Teleassistance Data Encoding for Self-Driving Vehicle Anomaly Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current autonomous vehicle technologies face challenges in dynamically resolving anomalies on public roads and highways, often requiring vehicles to pull over or stop, or relying on human intervention, due to limitations in on-board computational capabilities and sensor data processing.
Innovation Solution
Implementing a teleassistance module that prioritizes and encodes sensor data for transmission to remote operators, allowing for real-time assistance in detecting and classifying objects, and providing instructions for the vehicle to proceed safely, leveraging human cognition to enhance autonomous decision-making.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If autonomous vehicle systems rely solely on on-board computational capabilities to detect and resolve anomalies, then system independence is improved, but anomaly resolution capability deteriorates due to limited processing power
Solution Approach 1:
The patent introduces a teleassistance system as an intermediary between the autonomous vehicle and remote human operators. When the perception system detects an anomaly it cannot resolve, the system transmits relevant sensor data through a communication interface to remote operators who provide assistance, thereby resolving the limitation of on-board processing while maintaining system independence for normal operations
Solution Approach 2:
The patent segments the anomaly resolution function into two parts: routine anomaly detection and resolution handled by on-board systems, and complex anomalies requiring human intervention handled by remote operators. This segmentation allows the system to maintain independence for common scenarios while accessing external expertise only when necessary
2Measurement precision
If the vehicle transmits all sensor data to remote operators for anomaly resolution, then anomaly detection accuracy is improved, but bandwidth consumption increases
Solution Approach 1:
The patent extracts only the necessary sensor data related to detected anomalies for transmission to remote operators, rather than transmitting all sensor data. The system identifies specific anomalies, extracts relevant sensor readings and contextual information, and transmits only this focused data subset, thereby maintaining detection accuracy while minimizing bandwidth consumption
Solution Approach 2:
The patent applies local quality by transmitting sensor data at different quality levels based on its relevance to the detected anomaly. Critical data related to the anomaly is transmitted with high fidelity, while less critical contextual data is transmitted at lower quality, optimizing the balance between detection accuracy and bandwidth usage
3Reliability
If the vehicle stops or pulls over to resolve anomalies, then safety is improved, but operational continuity deteriorates
Solution Approach 1:
The patent implements preliminary action by continuously monitoring sensor data and detecting anomalies before they become critical safety issues. The system proactively identifies potential problems, attempts automated resolution, and only requests remote assistance when necessary, thereby maintaining operational continuity while ensuring safety through early detection and intervention
Solution Approach 2:
The patent enables self-service by implementing automated anomaly detection and resolution capabilities on the vehicle itself. The perception system continuously monitors for anomalies and attempts to resolve them using on-board computational resources, allowing the vehicle to maintain operational continuity for routine issues while reserving remote assistance for complex cases that require human expertise
Data Source
AI summary
A self-driving vehicle (SDV) can analyze a live sensor view to autonomously operate acceleration, braking, and steering systems of the SDV along a current route. The SDV can identify an indeterminate object in the live sensor view, and encoding sensor data identifying the indeterminate object for transmission to a backend transport system over one or more networks. The SDV may then receive a resolution response from the backend transport system to resolve the indeterminate object, and cause the SDV to proceed in accordance with the resolution response.