Autonomous Vehicle Speed Planning With Trajectory Switching Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating through environments where detected agents may have multiple predicted trajectories, requiring the vehicle to adapt its driving solution to avoid collisions while ensuring a comfortable ride for passengers.
Innovation Solution
The vehicle's computing devices determine a first driving solution based on an external constraint corresponding to an agent following a cooperating trajectory, and a switching time is calculated to deviate from this solution if the agent follows a non-cooperating trajectory. A switching constraint is formulated to allow the vehicle to switch to another driving solution at the switching time, ensuring safe navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If the vehicle determines a first driving solution based on an external constraint corresponding to an agent following a cooperating trajectory, then the ride comfort for passengers is improved, but the reliability of collision avoidance deteriorates when the agent follows a non-cooperating trajectory
Solution Approach 1:
The system performs preliminary actions by determining a switching time in advance and formulating a switching constraint that allows the vehicle to transition from the first driving solution to a second driving solution. This preliminary preparation enables the vehicle to maintain comfort during normal operation while having a pre-planned escape route ready when needed.
Solution Approach 2:
The system dynamically adjusts the driving solution by allowing switching between the first driving solution (optimized for comfort) and the second driving solution (optimized for safety) based on the actual behavior of the detected agent. The switching constraint creates a dynamic boundary that the vehicle can cross when necessary, transforming a static comfort-optimized path into a dynamic adaptive path.
2Reliability
If the vehicle hedges against unlikely but potentially severe collisions by ensuring it can switch to an alternative trajectory, then the reliability of collision avoidance is improved, but the complexity of the driving solution increases
Solution Approach 1:
The system segments the driving solution into two distinct parts: the first driving solution optimized for comfort and the second driving solution optimized for safety. By dividing the problem into these two segments, the system manages complexity through modular design, where each segment has its own optimization criteria and can be independently calculated and evaluated.
Solution Approach 2:
The switching constraint acts as an intermediary element that connects and coordinates the two driving solutions. Rather than creating a completely new complex solution, the switching constraint serves as a mediator that enables transitions between the two simpler, purpose-specific solutions, thereby managing overall system complexity.
3Reliability
If the vehicle frequently switches between driving solutions to adapt to agent behavior, then the reliability of collision avoidance is improved, but the ride comfort deteriorates due to increased slowing or stopping
Solution Approach 1:
The system applies preliminary anti-action by pre-calculating the switching constraint and second driving solution in advance, so that when a switch becomes necessary, the vehicle can transition smoothly without abrupt maneuvers. This preliminary preparation prevents the need for reactive, comfort-degrading emergency maneuvers.
Solution Approach 2:
By determining the switching time and switching constraint in advance, the system performs preliminary actions that enable smooth transitions. The vehicle doesn't need to make abrupt changes when switching solutions, as the transition parameters are pre-calculated to maintain ride comfort while ensuring safety.
Data Source
AI summary
A first driving solution for a vehicle along a portion of a route is determined based on an agent detected in the vehicle's environment following a first trajectory of a plurality of possible trajectories. A switching time is determined for the vehicle to deviate from the first driving solution for a situation in which the agent is following a second trajectory of the plurality of possible trajectories. The first driving solution is revised such that the vehicle will be able to switch from the revised first driving solution to another driving solution at the switching time in case if the detected agent is following the second trajectory.