Lead Vehicle Intention Estimation Using Partitioned Model Discrimination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for estimating the intention of a lead vehicle by an ego vehicle are inefficient due to complex calculations that can delay decision-making in autonomous or semi-autonomous systems, particularly in cyber-physical systems where models and behavior patterns are not fully accessible.
Innovation Solution
A partition-based parametric active model discrimination approach that uses online sensor measurements and predetermined partitions of the operating region to design optimal input sequences for the ego vehicle, minimizing computational burden by formulating the problem as a sequence of offline optimization problems and casting it as a mixed-integer linear program.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If complex model discrimination calculations are performed to accurately estimate lead vehicle intention, then measurement precision is improved, but loss of time increases due to computational burden
Solution Approach 1:
The patent pre-computes and stores optimal separating input sequences offline before real-time operation. During actual intention estimation, the system only needs to retrieve and apply pre-computed inputs rather than performing complex real-time optimization, thus maintaining high accuracy while reducing computational time to acceptable levels for autonomous driving decisions.
2Measurement precision
If complex model discrimination calculations are performed to accurately estimate lead vehicle intention, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The complex optimization problem is solved offline in advance, and the solutions are stored for online retrieval. This shifts the computational burden from the real-time execution system to an offline preprocessing stage, significantly reducing the complexity of the online decision-making system while maintaining estimation accuracy.
Solution Approach 2:
The patent divides the problem into two distinct phases: offline computation phase where optimal inputs are pre-calculated and stored, and online execution phase where pre-computed inputs are retrieved and applied. This segmentation separates the complex computational tasks from the real-time system, reducing overall device complexity.
3Adaptability or versatility
If real-time sensor measurements are used for intention estimation, then adaptability is improved, but loss of time increases due to processing requirements
Solution Approach 1:
The system utilizes real-time sensor measurements to select appropriate pre-computed input sequences based on current system state, but avoids real-time optimization calculations. This approach maintains adaptability to current conditions while eliminating the time-consuming real-time computational burden.
Data Source
AI summary
A method estimates an intention of a lead vehicle by an ego vehicle. The method includes: (a) receiving, from at least one of a first plurality of sensors coupled to the ego vehicle, information associated with a parametric variable, (b) selecting a partition of an operating region of the parametric variable based on the parametric variable information, wherein the operating region includes a predetermined range of values for the parametric variable, wherein the partition includes a subset of the predetermined range of values and being associated with a predetermined ego vehicle input, and wherein the predetermined vehicle input includes at least one value for a parameter corresponding to dynamics of the ego vehicle, and (c) causing a vehicle control system of the ego vehicle to perform a vehicle maneuver based on the predetermined ego vehicle input.