Autonomous Vehicle Velocity Determination Using Point Cloud Transformations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in accurately determining the velocity of moving objects within their environment, especially when the view of an object changes rapidly, leading to difficulties in predicting potential collisions and avoiding obstacles effectively.
Innovation Solution
The method involves receiving and processing sets of points from depth sensors over time periods to form point clouds, determining transformations between these point clouds, and using these transformations to calculate the velocity of objects, which enables precise control of the vehicle to avoid collisions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If the vehicle uses sensors to detect environmental information for autonomous navigation, then the vehicle can navigate without driver input, but the system cannot accurately determine object velocity when the view changes rapidly
Solution Approach 1:
The system performs preliminary actions by capturing multiple point clouds at different time periods before determining object velocity. By storing and processing these preliminary data points, the system can accurately calculate velocity even when view changes occur, resolving the contradiction between autonomous navigation and velocity measurement accuracy.
Solution Approach 2:
The system uses feedback mechanisms by continuously comparing point clouds from different time periods to determine object velocity. This feedback loop allows the autonomous vehicle to adjust its navigation based on accurate velocity information, even in dynamic viewing conditions.
2Measurement precision
If the system processes point clouds from multiple time periods to determine object velocity, then velocity measurement accuracy improves, but processing time and computational complexity increase
Solution Approach 1:
The system segments the environmental data into discrete point clouds at specific time periods. By dividing the continuous data stream into manageable segments, the system can process velocity information efficiently without excessive computational delay, balancing accuracy with processing time.
Solution Approach 2:
The system uses partial action by selecting only the necessary point clouds from multiple time periods rather than processing all available data. This selective approach maintains velocity determination accuracy while reducing unnecessary processing time and computational resources.
3Speed
If the vehicle rapidly processes environmental data to maintain low latency, then response time improves, but measurement precision of object velocity deteriorates
Solution Approach 1:
The system performs preliminary data collection and processing in advance, capturing point clouds at multiple time periods before velocity determination is needed. This preliminary action enables rapid processing when required while maintaining measurement precision through the pre-collected data.
Solution Approach 2:
The system maintains continuous useful action by continuously capturing and processing point clouds in real-time. This continuous processing enables low latency response while preserving measurement precision through ongoing data collection and velocity calculation.
Data Source
AI summary
An example method may include receiving a first set of points based on detection of an environment of an autonomous vehicle during a first time period, selecting a plurality of points from the first set of points that form a first point cloud representing an object in the environment, receiving a second set of points based on detection of the environment during a second time period which is after the first period, selecting a plurality of points from the second set of points that form a second point cloud representing the object in the environment, determining a transformation between the selected points from the first set of points and the selected points from the second set of points, using the transformation to determine a velocity of the object, and providing instructions to control the autonomous vehicle based at least in part on the velocity of the object.