Autonomous Vehicle Speed Planning With Temporal Derate Mapping

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing motion planning systems for autonomous vehicles face inaccuracies in transforming spatial derate intervals to the temporal domain, leading to premature or delayed slowing down due to approximate speed profile inaccuracies, affecting ride comfort and collision avoidance.

Innovation Solution

The method generates a spatial domain speed profile and derate profile, transforming the derate interval into a temporal derate interval using a precise derate profile, ensuring accurate input for longitudinal speed planning, thereby avoiding inaccuracies in speed profile transformation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If an approximate speed profile is used to transform spatial derate intervals to the temporal domain, then the transformation process is simplified and can be executed efficiently, but inaccuracies in the approximate speed profile lead to premature or delayed slowing down, affecting ride comfort and collision avoidance

Engineering Contradiction:
Improveexecution efficiency of speed planningVSAvoidaccuracy of temporal derate interval
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system performs a preliminary speed planning step to generate an initial speed profile before the main longitudinal problem solving. This preliminary speed profile is then used to accurately transform spatial derate intervals to the temporal domain, ensuring that the transformation is based on accurate speed information rather than approximations, thereby improving the accuracy of temporal derate intervals while maintaining execution efficiency

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary transformation process that uses the preliminary speed profile as a mediator to convert spatial derate intervals (distance-based) to temporal derate intervals (time-based). This intermediary step ensures accurate mapping between spatial and temporal domains, preventing the inaccuracies that would arise from using approximate speed profiles directly in the main optimization

Inventive Principle:
Principle #24Intermediary (Mediator)

2Device complexity

If spatial information is transformed to the temporal domain using an approximate speed profile, then the computational complexity is reduced, but the transformation inaccuracies propagate to the longitudinal problem output, affecting navigation accuracy

Engineering Contradiction:
Improvecomputational complexity of transformationVSAvoidnavigation accuracy
Core Design Contradiction:
Device complexityVSManufacturing precision

Solution Approach 1:

A preliminary speed profile is generated before the main longitudinal problem to serve as an accurate basis for transforming spatial derate intervals to the temporal domain. This preliminary computation, while adding a step, uses simplified assumptions that reduce overall computational complexity compared to performing the transformation within the full optimization, while significantly improving navigation accuracy by eliminating transformation errors

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates a copy of the speed profile information in the form of a derate profile that maps spatial derate intervals to temporal domains. This copied representation allows the longitudinal problem to access accurate temporal constraints without requiring complex real-time transformations during optimization, reducing computational complexity while maintaining high navigation accuracy

Inventive Principle:
Principle #26Copying

Data Source

PatentUS12168438B2Systems and methods for controlling speed of an autonomous vehicle
Publication Date: 2024.12.17 FORD GLOBAL TECH LLC
  • US12168438B2 patent drawing
  • US12168438B2 patent drawing
  • US12168438B2 patent drawing

AI summary

Systems and methods for generating a trajectory of a vehicle are disclosed. The methods include generating a spatial domain speed profile for a path represented as a sequence of poses of a vehicle between a first point and a second point. Generation of the spatial domain speed profile uses a longitudinal problem while excluding a derate interval on the path when speed of the vehicle cannot exceed a threshold. The methods further include generating a derate profile using the spatial domain speed profile and the derate interval, and transforming the derate interval to a temporal derate interval. The temporal derate interval may include time steps at which the speed of the vehicle cannot exceed the threshold while traversing the path, and may be used as an input to the longitudinal problem for generating a trajectory of the vehicle for navigating between the first point and the second point.