Autonomous Vehicle Fallback Trajectory Control by Road Type

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Autonomous vehicles face challenges in safely controlling themselves during system failures, particularly on highways and in heavy traffic situations, where immediate braking or pulling over may not be the best actions, and existing systems lack adaptive fallback behaviors based on road type and sensor functionality.

Innovation Solution

A system with multiple computing systems, including a primary, secondary, and fallback computing system, where the fallback system generates trajectories based on road type and available sensor functionality to ensure safe vehicle operation, reducing the likelihood of stopping in a lane and adapting maneuvers according to the situation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If the vehicle uses a simple fallback system that applies brakes as hard and as quickly as possible, then the system complexity is reduced, but the safety and adaptability to different road situations deteriorates

Engineering Contradiction:
Improvefallback system complexityVSAvoidsafety during system failure
Core Design Contradiction:
Device complexityVSReliability

Solution Approach 1:

The fallback system is segmented into multiple independent computing systems (first, second, and third computing systems) that can operate autonomously. Each computing system can generate trajectories independently, allowing the vehicle to maintain safety without requiring a single complex centralized system. This segmentation enables simpler individual components while achieving overall system reliability through redundancy.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system changes operational parameters based on road type detection. When a highway is detected, the fallback system generates trajectories suitable for highway conditions (maintaining higher speeds, different braking patterns). When surface streets are detected, different trajectory parameters are used. This allows the same hardware to adapt its behavior to different contexts, improving safety without increasing physical complexity.

Inventive Principle:
Principle #35Parameter changes

2Reliability

If the vehicle implements adaptive fallback behaviors based on road type and sensor functionality, then the safety and adaptability improve, but the device complexity increases

Engineering Contradiction:
Improvesafety during system failureVSAvoidfallback system complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The third computing system is designed as a universal fallback that can handle multiple road types (highways and surface streets) and multiple sensor failure scenarios. Rather than creating specialized systems for each scenario, a single multi-functional computing system performs all fallback operations, reducing overall system complexity while maintaining adaptability.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The fallback system dynamically adapts its behavior based on real-time conditions. The third computing system detects road type and sensor functionality, then dynamically generates appropriate trajectories. This dynamic adaptation allows the system to respond to varying conditions without requiring physical reconfiguration, achieving complexity through software rather than hardware.

Inventive Principle:
Principle #15Dynamics

3Measurement precision

If the fallback system generates comprehensive trajectories considering all sensor functionality, then the measurement precision and safety improve, but the computational resources and time required increase

Engineering Contradiction:
Improvetrajectory accuracyVSAvoidtrajectory generation time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The third computing system performs partial trajectory generation based on available sensor functionality. Rather than attempting to process all sensor data comprehensively (which would take excessive time), the system generates sufficient trajectories using only the functioning sensors. This partial action approach provides timely responses while maintaining adequate accuracy for safe operation.

Inventive Principle:
Principle #16Partial or excessive action

Solution Approach 2:

The system pre-determines which sensors are functioning and prepares corresponding trajectory generation strategies in advance. When system failure occurs, the third computing system immediately activates the pre-prepared trajectory generation approach based on the detected sensor status, eliminating the need for real-time comprehensive sensor evaluation and reducing computational delay.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentEP3856597B1Systems for implementing fallback behaviors for autonomous vehicles
Publication Date: 2024.12.04 WAYMO LLC
  • EP3856597B1 patent drawingFigure 1
  • EP3856597B1 patent drawingFigure 2
  • EP3856597B1 patent drawingFigure 3

AI summary

Aspects of the disclosure relate to controlling a vehicle 100 in an autonomous driving mode. The system includes a plurality of sensors configured to generate sensor data. The system also includes a first computing system 110 configured to generate trajectories using the sensor data and send the generated trajectories to a second computing system 120. The second computing system is configured to cause the vehicle to follow a received trajectory. The system also includes a third computing system 130 configured to, when there is a failure of the first computer system, generate and send trajectories to the second computing system based on whether a vehicle is located on a highway or a surface street.