Lidar Road Surface Feature Detection for Autonomous Vehicle Ride Comfort
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles (AVs) are unable to effectively detect and mitigate road surface features such as potholes, speed bumps, and utility access covers, which negatively impact ride quality for passengers.
Innovation Solution
AVs are equipped with a lidar sensor system and a road surface analysis component that uses neural networks and height maps to detect road surface features, allowing the vehicle to execute avoidance or mitigation maneuvers to improve ride quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If AVs use conventional sensor systems and control algorithms, then they can avoid sudden stops and starts, but they cannot detect road surface features that affect ride quality
Solution Approach 1:
The system segments the point cloud data into different components (road surface, objects, etc.) and specifically isolates road surface features for analysis. This segmentation enables the detection system to focus on relevant features while filtering out irrelevant data, solving the detection difficulty.
Solution Approach 2:
The system transitions from conventional 2D camera or radar detection to 3D point cloud analysis from lidar. This dimensional enhancement provides depth information and spatial context that enables reliable detection of road surface features like potholes and speed bumps that were previously undetectable.
2Reliability
If AVs execute avoidance maneuvers for road surface features, then ride quality improves, but travel time and route efficiency may decrease
Solution Approach 1:
The system performs preliminary detection and classification of road surface features before the vehicle reaches them. By identifying features in advance and planning avoidance maneuvers proactively, the system can execute smooth route adjustments without sudden reactive movements, maintaining both comfort and efficiency.
Solution Approach 2:
The system dynamically adjusts the avoidance strategy based on the type, size, and location of detected road surface features. Rather than applying a fixed avoidance rule, the system optimizes the maneuver in real-time, allowing for more efficient path planning that minimizes travel time while still ensuring passenger comfort.
3Measurement precision
If AVs use detailed point cloud analysis for road surface detection, then detection accuracy improves, but computational load and processing time increase
Solution Approach 1:
The system extracts only the relevant road surface points from the complete point cloud, separating them from other objects and elements in the environment. This extraction process reduces the data volume that requires detailed analysis while maintaining detection accuracy for the features of interest.
Solution Approach 2:
The system creates simplified representations or models of road surface features from the detailed point cloud data. These simplified models retain the essential characteristics needed for detection and classification while requiring less computational resources for processing and decision-making.
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 system enables AVs to effectively detect and respond to road surface features, enhancing passenger comfort by avoiding or mitigating the impact of these features, and updates map data for other AVs to improve overall route planning.
Implementation Method 1
a lidar sensor system that outputs lidar data based on sensor signals received from the at least one lidar sensor
Data Source
AI summary
An AV is described herein. The AV includes a lidar sensor system. The AV additionally includes a computing system that executes a road surface analysis component to determine, based upon lidar sensor data, whether a road surface feature is present on or in a roadway in a travel path of the AV. The AV can be configured to initiate a mitigation maneuver responsive to determining that the road surface feature is present. Performing the mitigation maneuver causes the AV to avoid the road surface feature or decelerate prior to reaching the road surface feature, thereby improving the apparent quality or comfort of the ride to a passenger of the AV.