Autonomous Vehicle Path Projection for Narrow-Aisle Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicles (AVs) often stop unnecessarily when encountering objects not in their path due to overcautious sensing, requiring wider aisles and limiting their operational flexibility in environments with narrow spaces.
Innovation Solution
A path adaptation method for AVs that generates 3-dimensional projections of the vehicle's path and shape, allowing it to adjust navigation by determining if detected objects overlap with these projections, enabling continued travel unless an overlap is confirmed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles use cautious sensing to detect all objects, then safety is improved, but operational flexibility deteriorates due to unnecessary stops in narrow spaces
Solution Approach 1:
The sensing system is segmented into multiple zones: a first sensing zone for detecting objects that require stopping, and a second sensing zone for detecting objects that allow continued travel. This segmentation allows the vehicle to differentiate between critical and non-critical obstacles, maintaining safety while improving operational flexibility in narrow spaces.
Solution Approach 2:
The vehicle's response to detected objects is made dynamic rather than static. Instead of always stopping when an object is detected, the system dynamically adjusts the response based on the object's location, size, and type. Objects in the first sensing zone trigger stops, while objects in the second sensing zone allow continued travel, enabling adaptive navigation through tight aisles and doorways.
2Reliability
If autonomous vehicles stop for all detected objects, then collision avoidance is improved, but productivity deteriorates due to frequent unnecessary stops
Solution Approach 1:
The sensing system is segmented into multiple zones: a first sensing zone for detecting objects that require stopping, and a second sensing zone for detecting objects that allow continued travel. This segmentation allows the vehicle to differentiate between critical and non-critical obstacles, maintaining safety while improving operational flexibility.
Solution Approach 2:
Instead of applying the full stopping action to all detected objects, the system applies partial action by allowing continued travel for objects in the second sensing zone. This partial action approach maintains sufficient safety margins while significantly reducing unnecessary stops and improving productivity.
3Ease of operation
If autonomous vehicles require wider aisles to avoid unnecessary stops, then operational smoothness is improved, but space utilization deteriorates in warehouse environments
Solution Approach 1:
The sensing system is segmented into multiple zones: a first sensing zone for detecting objects that require stopping, and a second sensing zone for detecting objects that allow continued travel. This segmentation allows the vehicle to differentiate between critical and non-critical obstacles, maintaining safety while improving operational flexibility.
Solution Approach 2:
The vehicle's response to detected objects is made dynamic rather than static. Instead of always stopping when an object is detected, the system dynamically adjusts the response based on the object's location, size, and type. Objects in the first sensing zone trigger stops, while objects in the second sensing zone allow continued travel, enabling adaptive navigation through tight aisles and doorways.
Data Source
AI summary
Provided is a path adaptation system and method for a self-driving vehicle, and a self-driving vehicle including path adaptation technology. The method includes providing a vehicle navigation path through an environment; determining a location of the vehicle relative to the path; generating one or more polygons representing a shape of the vehicle projected from the vehicle location in a vehicle travel direction long the path; combining the one or more projections into a projected motion polygon; acquiring object information representing an object shape from one or more sensors; and determining if the object shape overlaps the projected motion polygon. If so, the method includes adjusting the vehicle navigation. If not, the method includes, continuing navigation along the path. The path adaptation system includes one or more processors configured to execute the path adaptation method.


