Distributed Object Determination Among Autonomous Vehicles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face challenges in efficiently processing sensor data to determine objects and road conditions due to limited computational resources and communication delays, especially when collaborating with other vehicles.
Innovation Solution
A method where a first vehicle requests tasks from other vehicles in a group to collaboratively process sensor data, selecting vehicles based on computation resources, communication delay, and trust factors to achieve accurate object determination and road condition sensing, leveraging distributed computing and communication capabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If autonomous vehicles process sensor data locally to determine objects, then determination speed is improved, but computational resource limitations cause processing accuracy to deteriorate
Solution Approach 1:
The patent segments the object determination task into multiple sub-tasks that are distributed across different vehicles in the platoon. Each vehicle processes specific sensor data locally to generate intermediate results, which are then combined to achieve accurate object determination. This segmentation allows parallel processing (improving speed) while distributing computational load (managing resource limitations).
Solution Approach 2:
The patent merges computational resources across multiple vehicles in the platoon. By combining the processing capabilities of several vehicles and aggregating their intermediate determination results, the system achieves higher processing accuracy than any single vehicle could attain alone, while maintaining fast determination speed through parallel operations.
2Measurement precision
If tasks are distributed to multiple vehicles for collaborative processing, then processing accuracy is improved, but communication delay increases
Solution Approach 1:
The patent implements preliminary action by having vehicles continuously perform sensing and pre-processing of sensor data even before specific determination tasks are initiated. This allows intermediate results to be ready or near-ready when needed, reducing the actual communication and processing delay when collaborative determination is required, while still achieving high accuracy through multiple vehicles' contributions.
Solution Approach 2:
The patent applies dynamics by adaptively selecting which vehicles perform which sub-tasks based on real-time conditions such as communication channel quality, computational resource availability, and task complexity. This dynamic allocation optimizes the balance between communication delay and processing accuracy, ensuring that tasks are assigned to vehicles that can complete them most efficiently.
3Productivity
If computational tasks are distributed across the vehicle group, then workload balance is improved, but system complexity increases
Solution Approach 1:
The patent implements self-service by enabling each vehicle to autonomously select and execute appropriate sub-tasks based on its own computational resource status and capabilities. Vehicles independently manage their workload by taking on tasks when resources are available and delegating or skipping tasks when resources are constrained, achieving workload balance without requiring complex centralized scheduling or inter-vehicle coordination mechanisms.
Data Source
AI summary
Aspects of the disclosure provide a method for collaboratively determining an object. The method includes receiving sensor data indicating an object at a first vehicle of a group of vehicles communicating with each other, transmitting a first request including the sensor data and specifying a first task for determining the object from the first vehicle to a second vehicle of the group of vehicles, and transmitting a second request specifying a second task for determining the object from the first vehicle to a third vehicle of the group of vehicle. The first task is performed by the second vehicle to produce first intermediate data, and the second task is performed by the third vehicle based on the intermediate data produced by the second vehicle.