Shared Object Mapping for Occluded Autonomous Vehicle Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles (AVs) face challenges in navigating areas where objects are outside their observable or perceivable range due to occlusion, atmospheric conditions, or sensor limitations, affecting their ability to predict behaviors and plan collision-free paths with confidence.
Innovation Solution
AVs share information about objects detected by other vehicles in the fleet through vehicle-to-vehicle communication or a remote joint map management system, using encoders to compress and timestamp the data, enabling better object localization, understanding, and prediction, even for objects outside the sensor range.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AVs rely solely on their own sensors to detect objects, then the device complexity is reduced, but the reliability of object detection deteriorates when objects are outside observable range
Solution Approach 1:
The patent combines sensor data from multiple autonomous vehicles to create a comprehensive object detection system. By merging observations from different vehicles, the system achieves more reliable object detection than any single vehicle could accomplish alone, particularly for objects that are occluded or outside the observable range of individual sensors.
Solution Approach 2:
The patent introduces a communication system as an intermediary that transmits sensor data and object information between autonomous vehicles. This intermediary enables vehicles to share detection results, allowing each vehicle to benefit from the observational capabilities of others without requiring direct physical connection to all sensors.
2Reliability
If AVs use vehicle-to-vehicle communication to share object information, then the reliability of path planning improves, but the loss of time for data processing and communication increases
Solution Approach 1:
The patent performs preliminary actions by having vehicles continuously share object information and maintain updated maps of the environment in advance of when path planning is needed. This pre-processing of environmental data ensures that when path planning occurs, the necessary object information is already available, reducing the time required for actual path computation.
Solution Approach 2:
The patent optimizes communication by transmitting only locally relevant object information and sensor data that is specific to each vehicle's area of interest. This selective data transmission reduces the overall volume of communication required while maintaining the reliability needed for accurate path planning in each vehicle's local context.
3Measurement precision
If AVs transmit detailed sensor data about detected objects, then the measurement precision of object information improves, but the quantity of data to be transmitted increases
Solution Approach 1:
The patent extracts only the essential and relevant object information from complete sensor data for transmission between vehicles. By identifying and transmitting only the critical attributes needed for path planning and collision avoidance, the system maintains measurement precision for decision-making while significantly reducing the volume of data that requires communication.
Solution Approach 2:
The patent segments object information into different levels of detail, transmitting comprehensive data only when necessary and using summarized or simplified representations for routine communication. This segmentation allows the system to maintain high measurement precision when needed while reducing overall data transmission volume through selective use of detailed versus simplified information.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Autonomous vehicles (AVs) utilize perception and understanding of objects on the road to predict behaviors of the objects, and to plan a trajectory for the vehicle. In some scenarios, an AV may benefit from having information about an object that is not within a perceivable area of the sensors of the AV. Another AV in the area that has the object within a perceivable area of the sensors of the other AV may share information with the AV. Rich information about the object determined by the other AV can be compressed using an encoder and transferred efficiently to the AV for inclusion in a temporal map that combines locally determined object information and transferred object information determined by other AV(s). The temporal map may be used in one or more parts of the software stack of the AV.