Autonomous Driving Model Updates with Reduced Sensor Suites
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current self-driving vehicles require a substantial amount of hardware and sensors to function effectively, leading to increased costs and slower adoption due to the complexity and expense of these systems.
Innovation Solution
The implementation of a vehicle computing environment with a reduced sensor suite, primarily using optical sensors, and a cloud-based computing system to process data for autonomous driving, allowing for lower-cost and more efficient autonomous operations by leveraging cloud resources for processing and model updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a full sensor suite is used for autonomous driving, then safety and reliability are improved, but device complexity and cost increase
Solution Approach 1:
The patent segments the autonomous driving system into two parts: a simplified on-vehicle sensor suite for basic data collection, and a cloud-based processing system for complex analysis. This divides the computational burden away from the vehicle, allowing reduced hardware complexity while maintaining reliability through cloud-based safety checks and model validation.
Solution Approach 2:
The patent introduces cloud-based processing as an intermediary between the simplified vehicle sensors and the autonomous driving decisions. The cloud system acts as a mediator that enhances the capabilities of the reduced sensor suite through remote computing power, maintaining reliability without requiring complex on-vehicle hardware.
2Measurement precision
If a full sensor suite is used for autonomous driving, then navigation accuracy is improved, but cost increases
Solution Approach 1:
The patent uses cloud-based digital models and simulations to replicate the functionality of expensive physical sensors. By creating virtual representations of the environment and running simulations in the cloud, the system achieves high measurement precision without requiring costly duplicate hardware on each vehicle.
Solution Approach 2:
The cloud-based processing system serves multiple functions: it processes data from reduced sensors, runs safety validations, performs model training, and provides updates to multiple vehicles. This multi-functional approach allows a single cloud infrastructure to replace what would otherwise require expensive dedicated hardware on each vehicle.
3Device complexity
If cloud-based processing is used, then device complexity is reduced, but loss of time in data processing may increase
Solution Approach 1:
The patent implements preliminary processing of sensor data on the vehicle before transmission to the cloud. By performing initial filtering, validation, and preprocessing locally, the system reduces the amount of data that needs to be transmitted and processed remotely, minimizing latency while maintaining reduced on-vehicle complexity.
Solution Approach 2:
The system maintains continuous autonomous driving operations on the vehicle while cloud processing occurs in parallel. The vehicle continues its useful action of navigation and control without interruption, while cloud-based validations and model updates proceed concurrently, ensuring no significant time loss in the overall system.
Data Source
AI summary
Systems and methods for implementing one or more autonomous features for autonomous and semi-autonomous control of one or more vehicles are provided. More specifically, image data may be obtained from an image acquisition device and processed utilizing one or more machine learning models to identify, track, and extract one or more features of the image utilized in decision making processes for providing steering angle and/or acceleration/deceleration input to one or more vehicle controllers. In some instances, techniques may be employed such that the autonomous and semi-autonomous control of a vehicle may change between vehicle follow and lane follow modes. In some instances, at least a portion of the machine learning model may be updated based on one or more conditions.