Autonomous Vehicle Basis Paths for Lane Change Motion Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing autonomous vehicle technologies face challenges in efficiently generating motion paths that consider drivability constraints and environmental awareness, particularly in navigating lane changes and obstacle avoidance.
Innovation Solution
A vehicle computing system generates basis paths by accessing nominal paths, identifying lane change regions, and evaluating candidate trajectories based on drivability constraints, using sensor data and map information to plan safe and efficient lane transitions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional path planning methods are used for autonomous vehicles, then the system structure is simple, but the planning efficiency and safety are insufficient for complex urban environments
Solution Approach 1:
The patent segments the path planning system into multiple independent modules: basis path generation module, motion constraint module, and optimization module. Each module handles specific aspects of path planning (generating candidate paths, applying motion constraints, optimizing paths), allowing the complex planning task to be divided into manageable components that can be processed independently and efficiently
Solution Approach 2:
The patent introduces basis paths as intermediary elements between the environment map and the final motion plan. These basis paths serve as pre-computed candidate trajectories that capture the essential geometry of the environment, acting as a mediator that simplifies the subsequent optimization process while ensuring safety constraints are met
2Reliability
If complex path planning algorithms are implemented to improve safety, then the computing resources and time consumption increase
Solution Approach 1:
The patent performs preliminary computation by pre-generating basis paths that capture the essential geometry of the environment before the actual path planning is needed. These basis paths are computed offline or in advance, so that during real-time operation, the system only needs to optimize along these pre-computed trajectories rather than searching the entire configuration space, significantly reducing computing time
Solution Approach 2:
The patent transforms the path planning problem from searching for complete trajectories to optimizing parameters along pre-defined basis paths. By changing the problem parameters from full path coordinates to optimization variables (such as timing parameters, velocity profiles, and interpolation coefficients), the computational complexity is reduced while maintaining safety guarantees
3Manufacturing precision
If more candidate paths are generated to improve planning quality, then the computational complexity and processing time increase
Solution Approach 1:
The patent applies local quality optimization by focusing computational efforts on critical sections of the path rather than uniformly processing the entire trajectory. The optimization algorithm applies different levels of detail and computational intensity to different segments of the basis paths, concentrating resources on areas with high curvature, narrow passages, or complex constraints while using simpler representations in less critical areas
Data Source
Figure 1
Figure 2A
Figure 2B
AI summary
Systems and methods for basis path generation are provided. In particular, a computing system can obtain a target nominal path. The computing system can determine a current pose for an autonomous vehicle. The computing system can determine, based at least in part on the current pose of the autonomous vehicle and the target nominal path, a lane change region. The computing system can determine one or more merge points on the target nominal path. The computing system can, for each respective merge point in the one or more merge points, generate a candidate basis path from the current pose of the autonomous vehicle to the respective merge point. The computing system can generate a suitability classification for each candidate basis path. The computing system can select one or more candidate basis paths based on the suitability classification for each respective candidate basis path in the plurality of candidate basis paths.