Road Model Lane-Type Hypotheses With Quantified Uncertainty
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing road-perception systems are often inaccurate and fail to reliably model roadways and quantify uncertainty in lane types, which is a requirement for safety regulations in autonomous and assisted driving systems.
Innovation Solution
A method using Dempster-Shafer Theory to determine lane-type and roadway hypotheses by assigning belief masses and plausibility parameters, consolidating these into roadway hypotheses, and using them to operate vehicles safely, with the system dynamically updating based on sensor data and prior knowledge.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional road-perception systems are used to model roadways, then the system complexity is reduced, but the measurement precision and reliability of lane-type hypotheses deteriorate
Solution Approach 1:
The patent introduces Dempster-Shafer Theory as an intermediary framework that bridges sensor data and lane-type hypotheses. This theory provides belief masses and plausibility parameters as intermediate representations, enabling uncertainty quantification without requiring complex sensor arrays. The intermediary mathematical framework transforms raw sensor inputs into structured hypothesis evaluations with explicit uncertainty measures.
Solution Approach 2:
The patent changes the parameter representation from binary lane-type classification to continuous belief masses and plausibility parameters. By transforming discrete hypothesis outcomes into continuous uncertainty parameters, the system achieves more nuanced measurement precision while maintaining computational tractability through standardized parameter transformations.
2Reliability
If multiple sensors are added to improve road model accuracy, then the measurement precision improves, but the device complexity and cost increase
Solution Approach 1:
The patent enables the existing sensor system to serve itself by extracting maximum reliability information through Dempster-Shafer Theory. The system self-quantifies uncertainty using belief masses derived from current sensor data, eliminating the need for additional sensors. The mathematical framework allows the system to achieve higher reliability by better utilizing existing sensor capabilities rather than adding more sensors.
Solution Approach 2:
The patent replaces mechanical/sensor-based complexity with mathematical/computational complexity. Instead of adding physical sensors to improve reliability, the system substitutes a sophisticated uncertainty quantification algorithm that processes existing sensor data to produce reliable road models with explicit confidence measures.
3Reliability
If uncertainty quantification is implemented to satisfy safety standards, then the reliability improves, but the computational complexity increases
Solution Approach 1:
The patent segments the uncertainty quantification process into distinct computational stages: belief mass assignment, plausibility parameter calculation, and hypothesis consolidation. This segmentation allows each computational step to be optimized independently, reducing overall computational complexity while maintaining reliable uncertainty quantification for safety standard compliance.
Solution Approach 2:
The patent implements partial uncertainty quantification by focusing computational resources on critical lane-type hypotheses rather than all possible hypotheses. By applying Dempster-Shafer Theory selectively to the most relevant hypotheses, the system achieves sufficient reliability for safety standards without the excessive computational burden of complete hypothesis space analysis.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
This document describes techniques and systems to make determinations of lane-type and roadway hypotheses in a road model. The road-perception system can fuse various forms of evidence to determine lane-type hypotheses and respective belief masses associated with the lane-type hypotheses. The road-perception system the computes, using the belief masses, a belief parameter and a plausibility parameter associated with the lane-type hypotheses. One or more roadway hypotheses are then determined using the lane-type hypotheses. The road-perception system then uses the respective belief parameter and plausibility parameter associated with the lane-type hypotheses to compute a belief parameter and a plausibility parameter associated with the roadway hypotheses. In this way, the described techniques and systems can provide an accurate and reliable road model with quantified uncertainty.