Autonomous Vehicle Path Projection for Narrow-Aisle Obstacle Avoidance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current self-driving vehicles often stop unnecessarily when encountering objects not in their path due to overcautious sensor detection, requiring wider aisles and limiting their operational flexibility in environments with narrow spaces.
Innovation Solution
A path adaptation method that uses 3-dimensional projections of the vehicle's shape and load to determine if detected objects overlap with its planned path, allowing the vehicle to adjust navigation by continuing, slowing, or stopping as necessary, thereby enabling operation in narrower spaces.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sensor detection is made overcautious to detect all potential objects, then safety is improved, but the vehicle stops unnecessarily and operational flexibility deteriorates
Solution Approach 1:
The system applies different detection strictness to different spatial locations by creating a motion outline specific to the vehicle's planned path. Only objects within this localized motion outline trigger stopping, while objects outside it are ignored even if detected by sensors. This resolves the contradiction by making detection selective rather than uniform across all space.
Solution Approach 2:
The system segments the detection space into relevant (within motion outline) and irrelevant (outside motion outline) regions. By dividing the sensor field into these segments and applying different response rules to each, the system maintains safety for actual path obstacles while allowing flexible operation around non-path objects.
2Adaptability or versatility
If wider aisles are used to avoid unnecessary stops, then operational flexibility is improved, but the requirement for larger space deteriorates
Solution Approach 1:
Instead of requiring uniformly wide aisles, the system applies localized path-specific detection. The motion outline is generated based on the vehicle's specific navigation path, allowing operation in narrow spaces as long as objects outside the projected path are ignored. This enables flexible operation in constrained spaces without sacrificing safety.
3Reliability
If the vehicle stops for all detected objects, then safety is improved, but productivity deteriorates
Solution Approach 1:
The system segments detected objects into two categories: those within the motion outline (path-relevant) and those outside it (path-irrelevant). Only the former category triggers stopping, while the latter is ignored. This segmentation maintains safety for actual hazards while eliminating unnecessary stops that reduce productivity.
Solution Approach 2:
Instead of stopping for all detected objects (excessive action), the system stops only for objects within the motion outline (partial action). This partial application of the stopping rule eliminates unnecessary stops while maintaining adequate safety coverage for actual path obstacles.
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.