Autonomous Vehicle Road Geometry Estimation via Trajectory Tracking

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Autonomous vehicles face safety risks due to inaccuracies in road geometry maps caused by lane closures and changes, which can lead to crashes or navigation failures.

Innovation Solution

The method involves tracking the trajectories of other vehicles on the road to detect lane closures and road blocks, using a processor to generate a new trajectory based on observed vehicle paths and map data, and adjusting the vehicle's speed and direction to avoid obstacles, while also updating the map to correct inaccuracies.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If autonomous vehicles use pre-stored map data for navigation, then route planning efficiency is improved, but navigation safety deteriorates due to road geometry changes from lane closures and construction

Engineering Contradiction:

Improveroute planning efficiencyVSAvoidnavigation safety

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system implements feedback by continuously monitoring the trajectories of multiple vehicles and comparing observed paths against the pre-stored map data. When discrepancies are detected indicating road geometry changes, the system feeds this information back to update the map data, ensuring navigation safety while maintaining efficiency through automated real-time updates rather than manual intervention

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs preliminary action by pre-storing map data for efficient route planning, then proactively detects changes before they cause navigation failures. By monitoring vehicle trajectories in real-time and detecting road geometry changes early, the system updates map data preventively, maintaining both the efficiency of pre-stored maps and the safety of current road conditions

Inventive Principle:

Principle #10Preliminary action

2Device complexity

If autonomous vehicles rely solely on pre-stored map data, then system complexity is reduced, but measurement precision of road geometry deteriorates when road conditions change

Engineering Contradiction:

Improvesystem complexityVSAvoidroad geometry accuracy

Core Design Contradiction:

Device complexityVSMeasurement precision

Solution Approach 1:

The system merges pre-stored map data with real-time trajectory observations from multiple vehicles to maintain road geometry accuracy. By combining the efficiency of pre-stored data with the precision of real-time observations, the system achieves high measurement precision without significantly increasing system complexity, as the integration is performed through automated comparison and update protocols

Inventive Principle:

Principle #5Merging (Combining)

3Reliability

If autonomous vehicles track and process trajectories of multiple vehicles in real-time, then navigation safety is improved, but computational load and processing time increase

Engineering Contradiction:

Improvenavigation safetyVSAvoidprocessing time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system applies partial action by selectively processing trajectory data only when discrepancies are detected that indicate road geometry changes. Rather than continuously analyzing all trajectory data at full computational intensity, the system monitors for anomalies and performs detailed processing only when necessary, maintaining navigation safety while reducing unnecessary computational load and processing time

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS9460622B1Approach for estimating the geometry of roads and lanes by using vehicle trajectories

Publication Date: 2016.10.04 WAYMO LLC

AI summary

A method and apparatus is provided for controlling the operation of an autonomous vehicle. According to one aspect, the autonomous vehicle may track the trajectories of other vehicles on a road. Based on the other vehicle's trajectories, the autonomous vehicle may generate a representative trajectory. Afterwards, the autonomous vehicle may change at least one of its speed or direction based on the representative trajectory.