Teleoperated Trajectory Generation for Uncertain Vehicle Navigation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face navigation challenges when pathway indicators such as lane markings and runway lights are obscured, degraded, or invalidated, leading to inaccurate and inefficient navigation.
Innovation Solution
A teleoperations system collaborates with the autonomous vehicle's guidance system to generate and refine trajectories using sensor data, allowing the vehicle to request assistance remotely and continue moving without stopping, even at high speeds, by incorporating teleoperator input into the trajectory generation process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicle relies on onboard pathway indicators (lane markings, runway lights) for navigation, then navigation autonomy is improved, but navigation accuracy deteriorates when indicators are obscured or degraded
Solution Approach 1:
The patent introduces remote operators as intermediaries between the autonomous vehicle's navigation system and the environment. When onboard sensors fail to detect accurate pathway indicators, the system communicates with remote operators who provide corrective navigation guidance, thereby maintaining both autonomy and accuracy.
Solution Approach 2:
The system implements a feedback loop where the autonomous vehicle continuously monitors its navigation accuracy against detected pathway indicators. When degradation or obstruction is detected, the system receives feedback from remote operators and adjusts its navigation accordingly, resolving the contradiction between autonomous operation and navigation precision.
2Measurement precision
If autonomous vehicle requests remote assistance for navigation help, then navigation accuracy is improved in challenging scenarios, but operational efficiency deteriorates due to communication delays and intervention overhead
Solution Approach 1:
The system applies remote operator assistance selectively rather than continuously. Remote intervention is activated only when the autonomous vehicle detects pathway indicator degradation or navigation uncertainty, avoiding unnecessary communication overhead while maintaining accuracy when needed.
Solution Approach 2:
The autonomous vehicle performs preliminary detection and assessment of pathway indicator conditions before requesting remote assistance. This preliminary action filters out scenarios that don't require intervention, reducing communication overhead and maintaining operational efficiency while ensuring accuracy when truly needed.
3Reliability
If autonomous vehicle stops to resolve navigation uncertainties, then navigation safety is improved, but operational efficiency deteriorates due to loss of momentum and increased travel time
Solution Approach 1:
Remote operators serve as intermediaries that enable the vehicle to resolve navigation uncertainties without stopping. The vehicle maintains motion while communicating with remote operators who provide guidance, thereby preserving both safety through expert intervention and efficiency through continuous operation.
Solution Approach 2:
The system maintains continuous forward motion and continuous navigation processing even when uncertainties are present. By using remote operators as a support mechanism rather than requiring vehicle stops, the useful action of navigation continues uninterrupted, balancing safety and efficiency.
Data Source
AI summary
A teleoperations system that collaboratively works with an autonomous vehicle guidance system to generate a path for controlling the autonomous vehicle may comprise generating one or more trajectories at the teleoperations system based at least in part on environment data received from the autonomous vehicle and presenting the one or more trajectories to a teleoperator (e.g., a human user, machine-learned model, or artificial intelligence component). A selection of one of the trajectories may be received at the teleoperations system and transmitted to the autonomous vehicle. The one or more trajectories may be generated at the teleoperations system and/or received from the autonomous vehicle. Regardless, the autonomous vehicle may generate a control trajectory based on the trajectory received from teleoperations, instead of merely implementing the trajectory from the teleoperations system.