Vehicle Sensor Fusion for Low-Bandwidth Autonomous Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle sensor systems face challenges in efficiently processing large quantities of high-resolution imagery and range data for autonomous, semi-autonomous, and remote vehicle operations, particularly in terms of network bandwidth and processing resource limitations.
Innovation Solution
The system integrates an imaging subsystem with multiple cameras and a rangefinding subsystem, along with an onboard computing subsystem, to perform sensor fusion and data processing at the vehicle, enabling efficient data collection and processing of image and range data, and leveraging computational models for vehicle control inputs based on confidence metrics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high-resolution imagery and range data are collected from multiple sensors, then measurement precision and reliability are improved, but network bandwidth and processing resources are overwhelmed
Solution Approach 1:
The patent extracts and transmits only the essential confidence metric from the sensor system, separating this critical information from the full high-resolution sensor data. This allows the vehicle to receive sufficient operational information without being overwhelmed by the complete data set, resolving the contradiction between measurement precision and data volume.
Solution Approach 2:
The confidence metric serves as an intermediary that bridges the gap between the detailed sensor data and the vehicle control system. Instead of transmitting all sensor data, the confidence metric provides a condensed representation that enables informed decision-making while minimizing network bandwidth requirements.
2Reliability
If all sensor data is transmitted to remote servers for processing, then processing reliability is improved, but network bandwidth requirements increase and latency increases
Solution Approach 1:
The confidence metric is calculated and prepared in advance at the sensor system level, before transmission to the vehicle. This preliminary processing ensures that the most critical information is ready for immediate use, reducing latency while maintaining processing reliability.
Solution Approach 2:
The essential confidence metric is extracted from the complete sensor data set and transmitted separately. This allows the vehicle to receive and act on critical processing results without waiting for transmission of the entire data set, significantly reducing latency while maintaining reliability through selective data transmission.
3Measurement precision
If high-resolution sensor data is continuously transmitted, then data quality is improved, but network bandwidth consumption increases
Solution Approach 1:
The patent extracts only the essential confidence metric from the high-resolution sensor data for transmission. This selective extraction maintains the quality of operational decision-making by transmitting the most critical information while dramatically reducing network bandwidth consumption compared to transmitting complete sensor data sets.
Solution Approach 2:
Instead of transmitting the original high-resolution sensor data, the system creates and transmits a condensed representation (the confidence metric) that captures the essential information needed for vehicle operation. This copying approach preserves data quality for decision-making while minimizing energy consumption.
Data Source
AI summary
A system and method for collecting and processing sensor data for facilitating and/or enabling autonomous, semi-autonomous, and remote operation of a vehicle, including: collecting surroundings at one or more sensors, and determining properties of the surroundings of the vehicle and/or the behavior of the vehicle based on the surroundings data at a computing system.