Dynamic Occupancy Grid Collision Avoidance for LiDAR Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional algorithms for autonomous driving are impractical for complex routes due to the numerous decisions required, making them inefficient for vehicle navigation.
Innovation Solution
The use of a dynamic occupancy grid (DOG) to represent the environment, where grid cells are assigned probability density functions based on LiDAR data, allowing for the determination of time-to-collision (TTC) and object velocities, enabling collision avoidance maneuvers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If traditional algorithms are used for autonomous driving on complex routes, then the vehicle can navigate through the road network, but the system requires numerous decisions making the algorithm impractical and inefficient
Solution Approach 1:
The patent segments the complex navigation problem into discrete grid cells that cover the environment. Each grid cell independently represents a portion of space and can be evaluated for occupancy and collision risk separately. This segmentation allows the system to process navigation decisions in parallel across multiple grid cells rather than making sequential decisions through complex algorithms, thereby improving efficiency while reducing overall system complexity.
2Measurement precision
If the environment is represented at higher resolution to improve collision detection accuracy, then object tracking precision increases, but computational complexity increases
Solution Approach 1:
The environment is divided into discrete grid cells of appropriate resolution to achieve sufficient tracking precision without requiring excessively fine granularity. Each grid cell maintains independent occupancy and probability density function data, allowing the system to achieve accurate object tracking at manageable computational levels through parallel processing of segmented spatial units rather than treating the entire environment as a single complex computational problem.
Solution Approach 2:
Different grid cells can have different levels of detail and probability density allocations based on local requirements. Grid cells in areas with higher collision risk or object density can maintain higher resolution and more detailed probability distributions, while less critical areas use coarser representation. This local quality approach optimizes computational resources while maintaining necessary precision where it matters most.
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
Enhances navigation capabilities by tracking objects and free space at higher resolution with reduced computational complexity, effectively avoiding collisions through dynamic adjustments.
Implementation Method 1
receive light detection and ranging (LiDAR) data from one or more LiDARs of the vehicle
Data Source
AI summary
Methods for operating a vehicle in an environment include receiving light detection and ranging (LiDAR) data from a LiDAR of the vehicle. The LiDAR data represents objects located in the environment. A dynamic occupancy grid (DOG) is generated based on a semantic map. The DOG includes multiple grid cells. Each grid cell represents a portion of the environment. For each grid cell, a probability density function is generated based on the LiDAR data. The probability density function represents a probability that the portion of the environment represented by the grid cell is occupied by an object. A time-to-collision (TTC) of the vehicle and the object less than a threshold time is determined based on the probability density function. Responsive to determining that the TTC is less than the threshold time, a control circuit of the vehicle operates the vehicle to avoid a collision of the vehicle and the object.