Autonomous Vehicle Image-Space Trajectory Planning for Uncertain Depth
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating through environments with uncertain depth estimates, such as those with 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 planned path into the image space and adjusting it based on cost functions to minimize risk.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the autonomous vehicle navigates through areas with complex shapes like trees with intermittent foliage, then the vehicle can explore more environments, but the depth estimates become unreliable and collision risk increases
Solution Approach 1:
The image space is segmented into multiple regions based on depth estimation confidence levels. High-confidence regions are identified where depth estimates are reliable, while low-confidence regions are marked where depth estimates are unreliable. This segmentation allows the motion planning system to selectively navigate through high-confidence regions, avoiding low-confidence areas with complex shapes like trees with intermittent foliage, thereby maintaining both environmental exploration capability and navigation safety.
2Reliability
If the vehicle avoids regions with low confidence depth estimates, then collision risk is reduced, but the navigable area is constrained
Solution Approach 1:
The motion planning system dynamically adjusts the vehicle's trajectory by projecting the planned path into image space and identifying regions to avoid based on depth estimation confidence. The system continuously updates the avoidable region mask as new images are captured and processed, allowing the vehicle to adapt its navigation in real-time. This dynamic approach enables the vehicle to safely navigate through challenging environments by leveraging temporal information from sequential images while maintaining flexibility in path selection.
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.