Autonomous Vehicle Teleoperation for Unpredictable Road Obstacles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in navigating unpredictable real-world situations such as traffic congestion, emergency vehicles, or obstacles that prevent them from proceeding to their destination autonomously.
Innovation Solution
The system allows autonomous vehicles to transmit sensor data to a control center, which analyzes the situation and provides guidance instructions to the vehicle, enabling it to navigate through the obstacle using limited control and speed, allowing it to continue its journey safely.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicles operate completely autonomously, then automation level is improved, but ability to handle unpredictable real-world situations deteriorates
Solution Approach 1:
A control center serves as an intermediary between autonomous vehicles and human operators. The control center receives sensor data from vehicles, analyzes situations that the autonomous system cannot handle, and transmits teleoperation instructions back to the vehicle. This intermediary system enables the vehicle to maintain high automation levels while having access to human expertise for unpredictable situations.
Solution Approach 2:
The system dynamically adjusts the level of automation based on situational needs. During normal operation, the vehicle operates autonomously with high automation. When encountering unpredictable situations that the autonomous system cannot resolve, the system transitions to teleoperation mode, allowing human operators to take control. This dynamic switching resolves the contradiction by adapting automation level to task requirements.
2Reliability
If teleoperation instructions are transmitted to autonomous vehicles, then ability to navigate unpredictable situations is improved, but system complexity increases
Solution Approach 1:
The complex decision-making burden for unpredictable situations is extracted from the autonomous vehicle and relocated to the control center where human operators handle it. The vehicle's onboard system remains relatively simple, focusing on autonomous navigation and transmitting sensor data. Only when needed are teleoperation instructions transmitted back to the vehicle, minimizing the added complexity.
Solution Approach 2:
The autonomous vehicle handles routine navigation and situation assessment independently using its onboard sensors and processing systems. It only seeks teleoperation assistance when it determines that an unpredictable situation cannot be resolved autonomously. This self-service approach minimizes system complexity by keeping the teleoperation system dormant during normal operation and activating only when necessary.
3Measurement precision
If real-time sensor data is transmitted to control center, then navigation guidance accuracy is improved, but data transmission requirements increase
Solution Approach 1:
Instead of continuously transmitting all sensor data, the system transmits only partial data - specifically sensor data related to situations that require teleoperation assistance. The control center receives and analyzes only the necessary subset of data needed to make navigation decisions, reducing overall data transmission volume while maintaining guidance accuracy for critical situations.
Solution Approach 2:
The autonomous vehicle performs preliminary analysis of sensor data onboard before transmission. It pre-processes the data to identify and extract only those situations that require human intervention, filtering out routine data that can be handled autonomously. This preliminary action reduces the volume of data that needs to be transmitted to the control center while ensuring that all critical information is included.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
The present disclosure is directed to systems and techniques for providing a teleoperation instruction to an autonomous vehicle. While the autonomous vehicle is travelling to a destination, the autonomous vehicle may encounter a situation preventing the autonomous vehicle from travelling to the destination. A control center may receive information from the autonomous device and provide instructions with limited controls for the autonomous vehicle to navigate to an intermediate position. In such an intermediate position, the vehicle may make way for an emergency vehicle, obtain additional sensor data for continued autonomous planning, signal intent to other objects in the environment, and the like.