Autonomous Vehicle Basis Path Planning for Lane Change Merging

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in efficiently and safely navigating through complex environments, particularly in lane changes and obstacle avoidance, due to the lack of effective path planning systems that consider drivability constraints and dynamic environmental factors.

Innovation Solution

A vehicle computing system generates basis paths by identifying lane change regions, determining merge points, and evaluating candidate paths based on drivability criteria, using sensor data and map information to plan safe and efficient lane transitions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If a path planning system generates multiple candidate basis paths to evaluate different lane change options, then the completeness and safety of path evaluation is improved, but the processing time and computational complexity increase

Engineering Contradiction:

Improvepath evaluation completenessVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The path planning process is segmented into distinct phases: generating candidate basis paths, evaluating drivability constraints, and selecting optimal paths. By dividing the complex path planning task into manageable segments, the system can efficiently process multiple candidate paths without overwhelming computational burden at any single stage

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-generating candidate basis paths and pre-evaluating drivability constraints before final path selection. This preliminary processing allows the system to have multiple vetted options ready, reducing the time needed for final decision-making while maintaining comprehensive evaluation

Inventive Principle:

Principle #10Preliminary action

2Reliability

If the system evaluates multiple candidate basis paths with comprehensive drivability constraints, then the safety and suitability of path selection is improved, but the data storage requirements and processing complexity increase

Engineering Contradiction:

Improvepath selection safetyVSAvoidprocessing complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system applies local quality by evaluating different drivability constraints at specific locations along each candidate path. Rather than applying uniform complex evaluation to all paths, the system tailors the evaluation criteria to local conditions such as lane geometry, traffic patterns, and environmental factors at each merge point

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system changes parameters by adjusting drivability constraint thresholds and evaluation criteria based on local conditions. Parameters such as lateral acceleration limits, longitudinal acceleration limits, and lane change timing are dynamically adjusted according to the specific characteristics of each candidate path and environmental context

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If the autonomous vehicle uses extensive sensor data and map information for path planning, then the accuracy of environmental perception is improved, but the energy consumption and processing load increase

Engineering Contradiction:

Improveenvironmental perception accuracyVSAvoidenergy consumption

Core Design Contradiction:

Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system extracts only the essential sensor data and map information needed for path planning at each decision point. Rather than continuously processing all available sensor data, the system selectively extracts relevant information such as lane markings, merge points, and immediate environmental obstacles, reducing processing load while maintaining perception accuracy

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The system applies partial action by using a subset of available sensor data and map information sufficient for making safe path decisions. The system processes only the necessary portion of environmental data required for evaluating candidate basis paths, avoiding the energy cost of processing excessive data while maintaining adequate perception accuracy

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS12566440B2Systems and methods for generating basis paths for autonomous vehicle motion control

Publication Date: 2026.03.03 AURORA OPERATIONS INC

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.