Autonomous Vehicle Trajectory Optimization Under Lateral Acceleration Constraints
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous driving systems face challenges in generating optimal longitudinal trajectories that balance safety, comfort, and time efficiency, particularly when navigating road shapes with curves and straight sections, as they struggle to effectively incorporate road shape constraints into motion planning.
Innovation Solution
A trajectory optimizer that uses nonlinear optimization techniques to generate planned autonomous driving vehicle states, considering road shape functions, maximal jerk, and maximal lateral acceleration, while minimizing cumulative jerk and achieving a target end position, utilizing an SL-coordinate system and quartic polynomial road shape functions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If the autonomous vehicle accelerates to high speed on straight road portions to improve time efficiency, then the travel time is reduced, but the vehicle must decelerate before curves to maintain safety and comfort, resulting in increased stopping and starting frequency
Solution Approach 1:
The trajectory optimizer performs preliminary planning by incorporating road shape information (curves and straight sections) into the optimization process before trajectory execution. The system pre-calculates optimal speed profiles that anticipate upcoming curves, allowing the vehicle to maintain higher speeds longer while still meeting safety requirements, thereby reducing overall travel time without excessive stopping and starting
Solution Approach 2:
The system dynamically adjusts the trajectory optimization based on real-time road shape characteristics. By making the trajectory planning adaptive to the specific road geometry (using road shape functions to describe curves and straight sections), the system can optimize speed profiles for each specific road segment, balancing time efficiency with safety requirements for curves and comfort for straight portions
2Reliability
If the autonomous vehicle decelerates early before curves to ensure safety and comfort, then passenger comfort is improved, but the vehicle loses valuable travel time that could be used for faster traversal
Solution Approach 1:
The system changes the optimization parameters by incorporating lateral acceleration constraints and road shape functions into the trajectory optimization. This allows the vehicle to maintain higher speeds approaching curves by carefully managing lateral acceleration within comfortable limits, rather than simply decelerating early. The parameter changes enable smoother, more efficient speed profiles that prioritize both comfort and time efficiency
Solution Approach 2:
The trajectory optimizer uses road shape information to pre-plan speed profiles that anticipate curve locations and characteristics. By preparing optimal speed trajectories in advance that consider both safety/comfort requirements and time efficiency, the system avoids last-minute deceleration while maintaining passenger comfort through smooth, pre-planned acceleration and deceleration patterns
3Manufacturing precision
If the trajectory planning incorporates detailed road shape constraints and lateral acceleration limits, then the quality of optimal trajectories is improved, but the computational complexity of the optimization problem increases
Solution Approach 1:
The system transforms the trajectory planning problem by changing parameters to include road shape functions and lateral acceleration constraints directly in the optimization formulation. This parameter transformation allows the incorporation of detailed road geometry information and comfort constraints while maintaining a structured optimization approach that can be solved efficiently using nonlinear optimization techniques
Solution Approach 2:
The trajectory optimizer acts as an intermediary that translates road shape constraints and lateral acceleration limits into optimized speed and acceleration profiles. By using road shape functions as intermediaries to describe the road geometry, the system can incorporate detailed road characteristics into the optimization without directly managing the complexity of raw road data, enabling precise trajectory generation through mathematical optimization
Data Source
AI summary
In one embodiment, a method, apparatus, and system for planning a trajectory for an autonomous driving vehicle (ADV) is disclosed. The operations comprise: receiving a plurality of optimization inputs, the plurality of optimization inputs comprising a trajectory time length, a time discretization resolution, an autonomous driving vehicle (ADV) starting state, a road shape function, a maximal jerk, and a maximal lateral acceleration; receiving a plurality of optimization constraints, the plurality of optimization constraints comprising constraints relating to the maximal jerk and the maximal lateral acceleration; receiving a cost function associated with an optimization objective, the cost function comprising a first term relating to cumulative jerk, a second term relating to an end longitudinal position, a third term relating to an end longitudinal speed, and a fourth term relating to an end longitudinal acceleration; generating a plurality of planned ADV states as optimization results with nonlinear optimization, wherein the optimization results minimize a value of the cost function; and generating control signals to control the ADV based on the plurality of planned ADV states.