Vehicle Obstacle Probability Calculation Using Multi-Sensor Fusion
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional technologies for calculating obstacle presence probability around a vehicle using sensors, such as Lidar and millimeter wave radar, face challenges in reliability due to incomplete data acquisition, leading to insufficient accuracy in determining obstacle presence in blind spots and travelable areas.
Innovation Solution
An information processing apparatus that acquires positional information from multiple sensors, calculates obstacle presence probability using ray casting and time-series integration, and records non-measurement information to determine a final probability, enhancing reliability by combining data from different sensors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional single-sensor or simple probability calculation methods are used, then the calculation process is simple, but the reliability of obstacle presence probability is insufficient
Solution Approach 1:
The patent combines data from multiple sensors (laser sensor, millimeter wave radar, camera) to calculate obstacle presence probability. By merging information from different sensing modalities, the system achieves higher reliability in determining obstacle presence, especially in blind spots where single sensors fail. The probability integration mechanism fuses results from multiple sensors to produce a more reliable final probability value.
Solution Approach 2:
The patent introduces an intermediary processing layer that calculates obstacle presence probability based on positional information from multiple sensors. This intermediary probability calculation mechanism acts as a mediator between raw sensor data and final obstacle detection decisions, improving reliability by synthesizing information from multiple sources before making definitive obstacle presence determinations.
2Measurement precision
If positional information is not acquired for certain areas (blind spots), then sensor coverage is limited, but the obstacle presence probability cannot be determined accurately
Solution Approach 1:
The patent merges data from multiple sensors with different characteristics and coverage areas. By combining information from laser sensors, millimeter wave radar, and cameras, the system compensates for blind spots in individual sensors. Areas not covered by one sensor may be detected by another, and the probability calculation integrates these partial observations to determine overall obstacle presence even in previously blind areas.
Solution Approach 2:
The patent uses partial observations from multiple sensors to infer obstacle presence in areas where no single sensor provides complete information. By accumulating partial detection results from different sensors and time points, the system can determine obstacle presence probability in blind spots through aggregated evidence, even when no single sensor fully covers the area.
3Measurement precision
If obstacle presence probability is calculated without considering multiple sensor data, then the processing is faster, but the accuracy in blind spots and travelable areas is insufficient
Solution Approach 1:
The patent segments the surrounding area into multiple regions (blind spots, travelable areas, obstacle presence areas) and calculates obstacle presence probability separately for each segment based on sensor coverage and detection results. This segmentation approach allows targeted probability calculation for different area types, improving accuracy in distinguishing blind spots from travelable areas while maintaining processing efficiency through region-specific algorithms.
Data Source
AI summary
An information processing apparatus according to one embodiment includes a memory having computer executable components stored therein; and processing circuitry communicatively coupled to the memory. The processing circuitry is configured to: acquire, for each of a plurality of sensors installed in a vehicle, positional information of an object present around the vehicle measured by the sensor; calculate a probability that the object is present for each of a plurality of areas obtained by dividing surroundings of the vehicle based on the positional information measured by the sensors; record non-measurement information indicating that the positional information was not obtained for an area corresponding to a direction in which the positional information was not obtained for each of the sensors; and determine a final probability that the object is present based on the probability calculated for each of the sensors and the non-measurement information.