Multi-Antenna RF Side Detection for GPS-Denied Vehicle Pickup
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge of locating a target vehicle or rider in urban areas with blocked or attenuated GPS signals, especially in crowded environments and adverse weather conditions, leads to inefficiencies and increased CO2 emissions due to idle driving, as existing solutions like GPS and facial recognition are unreliable or invasive.
Innovation Solution
A vehicle-based Wi-Fi system using multiple antennae and CSI data processing, including amplitude difference analysis and LSTM classification, to determine the side of a target with high accuracy in both line-of-sight and non-line-of-sight conditions without requiring rider-specific data or heavy computation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS signals are used for location, then location accuracy is improved, but GPS signals are blocked by buildings and attenuated in crowded environments
Solution Approach 1:
The patent introduces RF signals as an intermediary communication medium between the vehicle and target device. Instead of relying directly on GPS satellite signals that are blocked by buildings, the system uses RF packets transmitted through the urban environment. The RF transceiver captures these packets and extracts location information, effectively mediating the location problem in GPS-denied environments.
Solution Approach 2:
The patent replaces the GPS satellite-based electromagnetic system with a ground-based RF communication system. By substituting the space-based GPS mechanism with a terrestrial RF packet transmission mechanism, the system achieves reliable location determination in urban canyons where GPS signals are blocked or attenuated.
2Measurement precision
If facial recognition is used for identification, then identification accuracy is improved, but privacy concerns arise and the system becomes invasive
Solution Approach 1:
The patent extracts only the necessary identifying information (RF packet data and channel state information) from the communication signals, discarding all other personal information. This extraction approach enables identification without capturing or storing invasive data such as facial images, thereby maintaining privacy while achieving accurate target identification.
Solution Approach 2:
The system uses the RF packets that the target device voluntarily transmits for communication purposes. The target device itself provides the identification data through its normal Wi-Fi communication, eliminating the need for active scanning or data collection from the target, thus respecting privacy while enabling identification.
3Measurement precision
If the vehicle waits for the target in crowded environments, then pickup accuracy is improved, but time is wasted and CO2 emissions increase
Solution Approach 1:
The system performs preliminary location determination using RF packet analysis before the vehicle arrives at the pickup location. By extracting channel state information and determining the target's precise position in advance, the vehicle can approach directly from the correct direction without unnecessary waiting or searching, reducing idle time and emissions.
Solution Approach 2:
The system continuously monitors RF packets and provides real-time feedback on target location and movement. This feedback enables the vehicle to dynamically adjust its approach, maintaining high pickup accuracy while minimizing idle time by responding to the target's actual position rather than waiting for confirmation.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The system achieves 95.44% accuracy in determining the target's side, reducing user frustration and CO2 emissions by enabling precise lane selection for safe and efficient pickup, while being privacy-respecting and computationally efficient.
Implementation Method 1
receive RF packets, via a second wireless connection, from a target at the location
Implementation Method 2
extract channel state information (CSI) from received signals associated with the identified packets
Implementation Method 3
determine an amplitude difference of subcarriers of the received signals between each of the multiple antennae
Data Source
AI summary
In one embodiment, a vehicle side target location method includes receiving a request, via a first wireless connection, for the vehicle to travel to a location, in response to the vehicle being less than a predetermined distance from the location, receiving RF packets, via a second wireless connection having a multiple antenna radio frequency (RF) transceiver having an identification (ID), from a target at the location, identifying packets based on the ID of the RF transceiver, extracting channel state information (CSI) from received signals associated with the identified packets, determining an amplitude difference of subcarriers of the received signals between each of the multiple antennae, filtering noise of the amplitude difference of subcarriers based on subcarrier selection to obtain multiple robust amplitude difference signals, and feeding the multiple robust amplitude difference signals to a classifier to obtain a side of the vehicle associated with the location of the target.