Vehicle Trajectory Updates for Dynamic Obstacle Blockage
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in predicting and adapting to dynamic environments, particularly when blocked by objects, as existing systems struggle to efficiently update trajectories without recalculating the entire route, leading to inefficiencies in processing resources and route planning.
Innovation Solution
The system retrieves sensor data to determine probable object locations and generates operational commands while the vehicle is blocked, allowing it to execute a trajectory when unblocked, and updates only the affected portion of the route based on probability calculations, rather than recalculating the entire trajectory.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the system recalculates the entire trajectory when blocked by an object, then the route planning reliability is improved, but the processing time and computational resources are excessively consumed
Solution Approach 1:
The trajectory is divided into multiple segments, and only the affected segment (where the blockage occurs) is recalculated rather than the entire trajectory. This segmentation allows the system to maintain route planning reliability for the blocked portion while avoiding unnecessary recalculation of unaffected portions, thus reducing processing time and computational resource consumption.
Solution Approach 2:
The system performs preliminary trajectory planning before the vehicle encounters a blockage, and when a blockage is detected, it quickly updates only the affected segment using pre-computed alternative paths or heuristics. This preliminary action approach ensures that the majority of the trajectory is already optimized, and only minimal adjustments are needed when blockages occur.
2Adaptability or versatility
If the system updates the entire trajectory whenever an object is detected, then the adaptability to dynamic environments is improved, but the processing resources are wasted
Solution Approach 1:
The system applies local quality by updating only the specific portion of the trajectory that is affected by the detected object, rather than uniformly updating the entire trajectory. This allows the system to maintain high adaptability to dynamic environments where objects are detected, while significantly reducing processing resource consumption by avoiding unnecessary updates to unaffected trajectory segments.
3Productivity
If the vehicle waits to plan the trajectory until it becomes unblocked, then the processing efficiency is improved, but the response time to resume movement is delayed
Solution Approach 1:
The system performs trajectory planning in advance while the vehicle is still blocked, using the blockage detection time productively to compute the updated trajectory. This preliminary action ensures that when the vehicle becomes unblocked, the trajectory is already ready for execution, thus maintaining high processing efficiency while minimizing the response time delay.
Solution Approach 2:
The trajectory planning process continues uninterrupted during the blockage period, with the system actively computing the updated trajectory instead of idle waiting. This continuity of useful action ensures that processing efficiency is maintained throughout the entire blockage duration, and the vehicle can resume movement immediately once unblocked without additional delay.
Data Source
AI summary
Techniques are provided for generating a driving trajectory for a vehicle while the vehicle is blocked (e.g., the sensor of the vehicle have detected an object results in the vehicle being unable to move) by an object (e.g., another vehicle, bicycle, or a pedestrian) and executing the driving trajectory when the vehicle becomes unblocked. In addition, techniques are provided for updating a portion of a driving trajectory of a vehicle based on a determination that an object will cross a segment of the current driving trajectory at a later point, without recalculating the whole trajectory.