Autonomous Vehicle Control Using Estimated Motion Vectors

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for controlling autonomous vehicles are inflexible and often result in unnecessary emergency stops due to the inability to accurately assess the movement and trajectory of objects in their detection area, leading to restrictive vehicle control.

Innovation Solution

A method that determines model objects based on distance and intensity values from optical sensors, estimates motion vectors using a Kalman filter, and controls the vehicle based on these vectors to anticipate and avoid collisions, reducing the need for emergency stops by allowing adaptive movement adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If emergency stop control is used to avoid collisions, then collision avoidance reliability is improved, but vehicle operational flexibility deteriorates

Engineering Contradiction:

Improvecollision avoidance reliabilityVSAvoidvehicle operational flexibility

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The system dynamically adjusts vehicle control based on real-time motion vector estimation. Instead of using a fixed emergency stop response, the control strategy adapts to the specific motion characteristics of detected objects, allowing the vehicle to maintain flexibility while ensuring collision avoidance when necessary.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the control parameter from a binary emergency stop decision to a continuous motion vector-based control approach. By estimating motion vectors and analyzing object trajectories, the system can adjust vehicle speed and direction gradually, maintaining operational flexibility while achieving reliable collision avoidance.

Inventive Principle:

Principle #35Parameter changes

2Speed

If simple thresholding methods are used for object detection, then detection speed is improved, but measurement precision deteriorates

Engineering Contradiction:

Improvedetection speedVSAvoidobject motion detection precision

Core Design Contradiction:

SpeedVSMeasurement precision

Solution Approach 1:

The system replaces simple thresholding methods with motion vector estimation based on Kalman filtering. This substitution enables precise motion detection by modeling object trajectories and predicting future positions, achieving both speed and precision through efficient recursive estimation algorithms.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system introduces motion vectors as an intermediary representation between raw sensor data and vehicle control decisions. By estimating motion vectors from sensor measurements and using them to predict object trajectories, the system achieves precise motion detection while maintaining real-time processing capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentEP3663881B1Method for controlling an autonomous vehicle on the basis of estimated movement vectors

Publication Date: 2021.02.24 SICK AG

Figure 1
Figure 2
Figure 3

AI summary

A method for controlling an autonomous vehicle, which has an optical sensor for detecting objects in a detection range, comprises the following steps: determining measurements of the detection range, wherein the measurements include at least distance values; determining model objects based on the measurements to detect objects in the detection range, wherein each object is represented by a respective model object; estimating a motion vector based on each model object, wherein the motion vector represents a movement of the respective object; and controlling the autonomous vehicle based on the motion vector.