Remote Assistance for Autonomous Vehicle Edge-Case Maneuvers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in making certain driving decisions where human intuition or additional sensory input is necessary, such as unprotected left turns or navigating temporary obstacles, due to limitations in onboard computing systems.
Innovation Solution
The system enables autonomous vehicles to request assistance from remote operators or computing systems by sending sensor data and situational information, allowing human guides or advanced systems to verify and provide instructions for safe maneuvers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If autonomous vehicles rely solely on onboard computing systems for decision-making, then device complexity is reduced, but reliability deteriorates in complex scenarios requiring human judgment
Solution Approach 1:
The patent introduces a remote operator as an intermediary between the autonomous vehicle and the control system. When the vehicle encounters a situation it cannot confidently resolve, it requests assistance from a remote operator who provides guidance through a communication interface. This mediator approach enhances reliability for complex scenarios without requiring the vehicle's onboard system to handle all decision-making independently.
2Reliability
If autonomous vehicles request remote assistance for all uncertain situations, then reliability improves, but loss of time increases due to communication delays
Solution Approach 1:
The system does not request remote assistance for all situations, but only for those that fall within a predetermined set of complex scenarios where human judgment is particularly valuable. The vehicle autonomously handles routine decisions while selectively engaging remote operators for specific challenging situations, balancing reliability improvement with time efficiency.
Solution Approach 2:
The system pre-defines a set of situations where remote assistance will be requested, allowing the vehicle to quickly determine whether assistance is needed without complex real-time analysis. This preliminary classification enables faster decision-making about when to engage remote operators.
3Productivity
If autonomous vehicles limit remote assistance to predetermined situations, then productivity improves, but adaptability deteriorates for unexpected scenarios
Solution Approach 1:
The system continuously learns from remote operator interventions. When a remote operator assists with a situation, the system records this interaction and uses it to refine its understanding of when remote assistance is appropriate. This feedback mechanism allows the predetermined set of situations to evolve and adapt to new scenario types while maintaining operational efficiency.
Data Source
AI summary
Example systems and methods enable an autonomous vehicle to request assistance from a remote operator in certain predetermined situations. One example method includes determining a representation of an environment of an autonomous vehicle based on sensor data of the environment. Based on the representation, the method may also include identifying a situation from a predetermined set of situations for which the autonomous vehicle will request remote assistance. The method may further include sending a request for assistance to a remote assistor, the request including the representation of the environment and the identified situation. The method may additionally include receiving a response from the remote assistor indicating an autonomous operation. The method may also include causing the autonomous vehicle to perform the autonomous operation.