Student Work: Improving on Traffic Lights & Helping the Visually-Impaired - Livestream

3D Navigation Method for the Visually Impaired

The visually impaired must currently rely on navigational aids to replace their sense of sight, like a white cane or GPS(Global Positioning System)-based navigation, both of which fail to work well indoors. The white cane cannot be used to determine a user’s position within a room, while GPS can often lose connection indoors and does not provide orientation information, making both approaches unsuitable for indoor use.Therefore, this research seeks to develop a 3D-imaging solution that enables contactless navigation through a complex indoor environment. The developed device consists of a simple IMU, radio transceiver, and microcontroller dev board. The localization process uses different types of feature extractors on images, and the extracted features are converted to positions and orientation data through dense
layers. The device can pinpoint a user’s position and orientation with 31% less error compared to previous approaches while requiring only 53.1% of the memory, and processing 125% faster. The object detection process works with a sparsely 3D convolutional neural network, which functions similar to a 2D convolutional network, but with sparsity to reduce processing and memory requirements. The device can also detect obstacles with 60.2% more accuracy than the previous state of the art models while requiring only 41% of the memory and processing 260% faster. When testing with human participants, the device allows for a 94.5% reduction in collisions with obstacles in the environment and allows for a 48.3% increase in walking speed, showing that my device enables safer and more rapid navigation for the visually imapired. All in all, this research demonstrates a 3D-based navigation system for the visually impaired. The approach can be used by a wide variety of mobile low-power devices, like cell phones, ensuring this research remains accessible to all. In this presentation, I will explain how the developed device functions in greater detail, the process of selecting components, as well as one possible application where my work could be used.

Demonstration Video: https://youtu.be/znhVKZAjXq8

Speaker: Stanley Shen, Los Gatos High School

Smart Traffic Lights

Traffic lights that operate on a set of fixed schedules and do not adapt to traffic conditions in real time result in inefficient traffic flow and increased wait times. With the invention of self-driving cars, there is an opportunity to improve the traffic flow by communication between the car and the intersection.

This talk will describe the design of a smart traffic light controller for intersections and a portable device for cars that will enable wireless car-to-intersection (C2I) and intersection-to-intersection (I2I) communication. Then, I will describe two new traffic light algorithms that adapt to current traffic conditions: a) one that determines light phases based on the number of cars queued at the intersection and b) a second one that also takes into account cars arriving from neighboring intersections using I2I communication. I will present results of a simulation based evaluation of the new algorithms compared to timed traffic intersections. Finally, I will provide a video demonstration showing the traffic light controller and portable car device models implementing both the timed and smart intersections.

Speaker: Aman Chandra, Challenger SchoolShawnee

Register at weblink for connection information