Radar Velocity Projection to Filter Phantom Reflections
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately navigating through environments due to inaccurate or incorrect sensor data from radar systems, which can result in false positives from reflections off objects, leading to unnecessary actions like braking or steering.
Innovation Solution
The implementation of techniques to differentiate radar returns associated with actual objects from reflected returns by using pair-wise comparisons, velocity projections, and additional sensor information to identify and exclude reflected returns from route planning, thereby improving the accuracy of sensor data used by autonomous vehicles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If radar data is used for autonomous vehicle navigation, then the vehicle can detect objects in the environment, but reflections off objects cause false positives and inaccurate sensor data
Solution Approach 1:
The patent uses velocity information as an intermediary parameter to distinguish between actual objects and reflected radar returns. By comparing the velocity of detected objects with the projected velocity from potential source objects, the system can identify and filter out false positives caused by reflections, thereby improving measurement precision without sacrificing detection capability
Solution Approach 2:
The system implements a feedback mechanism where detected objects are used to generate expected velocity projections, which are then compared against newly detected objects. This closed-loop verification process allows the system to continuously identify and eliminate false positives from reflections, improving the accuracy of sensor data over time
2Ease of operation
If the vehicle takes actions based on inaccurate sensor data, then it may respond to detected objects, but false positives lead to unnecessary actions like braking or steering
Solution Approach 1:
The patent applies preliminary velocity verification before the vehicle takes any actions. By projecting velocities from potential source objects and comparing them with detected objects in advance, the system identifies false positives before they trigger unnecessary braking or steering actions, thereby improving reliability while maintaining ease of operation for genuine obstacles
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the safety and comfort of autonomous vehicle operations by reducing unnecessary actions and improving trajectory generation, leading to improved safety outcomes and user experiences by accurately distinguishing between actual and phantom objects.
Implementation Method 1
a radar sensor may emit radio energy that reflects (or bounces) off objects in the environment before returning to the sensor
Implementation Method 2
radio energy may reflect off multiple objects in the environment before returning to the radar sensor
Implementation Method 3
The object return may include information about an object velocity... The first radar return may include a velocity having a direction along a first direction between the object and the vehicle
Data Source
AI summary
Techniques are discussed for determining reflected returns in radar sensor data. In some instances, pairs of radar returns may be compared to one another. For example, a velocity associated with a first radar return may be projected onto a radial direction associated with a second radar return to determine a projected velocity. In some examples, the second radar return may be a reflected return if the magnitude of the projected velocity corresponds to a magnitude of the second radar return. In some instances, a vehicle, such as an autonomous vehicle, may be controlled at the exclusion of information from reflected returns.