Occupancy Grid Mapping With Side Information for False-Positive Reduction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional occupancy grid mapping techniques rely solely on data from a single time-of-flight transceiver system, failing to exploit features like sparsity of occupancy or clustering of occupied cells, leading to inefficiencies and high false positive rates in obstacle detection.
Innovation Solution
An automotive system that utilizes side information such as camera images, previously generated OGMs, and digital maps in addition to primary ToF transceiver data for occupancy grid mapping, employing Sparse Bayesian Learning (SBL) or Bayesian Generalized Kernel (BGK) models to enhance detection accuracy and reduce false positives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional occupancy grid mapping techniques are used with single ToF transceiver data, then the system complexity is low, but the detection accuracy and reliability are poor with high false positive rates
Solution Approach 1:
The patent combines multiple data sources including ToF transceiver data, camera images, radar data, and previously generated occupancy grid maps into a unified processing system. This merging of multiple data streams enables the system to leverage complementary information from different sensors, improving obstacle detection accuracy and reducing false positives while maintaining manageable system complexity through integrated processing architecture
Solution Approach 2:
The processing system is designed to handle multiple types of data from different sensor modalities (ToF, camera, radar) and previously generated maps within a single unified framework. This multi-functional approach allows the system to process heterogeneous data types using common algorithms and processing pipelines, improving reliability without proportionally increasing system complexity
2Measurement precision
If conventional occupancy grid mapping techniques are used, then the processing time is short, but the false positive rate is high and detection precision is low
Solution Approach 1:
The system performs preliminary processing by generating and storing occupancy grid maps from previous time steps, which are then used as input for current frame processing. This preliminary action allows the system to leverage historical information and reduce computational complexity during real-time processing, improving detection precision without significant time penalty
Solution Approach 2:
The system uses previously generated occupancy grid maps and camera images as feedback inputs to refine current obstacle detection. This feedback mechanism allows the system to correct false positives from previous frames and improve detection precision by continuously learning from historical data while maintaining efficient real-time processing
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure relates to systems and methods for occupancy grid mapping. In one or more embodiments, a system includes a detection and ranging system configured to transmit signals, receive reflected signals corresponding to reflections of the transmitted signals by objects in an environment around the detection and ranging system, and generate point cloud data indicating positions of the objects, computer-readable memory configured to store side information, which can one or more digital maps, images of the environment, or previously generated occupancy grid maps, and processing circuitry configured to receive the point cloud data from the detection and ranging system, receive the side information from the computer-readable memory, determine hyperparameters for a mapping model based on the side information, and process the point cloud data using the mapping model using the hyperparameters to generate an occupancy grid map of the environment.