Trajectory Data Compression for CAN Bus Communication in Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current communication protocols, such as the CAN bus, are inadequate for conveying large amounts of data in autonomous driving vehicles due to bandwidth limitations, which hinders efficient motion planning and control.
Innovation Solution
A computer-implemented method that perceives the driving environment using sensor data, plans a trajectory, and transmits trajectory data as a stream of CAN messages to an electronic control unit (ECU) for control commands, employing data compression techniques to reduce message size and improve data transmission efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If CAN bus is used for communication between planning and control, then reliability is improved, but data transmission capacity deteriorates due to 64-bit size limitation per message
Solution Approach 1:
The patent segments large trajectory data into multiple smaller CAN messages for transmission. Each message contains a portion of the trajectory data rather than the complete dataset, allowing the system to overcome the 64-bit size limitation while maintaining reliable communication through the CAN bus protocol.
2Loss of information
If trajectory data is transmitted as complete messages, then data integrity is improved, but transmission time increases due to large message size
Solution Approach 1:
The patent divides complete trajectory data into segmented messages that are transmitted sequentially. This segmentation reduces the transmission time of individual messages while maintaining data integrity through proper sequencing and reassembly at the receiving end.
Solution Approach 2:
The system transmits trajectory data in periodic segments rather than as a single large message. This periodic transmission approach reduces the time any single message occupies the bus while ensuring complete data delivery through structured segmentation.
Data Source
AI summary
Based on sensor data obtained from a variety of sensors, a driving environment surrounding an autonomous driving vehicle (ADV) is perceived, including perceiving and identifying one or more obstacles. A trajectory is planned based on the perception data according to a set of rules to drive the ADV navigating through the driving environment. Trajectory data representing the trajectory is generated, where the trajectory data includes information indicating target or expected vehicle states at different points in time along the trajectory. The trajectory data is then transmitted in a sequence or a stream of one or more controller area network (CAN) messages to an electronic control unit (ECU) of the ADV over a CAN bus. The ECU is configured to generate and issue one or more control commands (e.g., throttle, brake, steering commands) based on the trajectory data to drive the ADV according to the trajectory.