Remote Object Annotation for Autonomous Vehicle Navigation Bottlenecks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face navigation challenges when encountering complex or unexpected situations, such as obstacles or road conditions, as their sensor systems may struggle to identify and classify objects, leading to temporary strandings or unsafe navigation strategies.
Innovation Solution
The implementation of a system that allows vehicles to request remote assistance through wireless communication, using a graphical user interface to visually represent sensor data and receive object identifiers from human or computer assistants, enabling accurate object classification and navigation strategy development.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If autonomous vehicles use sensor systems to identify and classify objects, then navigation capability is improved, but reliability deteriorates when encountering complex or unexpected situations
Solution Approach 1:
The patent introduces a remote assistant system as an intermediary between the autonomous vehicle and complex situations. When the vehicle's sensor system encounters objects it cannot reliably identify or classify, the system transmits sensor data to a remote assistant who provides guidance on object identification and navigation strategy, thereby resolving the reliability issue without compromising autonomous operation
Solution Approach 2:
The system performs preliminary actions by establishing a remote assistance infrastructure before the vehicle encounters problematic situations. The remote assistant system is pre-configured and available, allowing the vehicle to request help when needed rather than having to handle all situations independently, improving reliability for edge cases
2Productivity
If vehicles operate in fully autonomous mode without human drivers, then productivity is improved, but reliability deteriorates due to inability to handle complex situations
Solution Approach 1:
The remote assistant acts as a mediator that bridges fully autonomous operation with human expertise. The vehicle operates autonomously for routine tasks maintaining productivity, but can invoke the remote assistant intermediary when encountering complex situations, ensuring navigation safety without sacrificing autonomous operation capability
Solution Approach 2:
Instead of requiring full human oversight for all operations (which would reduce productivity), the system applies partial human action only when necessary. The vehicle operates fully autonomously for normal conditions, invoking remote assistance only for complex or unexpected situations, achieving both productivity and reliability
Data Source
AI summary
Example embodiments relate to techniques for enabling one or more systems of a vehicle (e.g., an autonomous vehicle) to request remote assistance to help the vehicle navigate in an environment. A computing device may be configured to receive a request for assistance from a vehicle. The request may include an image frame representative of a portion of an environment. The computing device may also be configured to initiate display of a graphical user interface to visually represent the image frame. Further, the computing device may determine a bounding region for the image frame. The bounding region may be associated with one or more objects in the image frame. Additionally, the computing device may be configured to receive, via the GUI, an input that includes an object identifier, and associate the object identifier with each of the one or more objects in the bounding region.