Obstacle Representation Using SLT Constraints for AV Trajectory Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for autonomous vehicle route planning face challenges in efficiently generating constraints for dynamic tracks, leading to increased computational complexity and reduced accuracy in obstacle avoidance.
Innovation Solution
The implementation of a system that uses sensor data to determine dynamic tracks of obstacles, generates obstacle data, and applies station and lateral constraints to optimize autonomous vehicle trajectories, thereby improving computational efficiency and accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current systems generate constraints for dynamic tracks using traditional methods, then obstacle avoidance is achieved, but computational complexity increases and accuracy decreases
Solution Approach 1:
The patent segments the continuous dynamic track into discrete station constraints and lateral constraints. By dividing the obstacle representation into discrete spatial and temporal components, the system simplifies computational processing while maintaining accuracy in obstacle avoidance planning.
Solution Approach 2:
The patent transforms the dynamic track representation by adding the time dimension to create Station-Lateral-Time (SLT) constraints. This dimensional transformation converts a complex continuous spatial problem into a structured spatio-temporal framework, improving both computational efficiency and representation accuracy.
2Productivity
If traditional obstacle representation methods are used, then basic trajectory planning is possible, but computational efficiency is reduced
Solution Approach 1:
The patent performs preliminary action by pre-defining the structure of SLT constraints based on station and lateral components. This pre-structuring of constraint generation reduces real-time computational burden, improving computational efficiency and reducing time loss during trajectory planning.
Solution Approach 2:
The patent changes parameters by representing obstacles in terms of discrete station constraints and lateral constraints rather than continuous spatial models. This parameter transformation simplifies the mathematical operations required for trajectory optimization, significantly improving computational efficiency.
Data Source
AI summary
Provided are methods for obstacle representation, which can include obtaining sensor data, determining a dynamic associated with an agent, generating obstacle data, and generating constraints based on obstacle data. Some methods described also include providing data to cause operation of an autonomous vehicle. Systems and computer program products are also provided.