Minimal Risk Maneuver Control for Autonomous Driving Failures
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face risks during unexpected events, such as component failures or deviations from designated driving paths, which can lead to accidents if not properly managed.
Innovation Solution
The vehicle is equipped with a minimal risk maneuver (MRM) system that allows it to perform autonomous driving without driver intervention, initiating maneuvers like steering, acceleration, or braking to mitigate risks and transition to a safe state when necessary, using sensors and a controller to assess situations and select appropriate MRM types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If autonomous driving is performed without driver intervention, then driving convenience is improved, but risk of accidents during unexpected events increases
Solution Approach 1:
The system performs preliminary risk assessment before executing autonomous driving maneuvers. The controller continuously evaluates potential risks and prepares minimal risk maneuver responses in advance, so when unexpected events occur, the vehicle can immediately execute pre-planned safe responses rather than reacting in real-time during critical moments
Solution Approach 2:
The system implements continuous feedback loops where sensors monitor the driving environment and vehicle state, the controller assesses risks based on this feedback, and adjusts autonomous driving actions accordingly. When risk is detected, the system provides feedback to initiate minimal risk maneuvers, creating a closed-loop control system that adapts to changing conditions
2Reliability
If minimal risk maneuver is initiated to eliminate risk, then vehicle safety is improved, but driving continuity is disrupted
Solution Approach 1:
The system applies partial minimal risk maneuvers rather than complete stops when possible. Instead of always initiating full emergency stops, the controller selects appropriate levels of risk mitigation actions based on the severity and type of risk detected, applying only the necessary degree of intervention to eliminate risk while maintaining driving flow
Solution Approach 2:
The system dynamically adjusts the intensity and type of minimal risk maneuvers based on real-time conditions. The controller can transition between different maneuver types (steering adjustments, acceleration modifications, braking interventions) depending on the situation, making the safety response flexible rather than rigid
3Measurement precision
If multiple sensors and controllers are used for risk assessment, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system merges multiple sensor inputs and control functions into a unified risk assessment framework. Rather than operating as separate independent systems, the sensors and controllers are integrated into a single coordinated system where data from multiple sources is combined and processed together to generate comprehensive risk evaluations
Data Source
AI summary
Disclosed is a vehicle which supports a minimal risk maneuver. The vehicle performs driving, perform the minimal risk maneuver when a specific event occurs during the driving, eliminates the risk of the vehicle in accordance with the initiation of the minimal risk maneuver, ends the minimal risk maneuver when the risk of the vehicle is eliminated, and performs the driving again after ending the minimal risk maneuver.