Vehicle Motion Corridors for Faster Autonomous Path Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle path planning systems generate excessive corridor data and inefficiently evaluate potential trajectories due to the use of minimal projection distance of obstacle vertices to reference lines, leading to increased processing time and energy consumption.
Innovation Solution
The method involves generating a vehicle travel corridor by accessing map and sensor data to identify obstacles and determining offset distances based on the smallest total distance to these obstacles, aggregating these into a corridor data structure that defines a safe travel area for the autonomous vehicle, thereby reducing unnecessary data generation and processing.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If minimal projection distance of obstacle vertices to reference lines is used for corridor generation, then the corridor data structure can be constructed, but excessive corridor data is generated leading to increased processing time and energy consumption
Solution Approach 1:
The patent divides the corridor generation process into segments based on road geometry changes. Instead of generating corridor data for the entire path, the system segments the path at locations where road geometry changes (curves, intersections, etc.) and generates corridor data only for each segment. This segmentation reduces the total amount of corridor data generated while maintaining safety, directly addressing the contradiction between productivity and processing time.
Solution Approach 2:
The patent extracts only the essential corridor data needed for safe navigation by using smallest total distance offsets rather than generating complete corridor structures. The system extracts minimal sufficient information (offset distances from reference line to obstacles) and discards redundant data, reducing processing requirements while maintaining the ability to evaluate trajectories safely.
2Reliability
If minimal projection distance of obstacle vertices to reference lines is used for corridor generation, then the corridor data structure can be constructed, but excessive data storage and processing needs increase energy consumption
Solution Approach 1:
The patent applies local quality by calculating offset distances based on the specific local geometry and obstacle positions at each segment rather than using uniform corridor widths throughout the entire path. The system determines smallest total distance offsets locally at each segment boundary and within segments, allowing the corridor data to adapt to local conditions. This reduces overall data storage needs while maintaining safety where obstacles are present.
Solution Approach 2:
The patent uses partial action by generating corridor data only for necessary segments rather than complete paths. The system calculates corridor offsets only where needed based on obstacle positions and road geometry changes, avoiding the excessive data generation that would occur with full-path corridor construction. This partial generation approach reduces energy consumption while maintaining reliable safe navigation.
3Reliability
If comprehensive corridor data is generated to ensure safe navigation, then collision avoidance is improved, but processing cycles and computational load increase
Solution Approach 1:
The patent performs preliminary action by pre-calculating offset distances from the reference line to obstacles at segment boundaries and storing these as corridor constraints. Instead of performing complex real-time calculations during trajectory evaluation, the system prepares the corridor data structure in advance with pre-computed smallest total distance offsets. This preliminary preparation reduces real-time processing complexity while maintaining collision avoidance capability.
Solution Approach 2:
The patent changes parameters by using smallest total distance offsets as the defining parameter for corridor boundaries instead of using fixed width corridors or complex geometric constructions. This parameter change simplifies the corridor data structure from comprehensive geometric descriptions to concise offset distance values, reducing processing complexity while ensuring reliable collision avoidance through accurate obstacle distance representation.
Data Source
AI summary
The present disclosure is directed to generating vehicle motion corridors for use in generating autonomous vehicle paths. In particular, a computing system can access map data for a geographic area and sensor data for the geographic area around an autonomous vehicle. The computing system can identify, based on the map data and the sensor data, object data describing a position and a size of one or more objects in the geographic area of the autonomous vehicle. The computing system can access path data describing a nominal path through the geographic area. The computing system can determine a plurality of corridor segments associated with the nominal path. The computing system can generate a vehicle motion corridor by aggregating the plurality of corridor segments, wherein the vehicle motion corridor defines an area in which the autonomous vehicle can travel without colliding with the one or more objects.