Spatio-Temporal Motion Planning for Smooth Autonomous Trajectories
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing motion planning systems for autonomous vehicles primarily optimize trajectories in the ST and LT frames, neglecting the SL frame, which can result in defects such as directional oscillation and large curvatures, leading to suboptimal trajectory planning that may not ensure smooth and comfortable vehicle operation.
Innovation Solution
The method involves generating a cost function with upper-bound cost terms that approximate the SL frame costs, allowing for optimization in the SL frame using quadratic programming solvers, thereby addressing the optimization gap in the SL frame and improving trajectory planning objectives like maintaining closeness to a reference path and minimizing lateral acceleration and directional oscillation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If motion planning optimizes only in ST and LT frames, then computational simplicity is maintained, but trajectory quality deteriorates with directional oscillation and large curvatures
Solution Approach 1:
The patent extends the optimization from two separate 2D frames (ST and LT) to a unified 3D spatio-temporal framework by incorporating the SL frame dimension. This dimensional expansion allows simultaneous optimization across all three spatial-temporal dimensions, eliminating directional oscillation and large curvatures while maintaining computational tractability through efficient algorithm design.
2Productivity
If motion planning neglects the SL frame optimization, then computational efficiency is maintained, but vehicle comfort and safety deteriorate due to uncontrolled lateral acceleration
Solution Approach 1:
The patent merges the previously separate ST and LT frame optimizations into a unified spatio-temporal optimization framework that simultaneously considers all three dimensions (SL, ST, LT). This integration ensures that lateral acceleration and directional oscillation are controlled while maintaining computational efficiency through a coordinated optimization approach rather than separate sequential optimizations.
Data Source
AI summary
Systems, methods and computer-readable media for spatio-temporal motion planning, including: receiving data defining a drivable area within a spatio-temporal space; generating a cost function to be minimized that includes one or more upper-bound cost terms, each upper-bound cost term approximating the upper-bound of a cost term for the trajectory for a spatial frame of the spatio-temporal space, each upper-bound cost term being expressed as one or more longitudinal-temporal cost terms and one or more lateral-temporal cost terms for the trajectory; and further cost terms for the trajectory for the spatio-temporal frames; computing, based on the constraints and cost function, a planned trajectory through the drivable area, the planned trajectory directory being optimized with respect to both spatial frame and the spatio-temporal frames. Optimizing the planned trajectory in the spatial frame in addition to the spatio-temporal frames can enable planning objectives for the spatial frame to be optimized, for example maintaining closeness to a reference path and minimizing lateral acceleration and directional oscillation.