Autonomous Vehicle Occupant Interface for Decision Transparency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous machines, such as vehicles, operate with limited input from occupants, leading to a lack of knowledge and understanding about their future actions and decision-making processes, which can decrease occupant confidence and cause unease.
Innovation Solution
Implementing a system that captures scan data of the environment around the vehicle's travel path using sensors, determines mutable and immutable objects, correlates navigation conditions with control operations, and generates a representation link between these operations and objects, which is then presented to the occupant through a user interface.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicles operate with limited input from occupants, then automation level and operational efficiency are improved, but occupant confidence and understanding of vehicle decisions deteriorate
Solution Approach 1:
The system provides continuous feedback to occupants by displaying detected objects, planned trajectories, and control operations through a presentation system. This feedback loop maintains high automation while improving occupant understanding by showing them what the vehicle perceives and plans to do, directly addressing the information loss problem.
Solution Approach 2:
The user interface acts as an intermediary between the autonomous vehicle's control system and the occupant. It translates complex sensor data and control decisions into comprehensible visual representations, bridging the gap between high-level automation and human understanding without requiring occupant intervention.
2Loss of information
If detailed information about vehicle operations is provided to occupants, then occupant confidence and understanding are improved, but system complexity and information processing requirements increase
Solution Approach 1:
The information presentation is segmented into distinct components: detected objects display, travel path visualization, mutable object identification, and control operation indicators. This segmentation allows complex information to be broken into manageable pieces that are easier to process and understand, reducing the perceived complexity while maintaining comprehensive information delivery.
Solution Approach 2:
The system provides different levels of information detail in different interface areas and contexts. Critical safety-related information receives prominent display, while less critical information is presented with lower visual weight. This local differentiation optimizes information delivery without uniformly increasing system complexity.
Data Source
AI summary
Systems and methods communicate an intent of an autonomous vehicle externally. In one implementation, scan data of a field around a travel path of an autonomous vehicle is obtained. The scan data is captured using at least one sensor. An object in the field around the travel path is determined from the scan data. The object is determined to be mutable or immutable. A navigation condition associated with the object is determined based on whether the object is mutable or immutable. The navigation condition is correlated to a portion of the travel path. Control operation(s) of the autonomous vehicle is determined for the portion of the travel path in response to the navigation condition. A representation link between the control operation(s) of the autonomous vehicle and the object is generated. A representation of the field around the travel path is rendered and includes the representation link.