Self-Driving Car Lane Planning for Fewer Lane Changes

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing self-driving car navigation systems face challenges in efficiently planning routes to minimize lane-changing maneuvers, which can be complex due to numerous lane-level alternatives and varying traffic conditions.

Innovation Solution

A system utilizing a global scoring model and a local scoring model to evaluate lane-level transitions, incorporating real-time data from sensors to adjust lane-changing decisions, and employing a lane-planning module with a graph-structure to optimize route planning, reducing unnecessary lane changes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Manufacturing precision

If the system evaluates all lane-level alternatives using comprehensive scoring models, then the route optimization quality improves, but the computational complexity and processing time increase

Engineering Contradiction:
Improveroute optimization qualityVSAvoidcomputational complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The lane planning problem is segmented into two distinct scoring models: a global scoring model that evaluates lane transitions based on overall route optimization, and a local scoring model that adjusts evaluations based on immediate traffic conditions. This segmentation allows the system to process complex routing decisions in manageable stages, improving computational efficiency while maintaining optimization quality

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The global scoring model performs preliminary evaluation of lane transitions before the vehicle reaches decision points. By pre-calculating optimal lane transitions based on the navigational route and traffic rules, the system reduces real-time computational burden while ensuring high-quality route optimization

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If the system uses multiple scoring models and real-time sensor data, then the accuracy of lane-changing decisions improves, but the system complexity increases

Engineering Contradiction:
Improvedecision accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system employs dynamic scoring where the local scoring model continuously adjusts lane transition evaluations based on real-time sensor data regarding traffic conditions. This dynamic approach enables accurate decision-making that adapts to changing environments without requiring a completely complex reevaluation of the entire routing plan

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The local scoring model provides feedback to the global scoring model by adjusting lane transition scores based on current traffic conditions detected by sensors. This feedback mechanism improves decision accuracy by incorporating real-time information while maintaining a structured two-level evaluation framework that manages system complexity

Inventive Principle:
Principle #23Feedback

3Reliability

If the system minimizes lane-changing maneuvers through careful planning, then the safety and efficiency improve, but the flexibility to adapt to changing traffic conditions decreases

Engineering Contradiction:
ImprovesafetyVSAvoidflexibility
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The global scoring model establishes a planned route with minimized lane changes in advance, improving safety by reducing unnecessary maneuvers. This preliminary planning provides a safe baseline route that can be executed with high reliability

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The local scoring model dynamically adjusts the planned route when traffic conditions change, allowing the system to adapt flexibly to new situations. When sensor data indicates changing traffic conditions, the local model modifies lane transition scores to enable appropriate lane changes, balancing safety with adaptability

Inventive Principle:
Principle #15Dynamics

Data Source

PatentEP3900997B1Method of and system for controlling operation of self-driving car
Publication Date: 2026.03.11 Y E HUB ARMENIA LLC
  • EP3900997B1 patent drawingFigure 1
  • EP3900997B1 patent drawingFigure 2
  • EP3900997B1 patent drawingFigure 3

AI summary

Method and device for controlling operation of a Self-Driving Car. The method includes determining route-level and lane-level information for generating a graph-structure, applying a first model for assigning costs to respective edges, storing the edges with the costs and the vertices with the scores. The method also includes at a given moment in time during operation: acquiring a lane path indicative of a lane segment extending from the current location without a lane-changing manoeuvre. The method includes, for the lane path: identifying a series of vertices covered by the lane segment, applying a second model for assigning additional costs to lane-path-departing edges of the series of vertices thereby determining locally-increased costs, determining local scores for vertices in the series of vertices based on the locally-increased costs, and identifying a lane path score for the lane path based on the local scores.