Autonomous Vehicle Control Model Switching Under Sensor Failure
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional self-driving systems face frequent failures in deriving control commands due to environmental factors like camera dirt or darkness, and position information unavailability, leading to increased manual operation frequency across various mobile bodies.
Innovation Solution
A control device with a first and second control model, where the second model can derive control commands from different types or input data, enabling automatic control in scenarios where the first model fails, thereby reducing manual operation frequency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single control model is used for autonomous vehicle control, then the system structure remains simple, but the reliability decreases due to frequent failures in deriving control commands under abnormal conditions
Solution Approach 1:
The control system is segmented into multiple control models (first control model and second control model) that operate independently but complement each other. Each model handles specific scenarios, with the first model handling normal conditions and the second model handling abnormal conditions, thereby improving overall reliability without creating a monolithic complex system.
Solution Approach 2:
The control device achieves multi-functionality by integrating multiple control models that can handle diverse operating conditions. The system universally addresses both normal and abnormal scenarios through different models, allowing a single control device to perform multiple control functions across various situations.
2Reliability
If multiple control models are deployed to handle abnormal scenarios, then the reliability improves, but the device complexity increases
Solution Approach 1:
The control system dynamically switches between different control models based on the operational context. The controller determines whether to use the first or second control model based on real-time conditions, creating a dynamic adaptation mechanism that maintains reliability while managing complexity through flexible model selection rather than static deployment.
Solution Approach 2:
The system changes operational parameters by switching between different control models with different input data types and processing characteristics. This parameter change approach allows the system to adapt to varying conditions without permanently increasing structural complexity, as the complexity management is achieved through parameter switching rather than permanent architectural expansion.
3Ease of operation
If the first control model is used exclusively, then the device complexity remains low, but the frequency of manual operation increases due to derivation failures
Solution Approach 1:
The system performs preliminary action by pre-configuring multiple control models with different capabilities before operation. The second control model is prepared in advance to handle specific abnormal scenarios, so when such scenarios occur, the system can immediately switch without requiring manual intervention, thereby reducing manual operation frequency through advance preparation.
Solution Approach 2:
The controller acts as an intermediary that manages the interaction between multiple control models and the vehicle control system. This intermediary component coordinates model selection and switching, simplifying the overall architecture by providing a unified interface that hides the complexity of multiple models from the rest of the system.
Data Source
AI summary
A control device tries derivation of a first control command using a first control model, and controls, if the derivation of the first control command by the first control model is normal, a mobile body according to the derived first control command. If an abnormality occurs in the derivation of the first control command by the first control model, the control device controls the mobile body according to a second control command derived from a second control model or a third control command originating from a manual operation by a user. The second control model is configured to be capable of normally deriving the control command in at least a part of scenes of an abnormality occurring in derivation of the control command by the first control model.