Vehicle Command Voting to Verify Autonomous Control Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle systems lack reliable mechanisms to ensure the integrity of control commands generated by computing devices, particularly in scenarios where memory failures can lead to unsafe driving conditions.
Innovation Solution
Implementing a command controller that uses a voting mechanism among redundant computing devices to verify command reliability, intercepts and tests critical memory areas, and initiates emergency responses when necessary to ensure safe vehicle operation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If memory tests are performed on computing devices to verify command reliability, then the reliability of control commands is improved, but the system complexity and processing time increase
Solution Approach 1:
The patent performs memory tests on computing devices before they generate control commands for autonomous vehicle operation. By conducting the memory test in advance (prior to command generation), the system ensures that only computing devices with functional memory produce control commands, thereby improving command reliability while managing system complexity through proactive verification rather than reactive testing
Solution Approach 2:
The patent introduces a command controller as an intermediary component between the computing device and the vehicle control elements. This command controller receives control commands from the computing device, intercepts them for verification, and determines whether to forward or block them based on memory test results. This intermediary structure separates the verification function from the control execution function, improving overall system reliability while maintaining manageable complexity through modular design
2Reliability
If memory tests are performed on computing devices to ensure command integrity, then the safety of vehicle operation is improved, but the processing time and response speed decrease
Solution Approach 1:
The memory test is performed before the computing device generates control commands, establishing the computational integrity of memory in advance. This preliminary verification ensures that subsequent command generation operates on validated memory, improving command integrity while minimizing time loss during actual control operations since the verification is already complete
Solution Approach 2:
The command controller implements a feedback mechanism where it receives control commands from the computing device, verifies them against memory test results, and determines whether to forward or block them. This feedback loop ensures that only commands from computing devices with passed memory tests are executed, maintaining high command integrity while enabling rapid response by making the verification decision process automated and immediate
3Reliability
If redundant computing devices are used with voting mechanism to verify commands, then the reliability of control commands is improved, but the device complexity and cost increase
Solution Approach 1:
The patent employs redundant computing devices that are essentially copies of the primary computing device, each capable of independently executing the same autonomous driving algorithms and generating control commands. These redundant devices include duplicated processors, memory, and sensors. By having multiple identical systems, the patent enables voting mechanisms where the majority decision determines the final control command, significantly improving control command reliability while managing complexity through standardized replicated components rather than fundamentally different system architectures
Data Source
AI summary
A vehicle having a control element for the speed, acceleration or direction of the vehicle, multiple identical or redundant computing devices (e.g., each implemented as a system on chip (SoC)) to separately generate driving commands in parallel during autonomous driving of the vehicle, and a command controller coupled between the control element and the computing devices. The commands may have one or more matching groups, where commands within each respective group agree with each other and thus vote for a candidate command representing the group. The computing device outputs a candidate command that represents the largest group for execution by the control element.