sensors. The time module is configured to generate time to synchronize timing of the operations of the sensors.