Automated Vehicle Trajectory Control in Dynamic Environments
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Controlling automated vehicles to accurately follow dynamic reference trajectories is challenging due to issues like conflicting terms, model mismatch, computational delays, and control delays, which can lead to excessive divergence from the normal state trajectory, impeding effective operation in dynamically changing environments.
Innovation Solution
A computer-implemented method and system that receives image data and LiDAR data to process a planned trajectory for an automated vehicle. This involves executing a predictive optimal control problem to determine control signals that enable the vehicle to follow the planned trajectory accurately within dynamic environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional control methods are used to follow dynamic reference trajectories, then the control system is simpler, but the vehicle experiences excessive divergence from the normal state trajectory due to conflicting terms, model mismatch, computational delays, and control delays
Solution Approach 1:
The control system dynamically adjusts control inputs based on real-time vehicle state and trajectory deviations. The method continuously solves optimal control problems using current sensor data and updated vehicle models, allowing the system to adapt to changing conditions and maintain accurate trajectory following without requiring excessive computational complexity in the control architecture
Solution Approach 2:
The system performs predictive optimal control by solving the optimal control problem in advance for a prediction horizon. The method calculates future control inputs based on predicted vehicle states and trajectory requirements, allowing the system to proactively compensate for model mismatch and computational delays before they cause significant trajectory divergence
2Manufacturing precision
If predictive optimal control is executed to determine control signals, then trajectory following accuracy is improved, but computational delays increase
Solution Approach 1:
The optimal control problem is solved periodically at discrete time steps with a defined sampling rate. The system executes the predictive control algorithm at regular intervals, updating control signals based on the latest sensor measurements and vehicle state, which balances computational load with the need for accurate real-time control
Solution Approach 2:
The prediction horizon is divided into discrete time steps or segments. The optimal control problem is solved for each segment independently, allowing the computational task to be broken down into manageable portions that can be processed efficiently without requiring excessive computational resources at any single moment
3Adaptability or versatility
If the vehicle operates in dynamically changing environments with obstacles, then adaptability is improved, but trajectory divergence increases due to conflicting control terms and model mismatch
Solution Approach 1:
The control system continuously monitors vehicle state through sensors (cameras, LiDAR, inertial measurement units) and compares actual position with desired trajectory. This feedback loop allows the system to detect deviations caused by dynamic environmental changes and adjust control inputs accordingly, compensating for model mismatch and maintaining trajectory accuracy in changing conditions
Solution Approach 2:
The system adapts control parameters and vehicle model parameters based on observed environmental conditions and vehicle behavior. By dynamically adjusting parameters such as control gains, prediction horizon, and model characteristics, the system maintains accurate trajectory following across diverse and changing operational environments without requiring a completely different control approach for each scenario
Data Source
AI summary
A system and method for providing accurate trajectory following for automated vehicles in dynamic environments that include receiving image data and LiDAR data associated with a dynamic environment of a vehicle. The system and method also include processing a planned trajectory of the vehicle that is based on an analysis of the image data and LiDAR data. The system and method further include communicating control signals associated with following the planned trajectory to autonomously control the vehicle to follow the planned trajectory to navigate within the dynamic environment to reach a goal.