Autonomous Driving Tree Policy Planning for Safe Switching Points
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating safely and efficiently due to uncertain behaviors of other road agents, leading to potential collisions and frequent slowing or stopping to account for unpredictable scenarios.
Innovation Solution
Implementing a tree policy planning method that detects agent vehicles, determines nominal and alternate driving solutions based on predicted trajectories, assesses risk factors, and identifies candidate switching points to adjust the driving solution dynamically, ensuring safe and efficient navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle frequently slows or stops to account for unpredictable scenarios, then safety is improved, but productivity deteriorates
Solution Approach 1:
The system performs preliminary actions by pre-planning multiple driving solutions (nominal and alternate) and identifying candidate switching points before uncertain scenarios actually occur. This allows the vehicle to have ready-made contingency plans that can be quickly activated, improving safety responses without requiring frequent reactive slowing or stopping that would hinder productivity
Solution Approach 2:
The system dynamically switches between different driving solutions based on real-time conditions. By maintaining multiple pre-computed driving solutions and being able to transition between them at candidate switching points, the system adapts to unpredictable scenarios efficiently, ensuring safety while maintaining continuous motion and productivity
2Reliability
If the autonomous vehicle uses complex tree policy planning with multiple scenarios, then reliability is improved, but device complexity worsens
Solution Approach 1:
The complex planning problem is segmented into manageable components: nominal driving solution, alternate driving solutions, and candidate switching points. Each component is computed and stored separately, allowing the system to handle multiple scenarios reliably while organizing the complexity in a structured, computationally efficient manner
Solution Approach 2:
The system computes a limited set of driving solutions (one nominal and a few alternate) rather than exhaustively planning for all possible scenarios. This partial action approach provides sufficient reliability for handling uncertain scenarios while keeping computational complexity and device requirements manageable
Data Source
AI summary
An autonomous vehicle is operated along a route according to a nominal driving solution that takes into account one or more first constraints including a first predicted trajectory for an agent vehicle. An alternate scenario is determined based on one or more second external constraints that include a second predicted trajectory for the agent vehicle different from the first predicted trajectory. A risk factor on the nominal driving solution is determined for the alternative scenario, and a secondary driving solution is determined based on the risk factor and the one or more second external constraints. A candidate switching point is identified where the secondary driving solution diverges from the nominal driving solution, and the nominal driving solution is revised up to the candidate switching point based on the secondary driving solution. The autonomous vehicle is then operated based on the revised nominal driving solution.