Autonomous Vehicle Speed Profiling Under Passenger Discomfort Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in determining optimal speed profiles while interacting with other vehicles, particularly when considering the discomfort of both their passengers and those in other vehicles, especially in situations like tailgating, where the behavior of other road users affects the vehicle's trajectory and safety.
Innovation Solution
The method involves identifying geometry for future vehicle trajectories, determining initial and adjusted allowable discomfort values, and generating speed profiles that balance the discomfort of all involved parties, including tailgating vehicles, by adjusting constraints and iteratively increasing discomfort values to find a feasible speed plan.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the autonomous vehicle uses a strict initial allowable discomfort value to ensure passenger comfort, then passenger comfort is improved, but the ability to find a feasible speed profile decreases
Solution Approach 1:
The system dynamically adjusts the allowable discomfort value based on the driving situation and interaction with other vehicles. Instead of using a fixed comfort threshold, the system iteratively modifies the discomfort value to find a feasible speed profile that balances comfort and safety requirements in real-time
Solution Approach 2:
The system changes the discomfort parameter iteratively by adjusting the allowable discomfort value when an initial feasible speed profile cannot be determined. This parameter adjustment allows the system to explore different comfort levels until a valid speed profile is found that satisfies both comfort and safety constraints
2Reliability
If the autonomous vehicle makes conservative estimates with larger safety margins to improve safety, then safety is improved, but the vehicle's speed and efficiency decrease
Solution Approach 1:
The system applies safety margins selectively rather than uniformly. By using discomfort values that account for other road users' reactions, the system applies conservative estimates only where necessary for safety, rather than imposing excessive safety margins in all situations, thus maintaining better speed and efficiency
3Reliability
If the autonomous vehicle considers the discomfort of passengers in other vehicles to improve overall safety, then overall safety is improved, but the complexity of determining the speed profile increases
Solution Approach 1:
The system uses discomfort value as an intermediary parameter to simplify the complex multi-vehicle interaction problem. Instead of directly modeling all interactions between multiple vehicles and passengers, the system uses discomfort values as a mediator to capture these interactions in a computationally manageable form
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Aspects of the disclosure relate to controlling a first vehicle (100) in an autonomous driving mode. While doing so, a second vehicle (720, 820, 920, 1020) may be identified. Geometry for a future trajectory of the first vehicle may be identified, and an initial allowable discomfort value may be identified. Determining a speed profile for the geometry that meets the value may be attempted by determining a discomfort value for the speed profile based on a set of factors relating to at least discomfort of a passenger of the first vehicle and discomfort of a passenger of the second 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.