Robotic Vehicle Motion Planning for Static and Dynamic Obstacle Scoring
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous robotic vehicles face challenges in navigating through environments with both static and dynamic objects, as existing methods struggle to accurately predict the movement of dynamic objects and avoid collisions effectively.
Innovation Solution
The implementation of a motion planning module that uses two separate models: a prediction model to account for dynamic objects and an analytical model to handle static objects, allowing for more accurate scoring of possible actions and improved navigation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single model is used to handle both dynamic and static objects, then the device complexity is reduced, but the measurement precision and reliability of collision avoidance deteriorate
Solution Approach 1:
The motion planning module is segmented into two separate models: a prediction model for dynamic objects and an analytical model for static objects. This segmentation allows each model to be optimized for its specific object type, improving prediction accuracy for dynamic objects using machine learning while ensuring precise collision avoidance for static objects using geometric calculations, without requiring a single overly complex unified model
2Adaptability or versatility
If a prediction model is used for dynamic objects, then the adaptability to unpredictable movements is improved, but the reliability of collision avoidance deteriorates due to inherent prediction uncertainties
Solution Approach 1:
The system introduces an intermediary analytical model that acts as a reliability safeguard for the prediction model. The analytical model uses deterministic geometric calculations to verify predicted trajectories and identify certain collision risks with static objects, providing a reliable fallback mechanism that compensates for the inherent uncertainties in dynamic object predictions while maintaining adaptability to unpredictable movements
3Ease of operation
If equal weights are given to both dynamic and static object avoidance scores, then the objectivity is maintained, but the harmful factors increase due to potential collisions with dynamic objects causing injury
Solution Approach 1:
The scoring system applies local quality by assigning different weights to scores from the prediction model and analytical model based on the specific context. The prediction model scores for dynamic objects are given higher weight (e.g., 0.7) compared to analytical model scores for static objects (e.g., 0.3), reflecting the greater harm potential of dynamic object collisions. This contextual weighting maintains objectivity by being transparent about the different harm levels while prioritizing safety
Data Source
AI summary
A method of operating a robotic vehicle is provided. The method includes generating, using a prediction model, first scores, each of the first scores associated with a possible action of the robotic vehicle. The prediction model generates the first scores based, at least in part, on a predicted probability of the robotic vehicle encountering a dynamic object. The method further includes generating, using an analytical model, second scores, each of the second scores associated with a possible action of the robotic vehicle. The analytical model generates the second scores based, at least in part, on the information on the static objects. The method also includes combining the first scores with the second scores to generate combined scores, and selecting an action for the robotic vehicle based, at least in part, on the combined scores. A motion planning module and a robotic vehicle implementing the method are also disclosed.