Remote AV Reversing Interface for Safe End-Pose Maneuvers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous Vehicles (AVs) face challenges in performing reverse maneuvers due to sensory limitations, particularly in unclear environments, leading to a need for remote assistance to ensure safe and efficient operation.
Innovation Solution
A computer-implemented system and user-interface protocol that allows remote human supervision for AVs, enabling instructions to shift gears, calculate reversing paths, and transmit signals to move the vehicle in reverse gear, with safety checks and adjustments to ensure the AV reaches a desired end-pose safely.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicles perform reverse maneuvers independently using sensor data, then automation level is improved, but safety and reliability deteriorate in unclear environments
Solution Approach 1:
A remote assistance platform serves as an intermediary between the autonomous vehicle and human operators. The platform receives sensor data from the vehicle, processes it, and presents it to remote operators who can provide supervisory control during reverse maneuvers. This mediator allows the system to maintain high automation levels while incorporating human judgment for safety-critical decisions.
Solution Approach 2:
The system performs preliminary actions by pre-processing sensor data, generating multiple candidate reverse paths, and presenting them to remote operators before execution. The platform prepares visualizations of the environment and path options in advance, allowing operators to make informed decisions quickly when needed.
2Reliability
If remote assistance is introduced for reverse maneuvers, then safety is improved, but device complexity increases
Solution Approach 1:
The remote assistance platform is designed to be multi-functional, handling sensor data reception, processing, visualization generation, communication with the vehicle, and operator interface management. By consolidating these functions into a single universal platform, the system avoids the complexity of separate dedicated systems for each function.
Solution Approach 2:
The system creates visual copies and representations of the vehicle's sensor data and environment model, presenting them to remote operators through the platform. These visualizations are simplified copies of the complex sensor data, making it easier for operators to understand and make decisions without directly processing the raw sensor complexity.
3Measurement precision
If sensor data visualization is enhanced for remote operators, then operational accuracy is improved, but information processing requirements increase
Solution Approach 1:
The platform segments sensor data into distinct categories (e.g., obstacle detection, path analysis, environmental features) and processes each segment separately. This allows selective enhancement of visualizations for critical elements while maintaining efficient processing for less critical data, reducing overall computational requirements while improving operational accuracy.
Data Source
AI summary
Examples of the present disclosure provide a computer-implemented system, comprising: one or more non-transitory computer-readable media storing instructions, which when executed by one or more processing units, cause the one or more processing units to perform operations including: providing instructions to shift a gear of a vehicle from drive to reverse; receiving, from the vehicle, an end-pose and a reversing path for the vehicle; calculating a reverse maneuver for the vehicle to move in reverse gear based on the end-pose and the reversing path; transmitting, to the vehicle, signals to move the vehicle in reverse gear, the signals being transmitted at a signal rate above a predetermined rate threshold; and stopping the vehicle in response to reaching the end-pose.