Autonomous Vehicle Speed Planning for Tailgating Discomfort
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in determining optimal speed profiles that consider the discomfort of both their occupants and other road users, particularly when interacting with tailgating vehicles, as existing systems often ignore constraints related to objects behind them, leading to potential safety issues.
Innovation Solution
The method involves identifying tailgating vehicles and adjusting discomfort values to determine a speed profile that meets specific factors such as maximum allowed deceleration and reaction time, ensuring the vehicle's trajectory minimizes discomfort for all involved, including occupants of the autonomous vehicle and other road users, by iteratively adjusting these values until a feasible speed profile is found.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the autonomous vehicle maintains a strict speed profile to ensure occupant comfort, then occupant discomfort is minimized, but safety interactions with tailgating vehicles are compromised
Solution Approach 1:
The system dynamically adjusts the discomfort threshold based on the presence and behavior of tailgating vehicles. When a tailgating vehicle is detected, the system modifies the speed profile parameters in real-time, allowing for adjusted deceleration rates and stopping distances that prioritize safety over strict comfort constraints.
Solution Approach 2:
The system changes key parameters including the discomfort threshold, maximum deceleration rate, and stopping distance based on the detected tailgating situation. These parameter adjustments enable the vehicle to transition from a comfort-optimized profile to a safety-optimized profile when needed.
2Reliability
If the autonomous vehicle adjusts speed profile to account for tailgating vehicle discomfort, then safety is improved, but system complexity increases
Solution Approach 1:
The system pre-establishes a set of discrete discomfort threshold levels and corresponding speed profile parameters. When a tailgating vehicle is detected, the system selects from these pre-defined configurations rather than calculating new parameters in real-time, reducing computational complexity while maintaining safety.
Solution Approach 2:
The system continuously monitors the tailgating vehicle's behavior and adjusts the discomfort threshold accordingly. This feedback mechanism allows the system to respond adaptively to changing conditions while using a structured approach that manages complexity through predefined adjustment ranges.
3Reliability
If the autonomous vehicle uses a high discomfort threshold to prioritize safety, then interaction with tailgating vehicles is improved, but occupant comfort deteriorates
Solution Approach 1:
The discomfort threshold is not fixed but dynamically adjusted based on the detected tailgating situation. The system uses moderate threshold increases rather than maximum thresholds, allowing for balanced adjustments that improve safety interactions while minimizing impact on occupant comfort.
Solution Approach 2:
The system applies partial adjustment to the discomfort threshold rather than using extreme values. This partial action approach allows the vehicle to account for tailgating vehicle safety needs while avoiding excessive threshold increases that would significantly degrade occupant comfort.
Data Source
AI summary
Aspects of the disclosure relate to controlling a first vehicle in an autonomous driving mode. While doing so, a second vehicle may be identified. This vehicle may be determined to be a tailgating vehicle. An initial allowable discomfort value representing expected discomfort of an occupant of the first vehicle and expected discomfort of an occupant of the second vehicle may be identified. Determining a speed profile for a future trajectory of the first vehicle that meets the value may be attempted based on a set of factors corresponding to a reaction of the tailgating vehicle. When a speed profile that meets the value cannot be determined, the value may be adjusted until a speed profile that meets the value is determined. The speed profile that meets an adjusted value is used to control the first vehicle in the autonomous driving mode.