Autonomous Vehicle Trajectory Optimization via Lateral Offset Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in generating safe and efficient trajectories that account for dynamic environmental factors, such as moving objects and changing road conditions, which existing systems often fail to address effectively.
Innovation Solution
A computer-implemented method that uses sensor data to generate multiple candidate trajectories for an autonomous vehicle, including velocity and offset profiles, which are evaluated for flatness criteria and cost functions to ensure safety and efficiency, allowing the vehicle to dynamically adjust its path to avoid obstacles and maintain speed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple candidate trajectories are generated and evaluated using flatness criteria and cost functions, then trajectory safety and efficiency are improved, but computational complexity and processing time increase
Solution Approach 1:
The system performs preliminary generation of multiple candidate trajectories using offset profiles before evaluation. By pre-generating trajectories with varying lateral offsets from the initial path, the system prepares multiple safety options in advance, allowing subsequent evaluation to select the optimal safe trajectory without real-time computational burden during critical decision moments.
Solution Approach 2:
The trajectory generation process is segmented into distinct components: initial path planning, offset profile generation, velocity profile determination, and cost function evaluation. This segmentation allows each component to be optimized independently and processed in stages, reducing the computational complexity of the overall system while maintaining comprehensive safety evaluation.
2Adaptability or versatility
If lateral offset profiles are used to generate multiple trajectories, then adaptability to dynamic environmental factors is improved, but trajectory evaluation and selection complexity increases
Solution Approach 1:
The system uses dynamic offset profiles that can be adjusted based on real-time environmental conditions detected by sensors. The lateral offset values in the profiles are not fixed but can be modified according to detected objects, road conditions, and traffic patterns, enabling the trajectory generation to adapt dynamically while maintaining a structured evaluation framework.
Solution Approach 2:
The system changes key parameters such as lateral offset values and velocity profiles to generate diverse candidate trajectories. By systematically varying these parameters around the initial path, the system creates multiple adaptable trajectories that can respond to environmental changes without requiring complete re-planning, thus managing evaluation complexity.
3Stability of the object's composition
If flatness criteria are applied to velocity and offset profiles, then motion smoothness and comfort are improved, but trajectory generation constraints increase
Solution Approach 1:
The system applies flatness criteria as preliminary constraints during trajectory generation to prevent harsh motions before they occur. By enforcing differential flatness conditions on velocity and offset profiles during the generation phase, the system ensures smooth motion characteristics are built into the candidate trajectories, avoiding the need for corrective smoothing later and reducing overall system complexity.
Data Source
AI summary
The present disclosure is directed generating candidate trajectories and selecting one of them to be implemented. In particular, a computing system can obtain an initial travel path for an autonomous vehicle. The computing system can obtain sensor data describing objects within an environment of the autonomous vehicle. The computing system can generate a plurality of trajectories for the autonomous vehicle based on the sensor data and the initial travel path. The computing system can determine whether the initial travel path, an offset profile, and a velocity profile meet flatness criteria. In response to determining that the initial travel path, the offset profile, and the velocity profile meet the flatness criteria, the computing system can combine the initial travel path, the offset profile, and the velocity profile into the respective trajectory. The computing system can determine a trajectory from the plurality of trajectories.