Vehicle Trajectory Planning Using Dynamic Occupancy Grids
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automatic driving vehicles face challenges in navigating dynamic traffic conditions, as existing technologies struggle to effectively perceive hazards and generate trajectories that avoid obstacles while ensuring safety and maximizing passenger utility.
Innovation Solution
The proposed solution involves a method and apparatus that utilize a dynamic occupancy grid and sensor fusion to detect space occupation and determine a trajectory of motion within a predetermined region, integrating perception and navigation skills to avoid hazards and optimize passenger routes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If bounding box approach is used to detect obstacles, then object detection is simplified, but it fails to detect large objects like buildings and fails to support information fusion from multiple sensors
Solution Approach 1:
The patent segments the environment into a grid of occupancy cells rather than attempting to detect complete objects with bounding boxes. Each cell independently represents occupancy probability, allowing the system to handle large objects like buildings by marking multiple adjacent cells as occupied without requiring a single bounding box to encompass the entire structure.
Solution Approach 2:
The patent merges information from multiple sensors (lidar, radar, cameras) by fusing their occupancy probability maps into a unified dynamic occupancy grid. This combination allows the system to overcome the limitations of individual sensors and support multi-sensor information fusion, addressing the bounding box approach's failure in this area.
2Ease of operation
If generic navigation direction is provided, then navigation simplicity is maintained, but the system fails to avoid hazards on the road
Solution Approach 1:
The patent transforms static navigation directions into dynamic trajectories by continuously updating the trajectory based on the dynamic occupancy grid. The trajectory is not a fixed path but adapts in real-time as obstacles move or appear, allowing the vehicle to avoid hazards while maintaining navigation toward the destination. This dynamic adjustment resolves the contradiction between simple navigation and safe hazard avoidance.
3Reliability
If dynamic occupancy grid is used to model environment, then information fusion from multiple sensors is enabled and large objects can be detected, but computational complexity increases
Solution Approach 1:
By segmenting the environment into a grid of cells, the patent simplifies the representation of complex scenes. Instead of processing complete object models from multiple sensors, the system only needs to determine occupancy probability for each cell, reducing computational complexity while maintaining reliable hazard detection including large objects like buildings.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method of determining a trajectory of motion of a vehicle in a predetermined region, wherein the predetermined region includes a plurality of sub-regions, the method being executed by one or more processors, the method including determining an occupancy hypothesis of the predetermined region, wherein the occupancy hypothesis indicates occupied sub-regions of the plurality of sub-regions and non-occupied sub-regions of the plurality of sub-regions; determining a utility value for each sub-region of the predetermined region; determining the trajectory of motion which crosses at least one sub-region of the non-occupied sub-regions, based on a function of the utility values of the least one sub-region of the non-occupied sub-regions crossed by the trajectory of motion and by maximizing a utility of motion of the vehicle, wherein the utility of motion of the vehicle is indicated by a function of the utility values of the sub-regions crossed by the trajectory of motion.