Autonomous Driving Override Control for Obstacle Proximity Buffers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle navigation systems face challenges in ensuring safety and scalability, as they need to process various data sources, navigate through complex environments, and adhere to liability constraints, while existing solutions are not scalable for widespread adoption.
Innovation Solution
A machine-readable storage medium and computing device system that uses cameras to analyze images, combined with GPS and sensor data, to determine navigational actions, including braking and acceleration capabilities, and implement responses based on driving policies to ensure safe navigation and liability adherence.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicle navigation systems process multiple data sources and adhere to liability constraints, then safety assurance is improved, but device complexity increases
Solution Approach 1:
The navigation system is divided into separate functional modules: data acquisition module (cameras, GPS, sensors), data processing module, decision-making module (with driving policy engine), and execution module. Each module handles specific tasks independently, improving safety through specialized processing while managing complexity through modular architecture.
Solution Approach 2:
A driving policy engine acts as an intermediary between raw sensor data and navigation decisions. This intermediary layer processes multiple data sources (camera images, GPS coordinates, sensor readings) and applies liability constraints to generate safe navigational actions, thereby improving safety assurance while encapsulating complexity within a dedicated component.
2Reliability
If engineering solutions are designed to ensure safety for every self-driving car, then safety assurance is improved, but scalability deteriorates due to increased costs
Solution Approach 1:
The navigation system employs universal components and standardized processing algorithms that can be deployed across different vehicle models and manufacturers. The driving policy engine uses generalizable liability constraints and decision-making frameworks that apply to all autonomous vehicles, enabling safety assurance to scale without proportionally increasing costs.
Solution Approach 2:
The system adjusts operational parameters (such as safety margins, braking distances, and speed limits) based on environmental conditions and vehicle characteristics rather than requiring completely different safety systems for each scenario. This parameter-based approach allows safety assurance to be adapted across diverse operating conditions while maintaining scalability.
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
An autonomous system may selectively displace human driver control of a host vehicle. The system may receive an image representative of an environment of the host vehicle and detect an obstacle in the environment of the host vehicle based on analysis of the image. The system may monitor a driver input to a throttle, brake, and/or steering control associated with the host vehicle. The system may determine whether the driver input would result in the host vehicle navigating within a proximity buffer relative to the obstacle. If the driver input would not result in the host vehicle navigating within the proximity buffer, the system may allow the driver input to cause a corresponding change in one or more host vehicle motion control systems. If the driver input would result in the host vehicle navigating within the proximity buffer, the system may prevent the driver input from causing the corresponding change.