Autonomous Vehicle Trajectory Segmentation for Blocked-Path Replanning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in predicting and adapting to future movements of objects in their environment, particularly when blocked by obstacles, requiring efficient route planning and updating without recalculating the entire trajectory.
Innovation Solution
The system retrieves sensor data to determine probable object locations and generates operational commands while blocked, allowing the vehicle to execute a trajectory when unblocked, and updates specific segments of the route based on probability calculations without recalculating the entire path.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the vehicle recalculates the entire trajectory when blocked by an object, then the route can be updated to avoid the object, but the processing time and computational resources increase significantly
Solution Approach 1:
The trajectory is divided into multiple segments, and only the affected segment(s) are recalculated when an obstacle is detected, rather than recalculating the entire trajectory. This segmentation allows the system to maintain route reliability while significantly reducing computational time and resources.
Solution Approach 2:
The system pre-calculates multiple possible trajectory segments and stores them in advance. When blocked by an object, the vehicle can quickly switch to a pre-calculated alternative segment without performing a complete recalculation, thus reducing processing time while maintaining route reliability.
2Measurement precision
If the vehicle waits until unblocked to plan the trajectory, then the system has real-time data, but the response time to resume movement is delayed
Solution Approach 1:
While the vehicle is blocked, the system continues to retrieve updated sensor data and pre-plans trajectory segments in advance. This preliminary action ensures that when the vehicle becomes unblocked, the trajectory can be executed immediately without delay, maintaining both data accuracy and response speed.
Solution Approach 2:
The trajectory planning process continues uninterrupted even while the vehicle is blocked. The system continuously updates sensor data and prepares trajectory segments during the blocked period, ensuring that planning activity never stops and the vehicle can resume movement quickly once unblocked.
3Stability of the object's composition
If the system updates the whole route based on a change in a segment, then the route remains consistent, but processing resources are wasted
Solution Approach 1:
The route is segmented into independent sections, and updates are applied only to the specific segment(s) affected by obstacles or changes. This maintains route consistency in updated areas while avoiding unnecessary processing of unchanged segments, thereby improving processing efficiency.
Solution Approach 2:
Different parts of the route have different update priorities and frequencies. Only the local segment affected by changes is updated with high priority, while other segments maintain their existing trajectories. This localised approach preserves overall route consistency while optimising processing resource utilisation.
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.