Remote Assistance Trajectory Interface for Autonomous Vehicle Obstacles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous and semi-autonomous vehicles may encounter obstacles such as construction sites, poorly marked roadways, or stranded vehicles, which can limit their navigation capabilities, and existing systems lack effective remote assistance mechanisms to guide them through such situations.
Innovation Solution
A computing device positioned remotely from the vehicle receives sensor data to display a representation of the vehicle's forward path, augments it with proposed trajectories relative to road boundaries, and provides navigation instructions based on selected trajectories, allowing human operators to assist the vehicle in overcoming obstacles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicles navigate independently without human intervention, then automation level and operational efficiency are improved, but the ability to handle complex obstacles and dynamic environments deteriorates
Solution Approach 1:
The patent introduces a remote operator as an intermediary between the autonomous vehicle and the control system. When the vehicle encounters obstacles it cannot handle independently, control is transferred to a human operator who can make decisions based on real-time sensor data and the augmented trajectory visualizations, thus maintaining high automation while providing human adaptability when needed
Solution Approach 2:
The system dynamically adjusts the level of automation based on the situation. The autonomous vehicle operates independently under normal conditions, but can seamlessly transition to remote human control when obstacles are detected that exceed the autonomous system's capabilities, creating a flexible hybrid control architecture
2Reliability
If remote assistance mechanisms are implemented to guide vehicles through obstacles, then adaptability and safety are improved, but system complexity and response time deteriorate
Solution Approach 1:
The system performs preliminary actions by pre-calculating multiple proposed trajectories and preparing augmented reality visualizations before human operators need to make decisions. The sensor data is continuously processed and potential navigation options are pre-computed, so when an obstacle is detected, the operator receives ready-to-use trajectory suggestions immediately
Solution Approach 2:
The system creates a virtual copy of the physical environment by generating augmented reality visualizations that replicate the real-world scene with overlaid trajectory information. This virtual representation allows operators to interact with and analyze the situation without directly processing complex raw sensor data, simplifying the interface while maintaining safety
3Ease of operation
If multiple proposed trajectories are displayed to human operators, then navigation decision quality is improved, but information processing complexity and operator workload increase
Solution Approach 1:
The system applies local quality by providing different levels of information detail in different parts of the interface. The augmented reality visualization shows simplified graphical representations of trajectories with key features highlighted, while detailed sensor data and raw measurements are available on-demand for operators who need deeper analysis, allowing selective information processing
Solution Approach 2:
The system provides more trajectory options than the operator may ultimately need (excessive action), but presents them in a simplified visual format. The augmented reality display shows multiple proposed trajectories with their key characteristics, allowing operators to quickly scan and select appropriate options without being overwhelmed by complete technical specifications of each path
Data Source
AI summary
Example embodiments relate to user interface techniques for recommending remote assistance actions. A remote computing device may display a representation of the forward path for an autonomous vehicle based on sensor data received from the vehicle. The computing device may augment the representation of the forward path to further depict one or more proposed trajectories available for the autonomous vehicle to perform. Each proposed trajectory conveys one or more maneuvers positioned relative to road boundaries in the forward path. The computing device may receive a selection of a proposed trajectory from the one or more proposed trajectories available for the autonomous vehicle to perform and provide navigation instructions to the vehicle based on the proposed trajectory.