Autonomous Vehicle Speed Planning for Trajectory Uncertainty
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating through uncertain environments due to unpredictable behaviors of other agents on the road, which can lead to potential collisions and discomfort for passengers, as existing systems struggle to adapt driving solutions in real-time to changing trajectories of detected agents.
Innovation Solution
The method involves determining multiple possible trajectories for detected agents, calculating a switching time based on confidence thresholds and discomfort levels, and revising driving solutions to ensure safe navigation by switching to alternative trajectories if an agent is predicted to follow a non-cooperating path, thereby mitigating collision risks and maintaining passenger comfort.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If the autonomous vehicle follows a single driving solution based on predicted trajectories, then the navigation efficiency is improved, but the collision risk increases when agents deviate from predicted paths
Solution Approach 1:
The system performs preliminary actions by pre-calculating multiple alternative driving solutions in advance before collision risk materializes. When an agent's actual trajectory deviates from the predicted trajectory, the system can immediately switch to a pre-computed alternative driving solution, avoiding collision while maintaining navigation efficiency.
Solution Approach 2:
The system dynamically adjusts the driving solution by continuously monitoring agent trajectories and switching between multiple pre-computed driving solutions based on real-time conditions. This dynamic adaptation allows the vehicle to respond to unpredictable agent behaviors while maintaining efficient navigation.
2Reliability
If the autonomous vehicle switches driving solutions frequently to account for trajectory uncertainties, then the collision risk is reduced, but the passenger comfort deteriorates due to increased maneuvers
Solution Approach 1:
By pre-calculating multiple alternative driving solutions, the system prepares contingency plans in advance without executing unnecessary maneuvers. The vehicle only switches to alternative solutions when actually needed, based on real-time trajectory monitoring, thus maintaining passenger comfort while ensuring safety.
Solution Approach 2:
The system changes the parameter of driving solution selection based on the deviation between actual and predicted trajectories. When deviation exceeds a threshold, the system transitions from one driving solution to another, optimizing the balance between collision risk reduction and passenger comfort.
3Adaptability or versatility
If the autonomous vehicle calculates multiple alternative driving solutions, then the adaptability to uncertain environments is improved, but the computational complexity increases
Solution Approach 1:
The system performs preliminary calculation of multiple alternative driving solutions based on predicted trajectories before real-time operation. This advance preparation reduces real-time computational burden while maintaining high adaptability to uncertain environments.
Solution Approach 2:
The system optimizes computational complexity by changing the parameter of trajectory deviation threshold. Only when actual trajectories deviate beyond this threshold does the system recalculate alternative solutions, balancing adaptability with computational efficiency.
4Measurement precision
If the autonomous vehicle waits for high confidence in trajectory prediction before acting, then the false alarm rate is reduced, but the response time to actual collisions increases
Solution Approach 1:
The system performs preliminary calculation of alternative driving solutions based on predicted trajectories in advance. When an agent's actual trajectory deviates from the prediction, the pre-computed alternatives enable immediate response without waiting for high confidence predictions, thus reducing response time while maintaining accuracy.
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.