Autonomous Vehicle Deviation Explanation Using Event Simulation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles (AVs) often deviate from planned paths unexpectedly, causing confusion among passengers and remote operators due to maneuvers like collision avoidance or maintaining distance from objects, leading to a lack of confidence in the AV system without proper notification or explanation.
Innovation Solution
An autonomous vehicle notification and post-action explanation system is implemented, which identifies the cause of deviations and provides users with visual and audio explanations using data from the AV stack, simulating the events to determine the cause of the deviation, such as avoiding an animal on the road, and logs these events for future analysis.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the AV deviates from the planned path to avoid collision or maintain clearance, then safety is improved, but user confidence and clarity deteriorate due to lack of explanation
Solution Approach 1:
The system implements feedback by notifying users of path deviations and providing post-action explanations. When the AV deviates from the planned path, the notification system alerts users in real-time, and after the deviation occurs, the explanation system communicates what caused the deviation (e.g., collision avoidance, maintaining clearance), thereby maintaining user understanding and confidence while preserving safety maneuvers.
2Reliability
If the AV provides detailed explanations for deviations, then user trust is improved, but system complexity increases
Solution Approach 1:
The explanation functionality is extracted as a separate module that receives deviation events from the autonomous driving system. Rather than embedding explanation logic throughout the entire AV stack, the system extracts the notification and explanation generation into a dedicated component that processes deviation information and communicates it to users, thereby building trust without significantly increasing overall system complexity.
3Loss of information
If the AV implements real-time notification and explanation systems, then user awareness is improved, but processing time may be affected
Solution Approach 1:
The system performs preliminary action by notifying users in real-time when a deviation is detected, rather than waiting for the maneuver to complete. The notification system is triggered immediately upon deviation detection, providing timely awareness to users without delaying the autonomous vehicle's response to safety-critical situations.
Data Source
AI summary
Among other things, techniques are described for notifying and explaining the action performed by an autonomous vehicle, including but not limited to: receiving a planned path of a vehicle, a state of the vehicle and environment data of an environment in which the vehicle is operating, receiving a deviation signal, determining whether the deviation signal was reported by a first system or a second system of the vehicle, in response selecting a first set of simulators or a second set of simulators for simulating the vehicle in the environment, simulating the vehicle in the environment using the selected first or second set of simulators, based on results of the simulating, generating a message and presenting the message to at least one occupant of the vehicle.