Autonomous Vehicle Path Adjustment for Target-Zone Actions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in efficiently planning paths that account for specific actions such as picking up or dropping off passengers or items, as existing systems often rely on nominal paths that do not consider obstacles or dynamic environments.
Innovation Solution
A computer-implemented method that accesses map data and sensor data to alter nominal paths, designating action regions within target zones, and generates trajectories based on target velocities to ensure safe and efficient execution of specific actions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If autonomous vehicles use nominal paths for navigation, then the path planning is simple and fast, but the vehicle cannot account for obstacles or dynamic environments requiring specific actions
Solution Approach 1:
The path planning system segments the nominal path into multiple path segments based on geometric characteristics and action requirements. Each segment can be independently evaluated and modified to accommodate obstacles or dynamic environments, allowing the vehicle to perform specific actions like picking up or dropping off passengers or items at designated locations along the path.
Solution Approach 2:
The system performs preliminary path segmentation and identifies action locations before the vehicle reaches them. By pre-processing the nominal path to identify where obstacles may exist or where actions need to be performed, the system can prepare appropriate path modifications in advance, reducing real-time computational complexity while maintaining adaptability.
2Reliability
If autonomous vehicles alter nominal paths to traverse target zones for performing actions, then the vehicle can safely perform actions like picking up or dropping off passengers or items, but the processing cycles and energy consumption increase
Solution Approach 1:
The system applies local quality by making minimal, localized modifications to the nominal path only at specific action locations where obstacles or dynamic conditions require intervention. Rather than re-planning the entire path, the system adjusts only the necessary path segments near action locations, thereby ensuring safety for performing actions while minimizing the computational energy required for path alterations.
Solution Approach 2:
The system performs partial path alterations only where necessary to enable actions, rather than completely re-planning the entire path. By applying partial modifications to specific path segments instead of excessive full-path re-planning, the system achieves the necessary reliability for safe action execution while reducing overall processing cycles and energy consumption.
3Adaptability or versatility
If autonomous vehicles frequently re-plan paths to account for dynamic environments, then the adaptability to changing conditions improves, but the processing cycles and battery life are adversely affected
Solution Approach 1:
By segmenting the nominal path into discrete path segments with identified geometric characteristics, the system can efficiently evaluate and respond to dynamic environmental changes. When changes are detected, only the affected path segments need to be re-planned rather than the entire path, maintaining adaptability while reducing processing cycles.
Solution Approach 2:
The system performs preliminary identification of path segments and action locations before dynamic changes occur. This pre-processing creates a structured framework that enables rapid response to environmental changes by only requiring local re-planning of affected segments, thereby maintaining high adaptability while minimizing the time and processing cycles required for path adjustments.
Data Source
AI summary
The present disclosure is directed to altering vehicle paths. In particular, a computing system can access map data for a geographic area. The computing system can obtain target zone data describing a target zone within the geographic area. The computing system can determine an altered nominal path to traverse the target zone. The computing system can designate a portion of the altered nominal path as a designated action region associated with the target zone. The computing system can generate a longitudinal plan for an autonomous vehicle through the geographic area based on the altered nominal path. The computing system can generate a target velocity for one or more portions of the nominal path within the designated action region. The computing system can generate a trajectory for the autonomous vehicle based on the target velocity and the altered nominal path.