Remote Assistance Interface With Proposed Trajectories for AV Obstacles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous and semi-autonomous vehicles may encounter obstacles or challenging navigation situations that their systems cannot independently overcome, necessitating remote assistance to guide the vehicle safely through the issue.
Innovation Solution
A computing device positioned remotely from the vehicle receives sensor data depicting the vehicle's forward path and displays a representation of this path. It augments this representation with proposed trajectories that convey maneuvers relative to road boundaries, allowing a human operator to select and provide navigation instructions to the vehicle based on these trajectories.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicle systems navigate independently without remote assistance, then automation level and response speed are improved, but the ability to handle complex obstacles and challenging navigation situations deteriorates
Solution Approach 1:
The patent introduces a remote assistance system as an intermediary between the autonomous vehicle and human operators. The system includes a remote computing device that receives sensor data from the vehicle, generates proposed trajectories, and allows human operators to select and communicate navigation instructions. This intermediary architecture enables the autonomous system to maintain high automation levels while providing on-demand human assistance for complex situations, thus resolving the contradiction between automation extent and adaptability.
2Measurement precision
If remote assistance is provided with detailed sensor data and proposed trajectories, then navigation accuracy and safety are improved, but communication bandwidth and processing requirements increase
Solution Approach 1:
The patent extracts and transmits only the essential elements needed for remote assistance: sensor data depicting the forward path and generated proposed trajectories. Rather than transmitting all raw sensor data, the system processes data on the vehicle and remote computing devices to extract only the critical information required for human operators to make navigation decisions. This extraction approach maintains navigation accuracy while reducing communication bandwidth requirements.
3Reliability
If human operators provide real-time guidance for every obstacle, then vehicle safety is improved, but response latency and operational efficiency deteriorate
Solution Approach 1:
The patent implements preliminary action by having the remote computing device generate multiple proposed trajectories in advance before human operators need to provide guidance. The system proactively processes sensor data, identifies potential obstacles, and prepares navigation options ahead of time. This allows human operators to review pre-generated trajectories and provide instructions with reduced latency, improving both safety and response efficiency.
Data Source
Figure 1
Figure 2A~2B
Figure 2C~2D
AI summary
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.