Autonomous Vehicle Fallback Trajectories for Highway System Failures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in safely controlling themselves during system failures, particularly on highways and in heavy traffic situations, where immediate braking may not be the best response and requires fallback systems that can adapt to available sensor functionality and road types.
Innovation Solution
A system with multiple computing systems, where a third computing system with reduced capabilities takes over to generate trajectories based on the vehicle's location and available sensors, allowing for different fallback behaviors to minimize the risk of stopping in the lane, by determining the type of road and assessing sensor functionality to adjust maneuvers accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a fallback system applies brakes as hard and as quickly as possible in an emergency, then the vehicle can stop safely in most situations, but this approach may cause accidents on highways and in heavy traffic where immediate braking is not the best response
Solution Approach 1:
The fallback system dynamically adapts its behavior based on the current driving context. The third computing system generates different fallback trajectories depending on whether the vehicle is on a highway or surface street, and adjusts the list of possible maneuvers based on sensor functionality and road type, making the safety response flexible rather than fixed
Solution Approach 2:
The system changes operational parameters of the fallback behavior based on detected conditions. When on a highway, the system modifies the fallback trajectory to avoid immediate braking and instead plan for controlled exits. The list of possible maneuvers is adjusted as a parameter based on sensor availability and road type
2Adaptability or versatility
If a full-featured computing system generates trajectories, then the vehicle can optimize for all possible maneuvers and situations, but this increases system complexity and computational requirements
Solution Approach 1:
The third computing system performs a subset of the functions of the first computing system. Instead of generating all possible optimized trajectories, it generates a reduced set of fallback trajectories based on the current situation and available sensors, performing only the necessary safety-critical planning
Solution Approach 2:
The trajectory generation function is segmented between multiple computing systems. The first computing system handles normal operation with full capabilities, while the third computing system handles fallback scenarios with reduced capabilities, dividing the overall functionality into specialized segments
Data Source
AI summary
Aspects of the disclosure relate to controlling a vehicle in an autonomous driving mode. The system includes a plurality of sensors configured to generate sensor data. The system also includes a first computing system configured to generate trajectories using the sensor data and send the generated trajectories to a second computing system. The second computing system is configured to cause the vehicle to follow a receive trajectory. The system also includes a third computing system configured to, when there is a failure of the first computer system, generate and send trajectories to the second computing system based on whether a vehicle is located on a highway or a surface street.