AGV Trajectory Prediction Using ROI-Based Dynamic Refinement
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous ground vehicles face delays and synchronization issues due to high computational needs for object detection and mapping, which often exceed the available on-board computational capacity, impacting navigation efficiency.
Innovation Solution
A method and system that utilize two AI prediction models to predict and refine navigation trajectories by receiving Region of Interest (ROI) data before and after reaching a trajectory path, modifying attributes based on environmental data, and dynamically refining predictions to generate a final navigation trajectory, reducing computational power consumption and processing time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high computational capacity algorithms are used for object detection and mapping, then navigation accuracy and environmental understanding are improved, but processing time increases and synchronization issues occur
Solution Approach 1:
The patent segments the computational workload by dividing the trajectory determination into multiple stages: receiving ROI data from current location, receiving predicted attributes from future location, modifying attributes based on environmental data, and dynamically receiving second ROI data. This segmentation allows distributed processing across different time points and locations, reducing the computational burden at any single moment while maintaining overall navigation accuracy.
Solution Approach 2:
The system performs preliminary actions by receiving predicted attributes associated with future navigation trajectory before the AGV actually reaches that location. These predictions are generated in advance based on map data and environmental attributes, allowing the system to prepare navigation plans ahead of time rather than computing everything in real-time, thus reducing processing delays.
2Productivity
If high computational capacity is allocated on-board the AGV, then real-time navigation processing is improved, but hardware complexity and energy consumption increase
Solution Approach 1:
The patent introduces an intermediary communication system that transmits ROI data and predicted attributes between the current location and future location of the AGV. This intermediary mechanism allows computational tasks to be distributed and coordinated across different spatial and temporal points, reducing the need for high computational capacity concentrated on a single on-board platform while maintaining real-time processing capability.
Solution Approach 2:
The system dynamically adjusts the navigation trajectory by receiving second ROI data upon reaching the anticipated future location and refining the trajectory based on actual environmental conditions. This dynamic approach allows the system to perform computations adaptively rather than requiring all computations to be completed in advance with high on-board capacity, reducing hardware complexity requirements.
3Reliability
If comprehensive environmental data is collected and processed, then navigation reliability is improved, but computational power consumption increases
Solution Approach 1:
The patent applies local quality by focusing computational resources on Region of Interest (ROI) data rather than processing all environmental data uniformly. The system receives ROI data associated with upcoming trajectory paths and modifies predicted attributes based on environmental attributes within these specific regions of interest, thereby maintaining navigation reliability while reducing overall computational power consumption by concentrating processing efforts where they are most needed.
Data Source
AI summary
A method of determining a navigation trajectory for an autonomous ground vehicle (AGV) is disclosed. The method may include receiving first Region of Interest (ROI) data associated with an upcoming trajectory path, and receiving predicted attributes associated with a future navigation trajectory for the upcoming trajectory path. The predicted attributes are derived based on map for the upcoming trajectory path. The method may further include modifying the predicted attributes based on environmental attributes extracted from first ROI data to generate modified attributes, and dynamically receiving a second ROI data associated with the upcoming trajectory path upon reaching the upcoming trajectory path. The method may further include predicting dynamic attributes associated with an imminent navigation trajectory for the upcoming trajectory path based on the second ROI data, and refining the modified attributes based on the one or more dynamic attributes to generate a final navigation trajectory.