Personal Mobility Vehicle Sidewalk Detection and Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Personal mobility vehicles (PMVs) often operate in densely populated areas, increasing the likelihood of accidents and undesired interactions with pedestrians and other vehicles, and existing technologies lack effective solutions to mitigate these risks by detecting suitable travel corridors.
Innovation Solution
A terrestrial sensing system equipped with sensors such as accelerometers, gyroscopes, GPS, cameras, and LIDAR, which processes data using machine learning algorithms to determine the type of travel surface and adjust PMV operations accordingly, such as limiting speed or preventing operation on sidewalks during high pedestrian density.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If PMVs operate in densely populated areas to provide rapid mobility, then productivity and accessibility are improved, but the risk of accidents and undesired interactions with pedestrians increases
Solution Approach 1:
The system performs preliminary detection of travel corridor types using sensors (cameras, LIDAR, accelerometers) and machine learning algorithms before the PMV enters a potentially hazardous area. This advance identification allows the system to prepare appropriate safety measures, such as adjusting speed limits or alerting the rider, thereby preventing accidents before they occur while maintaining rapid mobility in safe zones
Solution Approach 2:
The system continuously monitors the environment using onboard sensors and provides real-time feedback about the detected travel corridor type to the PMV's control system. This feedback loop enables dynamic adjustment of operating parameters (speed, routing) based on the current environment, allowing rapid mobility in safe areas while automatically reducing risk in densely populated or restricted zones
2Reliability
If sensors and machine learning algorithms are integrated into PMVs to detect travel corridors, then safety is improved, but device complexity increases
Solution Approach 1:
The safety system is divided into modular functional components: sensor modules (cameras, LIDAR, accelerometers), data processing module (machine learning algorithms), and control module (speed adjustment, routing). Each module performs a specific function and can be independently optimized or replaced, reducing overall system complexity while maintaining high safety standards
Solution Approach 2:
The sensor system is designed to serve multiple functions: detecting travel corridor types, measuring speed, determining location, and identifying pedestrian presence. By making the sensor suite multi-functional, the patent reduces the need for separate dedicated sensors for each function, thereby improving safety without proportionally increasing device complexity
Data Source
AI summary
The disclosed embodiments relate to detecting sidewalk riding by a personal mobility vehicle (e.g., an electric scooter). For example, a method includes collecting sensor data (e.g., vibration data of an accelerometer) generated by the scooter while traveling on a surface of a travel pathway. The method further includes identifying a surface type by processing the collected sensor data with a computer model that can distinguish among different surface types, and determining that the travel pathway is unsuitable (e.g., a sidewalk) for the scooter based at least in part on the identified surface type (e.g., a pattern of concrete sections). In response to determining that the travel pathway is a sidewalk, causing the personal mobility vehicle to assist the user in navigating the personal mobility vehicle, alter a mobility operation of the personal mobility vehicle, or notify a surrounding area of a presence of the personal mobility vehicle.