Remote Assistance Control for Autonomous Vehicle Edge Cases
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle systems face challenges in reliably establishing perfect communication with teleoperators, necessitating either a human operator onboard or extensive training for the vehicle to handle rare scenarios, which is complex and often impossible to achieve.
Innovation Solution
A system and method for remote assistance of autonomous agents that includes a sensor suite, computing system, communication interface, and teleoperator platform, enabling information exchange and allowing teleoperators to provide remote inputs to assist the vehicle in challenging situations, thereby reducing the need for perfect communication and minimizing training requirements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If teleoperators are used to take over control of the vehicle in risky scenarios, then the autonomous vehicle can handle challenging situations, but perfect communication between the vehicle and teleoperator is required which is extremely complex and unreliable to establish
Solution Approach 1:
The patent introduces an onboard human operator as an intermediary between the autonomous vehicle system and teleoperators. This intermediary can locally assess situations and determine when teleoperator assistance is needed, reducing the burden on perfect vehicle-teleoperator communication while maintaining the ability to handle challenging situations.
Solution Approach 2:
The control system is segmented into multiple levels: autonomous vehicle control, onboard human operator decision-making, and remote teleoperator assistance. This segmentation allows each component to operate within its capabilities, with the onboard operator serving as a local decision-maker that reduces reliance on complex continuous communication with remote teleoperators.
2Reliability
If a human operator is required onboard to handle risky scenarios, then the vehicle can receive immediate human judgment, but the device complexity and operational cost increase
Solution Approach 1:
The onboard human operator serves as an intermediary that provides local human judgment when needed, rather than requiring continuous remote human oversight. This intermediary role allows the system to maintain reliability in risky scenarios while reducing overall system complexity compared to fully remote teleoperation.
Solution Approach 2:
The onboard human operator enables the vehicle to self-assess situations and self-determine when human intervention is necessary, rather than relying on external teleoperators for all decisions. This self-service capability reduces the complexity of continuous remote monitoring while maintaining reliability.
3Adaptability or versatility
If the autonomous vehicle is trained to reliably understand and react to rare circumstances, then the vehicle can handle edge cases autonomously, but extensive training is required which is complex and often impossible to achieve
Solution Approach 1:
The onboard human operator acts as an intermediary that handles rare and edge cases that the autonomous system cannot reliably handle through training alone. This eliminates the need for extensive and often impossible training scenarios while maintaining the ability to handle rare circumstances through human judgment.
Solution Approach 2:
Instead of training the autonomous system for all possible rare scenarios (excessive action), the system uses partial automation with human oversight for edge cases. This approach acknowledges that complete autonomous handling of all rare circumstances through training is impractical.
Data Source
AI summary
A system 100 for remote assistance of an autonomous agent can include and/or interface with any or all of: a sensor suite 110, a computing system 120, a communication interface 130, and/or any other suitable components. The system can further optionally include a set of infrastructure devices 140, a teleoperator platform 150, and/or any other suitable components. The system 100 functions to enable information to be exchanged between an autonomous agent and a tele-assist. Additionally or alternatively, the system 100 can function to operate the autonomous agent (e.g., based on remote inputs received from a teleoperator, indirectly, etc.) and/or can perform any other suitable functions.