Image-Space Trajectory Planning for Uncertain Depth Regions
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating through environments with uncertain depth estimates, particularly due to complex shapes like trees with intermittent foliage, which can lead to unreliable depth measurements and increased collision risks.
Innovation Solution
The implementation of image space motion planning techniques that identify regions with low confidence depth estimates and associate them with higher collision risks, optimizing the vehicle's trajectory to avoid these areas by projecting the 3D trajectory into the image space and adjusting the path to minimize risk, using cost functions and machine learning to assess danger and uncertainty.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If visual odometry is used to estimate position and orientation based on captured images, then the autonomous vehicle can navigate using image data, but depth estimation reliability deteriorates in regions with complex shapes like trees with intermittent foliage
Solution Approach 1:
The patent divides the image into multiple depth map layers (first depth map and second depth map) with different confidence levels. Regions with complex shapes like trees are segmented and identified as having low confidence depth estimates, allowing the system to handle reliable and unreliable regions differently in motion planning
Solution Approach 2:
The patent introduces an intermediary confidence metric that mediates between the captured image data and motion planning decisions. This confidence information acts as a bridge, allowing the system to account for depth estimation reliability without requiring perfect depth data for all regions
2Productivity
If the autonomous vehicle navigates through regions with uncertain depth estimates, then coverage and exploration are improved, but collision risk increases
Solution Approach 1:
The patent performs preliminary identification of low confidence depth estimate regions before final motion planning. By pre-segmenting unreliable regions and associating them with higher collision risks, the system can proactively adjust trajectories to avoid these areas while maintaining overall navigation coverage
Solution Approach 2:
The patent changes the risk parameter assignment dynamically based on depth map confidence. Regions with low confidence depth estimates are assigned higher collision risk parameters, which then influence motion planning to avoid these regions, effectively adjusting navigation behavior based on data reliability
3Speed
If traditional motion planning is used without considering depth confidence, then planning speed is maintained, but safety deteriorates due to unreliable depth measurements
Solution Approach 1:
The patent applies partial action by considering only the confidence information for motion planning rather than reprocessing all image data. By using pre-computed confidence metrics from depth map comparison, the system adds safety checks without requiring complete replanning from scratch, maintaining planning speed while improving safety
Data Source
AI summary
An autonomous vehicle that is equipped with image capture devices can use information gathered from the image capture devices to plan a future three-dimensional (3D) trajectory through a physical environment. To this end, a technique is described for image-space based motion planning. In an embodiment, a planned 3D trajectory is projected into an image-space of an image captured by the autonomous vehicle. The planned 3D trajectory is then optimized according to a cost function derived from information (e.g., depth estimates) in the captured image. The cost function associates higher cost values with identified regions of the captured image that are associated with areas of the physical environment into which travel is risky or otherwise undesirable. The autonomous vehicle is thereby encouraged to avoid these areas while satisfying other motion planning objectives.