Dynamic Coordinate Origin Shifting for Vehicle Trajectory Precision
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous electric vehicles face computational inefficiencies and inaccuracies in determining trajectories due to large numerical values required for positional information, especially when using static global coordinate systems, which can lead to rounding errors and increased storage needs.
Innovation Solution
Dynamic modification of the coordinate system based on conditions such as speed, distance traveled, and availability of computing resources allows for the use of single-precision floating-point data, reducing rounding errors and enhancing computational efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a static global coordinate system is used for positional information, then the trajectory can be determined globally, but the numerical values become large leading to rounding errors and computational inefficiency
Solution Approach 1:
The coordinate system origin is dynamically adjusted based on the vehicle's current position rather than remaining static at the starting point. This allows the coordinate values to remain small and manageable throughout the journey, preventing rounding errors while maintaining global trajectory determination capability
Solution Approach 2:
The patent changes the reference frame parameters by switching between different coordinate systems (global vs. local) and adjusting the origin point dynamically. This parameter change enables the use of single-precision floating-point data with smaller numerical values, improving computational efficiency without sacrificing positional accuracy
2Productivity
If single-precision floating-point data is used to reduce computational overhead, then processing efficiency improves, but rounding errors increase due to large numerical values
Solution Approach 1:
By dynamically adjusting the coordinate system origin to track the vehicle's position, the patent ensures that coordinate values remain small throughout operation. This enables the use of single-precision floating-point data without accumulating significant rounding errors, as the values stay within a manageable range
Solution Approach 2:
The patent changes the numerical parameter range by introducing local coordinate systems with origins positioned to minimize coordinate values. This allows single-precision floating-point representation to maintain adequate precision while providing computational efficiency benefits
3Measurement precision
If double-precision floating-point data is used to maintain accuracy, then positional information precision improves, but storage needs and computational overhead increase
Solution Approach 1:
The patent changes the parameter representation by using coordinate system transformations that result in smaller numerical values. This enables the use of single-precision floating-point data (32-bit) instead of double-precision (64-bit), reducing storage requirements by half while maintaining adequate precision through dynamic origin adjustment
Data Source
AI summary
Techniques are described for determining to modify a coordinate system in response to the occurrence of a condition. As non-limiting examples, such conditions comprise distance traveled, speed of the vehicle (or system), an amount of computational resources available, a time since the last change, a number of objects present, the presence (or absence) of a particular object proximate the vehicle, a distance to a proximate object, based on a particular frequency, or the like. Such modifications may improve the operation and safety of a computing system used for path planning and trajectory generation by allowing lower precision numerical representations to be used in safety-critical situations while avoiding potential computational errors that would otherwise result from using such a representation.