Autonomous Vehicle Trajectory-Based Maneuvering Control Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous driving systems face challenges in optimizing manoeuvring controller configurations to balance control accuracy and vehicle occupant comfort across diverse driving situations, often requiring external sensor data and high-definition maps.
Innovation Solution
A control system that determines manoeuvring control configurations based on trajectory characteristics and vehicle dynamics, allowing internal and rapid adaptation without relying on external sensors, and uses an inference engine to classify driving situations for optimal actuator control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If the manoeuvring controller uses a fixed configuration, then the system complexity is reduced, but the control accuracy and comfort cannot be optimized for different driving situations
Solution Approach 1:
The patent implements dynamic adaptation by enabling the manoeuvring controller to automatically adjust its configuration parameters in real-time based on the analyzed trajectory characteristics, transforming a static fixed-configuration system into a dynamic adaptive system that optimizes control accuracy and comfort for each specific driving situation
Solution Approach 2:
The system changes controller parameters (such as control horizon, tuning parameters, or calculation speed) based on trajectory characteristics like curvature, speed, and yaw angle, allowing the same controller hardware to exhibit different behavioral characteristics suited to various driving scenarios without increasing physical system complexity
2Reliability
If the control system relies on external sensor data and high-definition maps, then the driving situation awareness is improved, but the system complexity and data processing requirements increase
Solution Approach 1:
The patent extracts and utilizes only the necessary trajectory characteristics from the planned local trajectory that are already available within the motion controller, eliminating the need to integrate and process additional external sensor data and high-definition map information, thus reducing system complexity while maintaining reliable driving situation classification
Solution Approach 2:
The motion controller performs self-analysis by examining its own planned trajectory characteristics to determine the appropriate manoeuvring control configuration, making the system self-sufficient without requiring external data sources, thereby reducing overall system complexity while maintaining accurate driving situation awareness
3Speed
If the manoeuvring controller increases calculation speed, then the real-time control performance is improved, but the control accuracy may be compromised
Solution Approach 1:
The system dynamically adjusts the calculation speed and control horizon of the manoeuvring controller based on the driving situation class determined from trajectory characteristics, allowing high-speed operation in simple scenarios and high-precision calculation in complex scenarios, thus resolving the trade-off between speed and accuracy
Solution Approach 2:
The controller changes its operational parameters such as control horizon length and calculation frequency according to the analyzed trajectory characteristics, enabling it to operate at high speed with reduced precision for straight-path driving while switching to higher precision modes for curved or complex trajectories
Data Source
AI summary
There is provided a control system (200), a method (700) and computer software (208) for controlling autonomous driving of a vehicle (1). The control system (200) comprises one or more controllers (201). The control system (200) is configured to: obtain information (702) indicative of one or more trajectory characteristics associated with a planned local trajectory (4, 5) of the vehicle (1); and determine (706) a manoeuvring control configuration in dependence on the one or more trajectory characteristics, wherein the manoeuvring control configuration is configured to control autonomous manoeuvring actuations of the vehicle (1) associated with following the planned local trajectory.