Autonomous Intersection Navigation via Predictive Obstacle Convergence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Automatic driving vehicles face challenges in accurately determining the theoretical location of obstacles in complex traffic environments, leading to potential safety risks due to errors in convergence location information, which can result in collisions.
Innovation Solution
A method for automatic driving at intersections that involves determining initial and current location information of obstacles, correcting convergence location information using orientation and angular speed, and selecting a target travelling plan to ensure safe navigation, employing Kalman filtering and game theory to improve accuracy and safety.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the automatic driving vehicle uses basic travelling parameters (location, speed, acceleration) to determine the theoretical location of obstacles, then the calculation process is simple and fast, but the accuracy of convergence location information is insufficient leading to safety risks
Solution Approach 1:
The patent applies preliminary action by predicting the theoretical location of obstacles in advance before actual convergence occurs. The system uses current location, speed, and acceleration data to calculate where obstacles will be at future time points, allowing the vehicle to plan trajectories proactively rather than reactively. This predictive approach improves accuracy while maintaining computational efficiency.
Solution Approach 2:
The patent introduces an intermediary computational layer that processes basic travelling parameters through mathematical models to derive more accurate convergence location information. Instead of directly using raw sensor data, the system uses intermediate calculations involving time predictions and trajectory projections to bridge the gap between simple measurements and accurate convergence points.
2Measurement precision
If the vehicle determines theoretical location of obstacles using complex algorithms, then the accuracy of convergence location information is improved, but the real-time processing capability and response speed are reduced
Solution Approach 1:
The system performs preliminary calculations of obstacle trajectories using current motion parameters before convergence events occur. By pre-computing theoretical locations based on current speed and acceleration, the system avoids complex real-time calculations during critical moments, maintaining both accuracy and speed.
Solution Approach 2:
The patent applies dynamics by continuously updating the theoretical location predictions as new sensor data becomes available. The system dynamically adjusts obstacle trajectory predictions based on changing speed and acceleration measurements, allowing accurate real-time tracking without requiring overly complex static models.
3Speed
If the vehicle uses simplified methods to determine obstacle location, then the processing speed is fast, but the safety is compromised due to errors in convergence location information
Solution Approach 1:
The system uses preliminary action by calculating theoretical obstacle locations in advance based on current motion parameters. This allows the vehicle to identify potential convergence points and plan safe trajectories before reaching them, maintaining high processing speed while ensuring safety through proactive prediction rather than reactive correction.
Solution Approach 2:
The patent implements feedback mechanisms where the actual positions of obstacles are continuously compared against predicted theoretical locations. This feedback loop allows the system to verify the accuracy of its predictions and adjust its travelling plan accordingly, ensuring safety while maintaining efficient processing speeds.
Data Source
AI summary
A method for automatic driving at an intersection, an electronic device, storage medium, and an automatic driving vehicle, which relate to a field of a data processing technology, in particular to a field of automatic driving. The method includes: determining a first initial convergence location information between an obstacle and a vehicle, a current location information of the obstacle, and an orientation information of the obstacle; determining a target convergence location information between the obstacle and the vehicle according to the first initial convergence location information, the current location information of the obstacle and the orientation information of the obstacle; determining a target travelling plan from a plurality of candidate travelling plans for the vehicle according to the target convergence location information and a current travelling parameter of the obstacle; and controlling the automatic driving of the vehicle according to the target travelling plan.