Secondary AV Sensor Sharing for Occluded Route Planning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous vehicles face difficulties in navigating areas with occlusions, as their sensors may lack the necessary field of view, leading to incomplete or inaccurate data for tasks like left-hand turns and navigating narrow streets, where occlusions block or partially obscure essential information.
Innovation Solution
A system where a second autonomous vehicle, positioned at a different location, provides sensor data to the first autonomous vehicle to assist in navigating occlusions, enhancing the first vehicle's field of view and enabling safer navigation by sharing raw or processed sensor data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If autonomous vehicles rely solely on their own sensors, then device complexity is reduced, but measurement precision deteriorates in occluded areas
Solution Approach 1:
The patent introduces a intermediary vehicle as a mediator that captures sensor data from occluded areas and transmits it to the ego vehicle. This intermediary vehicle acts as a mobile sensor platform that fills the gap between the ego vehicle's limited field of view and the need for complete environmental awareness, resolving the contradiction by externalizing the sensing capability rather than adding complex sensors to the ego vehicle itself
Solution Approach 2:
The patent merges the sensing capabilities of multiple vehicles (ego vehicle and intermediary vehicle) into a unified perception system. By combining sensor data from multiple sources and locations, the system achieves comprehensive environmental awareness that exceeds what any single vehicle could obtain alone, improving measurement precision without requiring each individual vehicle to have complete sensing coverage
2Measurement precision
If autonomous vehicles use multiple sensors to improve field of view, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent transitions from a single-vehicle sensing model to a multi-vehicle sensing model, adding a spatial dimension to the sensing architecture. By deploying sensors across multiple vehicles at different locations, the system achieves three-dimensional environmental coverage, allowing detection of occluded areas that would be invisible from any single viewpoint, thereby improving occlusion detection accuracy without requiring each vehicle to have omnidirectional sensors
3Reliability
If autonomous vehicles collect more sensor data, then reliability improves, but loss of time increases due to data processing
Solution Approach 1:
The patent extracts and transmits only the critical sensor data related to occluded areas from the intermediary vehicle to the ego vehicle, rather than transmitting all sensor data. This selective data extraction focuses computational resources on the most relevant information for safe navigation, improving reliability by ensuring critical data is available while minimizing time loss through reduced data processing requirements
Data Source
AI summary
Aspects of the disclosed technology provide solutions for improving object detection and in particular, for improving object detection by an autonomous vehicle (AV) perceptions stack. In some aspects, a process of the disclosed technology can include steps for receiving first sensor data corresponding with an environment around the first vehicle, wherein the first sensor data represents one or more objects in the environment, receiving second sensor data corresponding with the environment around the first vehicle, and formulating a navigation route, by the first vehicle, based on the one or more occluded objects in the environment. Systems and machine-readable media are also provided.