Autonomous Vehicle Teleoperation for Yielding Deadlock Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face delays and traffic congestion issues when navigating to pickup or destination locations due to impediments such as stopped or obstructed vehicles, leading to inefficient route management and potential blockages in traffic flow.
Innovation Solution
The autonomous vehicle determines when to contact a teleoperator by assessing the duration of impediment and intervening conditions, using sensor data to identify the cause of obstruction and sending relevant data for guidance, allowing it to alter navigation policies such as yielding or following, thereby resolving the impasse.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the autonomous vehicle follows navigation policies (yielding or following other vehicles), then safety and traffic rules are maintained, but progress is impeded causing delays and traffic blockages
Solution Approach 1:
The patent introduces a teleoperator as an intermediary between the autonomous vehicle and the control system. When the vehicle detects impeded progress due to yielding or following policies, it contacts the teleoperator who then communicates with the other vehicle's control system to coordinate movements, enabling the autonomous vehicle to proceed while maintaining safety through human-mediated negotiation
Solution Approach 2:
The system implements feedback by continuously monitoring the autonomous vehicle's progress and detecting when it is impeded. Based on this feedback, the vehicle dynamically adjusts its behavior by contacting the teleoperator, creating a closed-loop control system that responds to real-time navigation conditions
2Productivity
If the autonomous vehicle contacts a teleoperator for real-time guidance, then navigation efficiency is improved by resolving impasses, but system complexity and operational dependency increase
Solution Approach 1:
The autonomous vehicle does not contact the teleoperator for all navigation decisions, but only when progress is impeded and specific conditions are met. This partial action approach maintains high automation while reducing teleoperator dependency to only necessary cases, balancing efficiency gains with system simplicity
Solution Approach 2:
The autonomous vehicle independently detects when its progress is impeded, determines that teleoperator contact is necessary, and initiates the contact sequence without external prompting. The vehicle serves itself by autonomously identifying navigation impasses and self-managing the teleoperator interaction workflow
Data Source
AI summary
Techniques and methods for navigating an autonomous vehicle using teleoperator instructions. For instance, while navigating to a location, progress of an autonomous vehicle may stop. This may be caused by the autonomous vehicle yielding to another vehicle, such as at an intersection or when the other vehicle is located along a route of the autonomous vehicle. After yielding for a threshold amount of time, the autonomous vehicle may send sensor data and/or an indication of the other vehicle to the teleoperator. The autonomous vehicle may then receive, from the teleoperator, an instruction to cease yielding to the other vehicle. Based at least in part on the instruction, the autonomous vehicle may again begin navigating.