History-Corrected Lidar Trajectories for Reliable Automated Steering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for steering automated vehicles using offboard sensors face issues with grid cell state inadvertent switching due to temporary occlusions and signal quality loss, affecting trajectory computation times and reliability.
Innovation Solution
A computer-implemented method using 3D laser scanning Lidars to generate 2D occupancy grids, where cell states are revised based on historical data to compensate for temporary occlusions and signal alterations, reducing computational load by determining trajectories on 2D grids and utilizing simple arithmetic operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If grid cell states are determined based on perception signals from offboard sensors, then trajectory computation can be performed, but grid cell states may inadvertently switch due to temporary occlusions and signal quality loss, reducing reliability
Solution Approach 1:
The system performs preliminary actions by maintaining a history of grid cell states and using this historical information to predict and correct current cell states before trajectory computation. This allows the system to compensate for temporary occlusions and signal quality loss by relying on previously observed states, thereby maintaining trajectory reliability even when current perception signals are degraded.
Solution Approach 2:
The system implements feedback by comparing current grid cell states with historical states and using this comparison to correct inadvertent switching. The history of cell states serves as feedback information that helps identify and correct erroneous state changes caused by temporary occlusions, thus improving the reliability of trajectory computation.
2Speed
If frequent trajectory computations are performed at 5-20 hertz, then vehicle steering responsiveness is improved, but computational load increases due to grid revision requirements
Solution Approach 1:
The system extracts only the essential historical information needed for cell state correction, storing and processing only relevant past states rather than complete historical data. This extraction of necessary information reduces the computational burden while maintaining the ability to correct cell states at high frequencies.
Solution Approach 2:
The system changes parameters by using a simplified history-based correction approach that requires fewer computational resources. By modifying the cell state determination process to rely on historical data rather than complex real-time analysis, the system enables frequent computations at 5-20 hertz while reducing energy consumption.
3Measurement precision
If complete grid revision is performed to correct cell states, then trajectory accuracy is improved, but computation time increases
Solution Approach 1:
The system applies local quality by performing corrections only on specific grid cells that are suspected of having erroneous states, rather than revising the entire grid. This localized approach maintains measurement precision for critical cells while significantly reducing the overall computation time required for trajectory generation.
Solution Approach 2:
The system performs partial action by applying history-based correction only to grid cells where temporary occlusions or signal quality issues are detected, rather than uniformly revising all cells. This selective correction maintains accuracy where needed while minimizing unnecessary computational overhead.
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
The method stabilizes cell states over time, resulting in more reliable trajectories with reduced computational overhead, enabling efficient and secure steering of automated vehicles at high frequencies.
Implementation Method 1
3D laser scanning Lidars, which may be arranged as infrastructure-based Lidars
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
The invention is notably directed to a computer-implemented method of steering an automated vehicle in a designated area using a set of one or more offboard sensors. Each of these sensors is preferably a 3D laser scanning Lidar, e.g., an infrastructure-based Lidar. The method comprising repeatedly executing algorithmic iterations, wherein each iteration comprises obtaining (S30) a grid, performing (S200) a revision procedure to revise the grid, and determining (S90) a trajectory for the automated vehicle, based on the revised grid. The grid is obtained (S30) as a 2D occupancy grid of cells. This is achieved by determining a state of each cell in accordance with a perception of the one or more offboard sensors. The aim of the revision procedure (S200) is to revise the obtained grid. The grid is revised by correcting the state determined for each of one or more of the cells based on a history of such a cell. Eventually, the method determines (S90) a trajectory for the automated vehicle, based on the revised grid, and forwards (S100) the determined trajectory to a drive-by-wire system of the automated vehicle, to steer the latter. The invention is further directed to related systems and computer program products.