Multi-LiDAR Occupancy Mapping for Dynamic Obstacle Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional camera-based methods for occupancy mapping in automated driving are not robust enough to detect arbitrary obstacles and require expensive training to estimate the velocity of moving obstacles, while static occupancy maps only provide position information, lacking the necessary dynamic data for safe and smooth online operation of automated vehicles.
Innovation Solution
A computer-implemented method using LiDAR data from multiple sensors to create online multi-LiDAR dynamic occupancy maps, processing region of interest grids to compute static and dynamic occupancy maps, and utilizing phase congruency to segment dynamic and static objects, enabling control of the ego vehicle based on the dynamic occupancy map.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If camera-based methods are used for occupancy mapping, then the system can detect obstacles, but the robustness is insufficient and expensive training is required to estimate velocity of moving obstacles
Solution Approach 1:
The patent replaces camera-based optical detection with LiDAR-based laser ranging technology. LiDAR sensors emit laser beams and measure the time of flight to detect obstacles, providing direct depth information without requiring complex image processing or training. This substitution of detection mechanism fundamentally improves robustness while eliminating the need for expensive velocity estimation training.
Solution Approach 2:
The patent creates a unified occupancy mapping system that simultaneously detects both static and dynamic obstacles using LiDAR data. By processing point cloud data from multiple LiDAR sensors through a common pipeline that generates both static and dynamic occupancy maps, the system achieves multi-functionality in obstacle detection without requiring separate specialized models for different obstacle types.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach provides robust detection and estimation of obstacle velocities, enhancing the safety and smooth operation of automated vehicles by accurately differentiating and tracking dynamic and static objects in the environment.
Implementation Method 1
receiving LiDAR data from each of a plurality of LiDAR sensors
Data Source
AI summary
A system and method for providing online multi-LiDAR dynamic occupancy mapping that include receiving LiDAR data from each of a plurality of LiDAR sensors. The system and method also include processing a region of interest grid to compute a static occupancy map of a surrounding environment of the ego vehicle and processing a dynamic occupancy map. The system and method further include controlling the ego vehicle to be operated based on the dynamic occupancy map.