Hybrid Machine-Cloud Computing for Autonomous Vehicle Diagnostics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional autonomous driving systems face performance and latency issues due to limited in-vehicle power and require expert technicians to decode error codes, limiting efficient error fixing and route optimization.
Innovation Solution
Combining in-vehicle engines with cloud-based systems for faster computations, automatic error decoding, and dynamic route optimization based on vehicle component status using hybrid machine-cloud computing and CNN-based diagnostics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If all computations are performed in-vehicle using conventional autonomous driving systems, then system independence is maintained, but power consumption increases and computation speed decreases
Solution Approach 1:
The patent segments computational tasks between in-vehicle processors and cloud-based systems. Complex computations are divided into local processing (for time-critical functions) and cloud processing (for power-intensive tasks), allowing the system to maintain independence while reducing power consumption and improving computation speed for specific tasks.
Solution Approach 2:
The patent introduces communication interfaces and protocols as intermediaries between in-vehicle systems and cloud-based systems. These intermediaries enable efficient data exchange and task coordination, allowing the distributed system to function as a unified computing platform while managing power consumption and computation speed optimally.
2Productivity
If conventional error decoding techniques are used requiring expert technicians, then system complexity is reduced, but error fixing efficiency decreases
Solution Approach 1:
The patent implements self-service error decoding capabilities within the autonomous vehicle system. Error codes are automatically decoded and diagnosed using onboard processors and cloud-based databases, eliminating the need for expert technicians to manually interpret codes. The system performs self-diagnosis and generates repair recommendations automatically.
Solution Approach 2:
The patent pre-loads error code databases and diagnostic algorithms into the vehicle's computing systems before deployment. This preliminary action enables rapid error code lookup and interpretation without requiring external expert intervention, significantly improving error fixing efficiency while managing system complexity through pre-configured solutions.
3Adaptability or versatility
If conventional route guidance is used without dynamic optimization, then system simplicity is maintained, but route optimization based on vehicle component status is insufficient
Solution Approach 1:
The patent implements dynamic route optimization that adapts to real-time vehicle component status. The system continuously monitors battery levels, motor conditions, and other component states, then dynamically adjusts routing decisions to optimize performance and energy consumption. This dynamic adaptation enhances versatility while managing complexity through event-driven architecture.
Solution Approach 2:
The patent incorporates feedback loops where route guidance decisions are continuously refined based on actual vehicle performance data and component status. The system uses feedback from sensor readings and diagnostic systems to adjust routing recommendations, improving adaptability while controlling complexity through iterative optimization algorithms.
Data Source
AI summary
A mechanism is described for facilitating smart collection of data and smart management of autonomous machines. A method of embodiments, as described herein, includes detecting one or more sets of data from one or more sources over one or more networks, and combining a first computation directed to be performed locally at a local computing device with a second computation directed to be performed remotely at a remote computing device in communication with the local computing device over the one or more networks, where the first computation consumes low power, wherein the second computation consumes high power.