Articulated Object Detection Through Merged Vehicle Detections
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle planning systems struggle to accurately identify and navigate around articulated objects, such as tractor-trailers, due to inefficiencies in object representation and resource allocation, leading to potential collisions and suboptimal navigation.
Innovation Solution
Implementing a model that joins detected objects as articulated objects based on heuristics and algorithms, considering size, overlap, intersection, and distance, to generate more accurate representations, reducing computational resources and improving trajectory prediction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple separate object representations are used to represent articulated objects, then object detection coverage is improved, but computational resources and processing complexity increase
Solution Approach 1:
The patent merges multiple detected object representations (e.g., tractor and trailer detected as separate objects) into a single unified articulated object representation. This combining process reduces the number of separate objects to track and plan around, thereby decreasing computational complexity while maintaining accurate detection of all components through the merged representation.
2Productivity
If articulated objects are identified and tracked as unified entities, then navigation planning efficiency is improved, but object detection accuracy may deteriorate
Solution Approach 1:
The patent segments the articulated object representation into distinct components (e.g., tractor portion and trailer portion) while maintaining their unified relationship. This segmentation allows the system to track and plan for each component individually, preserving detection accuracy for navigation purposes while still benefiting from the efficiency of treating them as a connected entity for overall path planning.
Data Source
AI summary
A vehicle computing system may implement techniques to determine whether two objects in an environment are related as an articulated object. The techniques may include applying heuristics and algorithms to object representations (e.g., bounding boxes) to determine whether two objects are related as a single object with two portions that articulate relative to each other. The techniques may include predicting future states of the articulated object in the environment. One or more model(s) may be used to determine presence of the articulated object and/or predict motion of the articulated object in the future. Based on the presence and/or motion of the articulated object, the vehicle computing system may control operation of the vehicle.