VoxarWild Perception

Industry R&D project in partnership with Volkswagen Trucks and Bus and Eyeflow.ai

Vehicle-to-everything (V2X) communication allows vehicles to exchange data with various elements in their environment, including other vehicles (V2V). The goal is to enhance traffic efficiency, improve road safety, and support advanced driver-assistance systems (ADAS) and autonomous driving. However, before vehicles can communicate through this channel, they must first be able to perceive important information from the outside world. The VoxarWild Perception project, funded by Embrapii in partnership with Volkswagen Trucks and Bus and Eyeflow.ai, aims to collect useful sensor data about the external driving context as well as extract human behavioral cues from pedestrians. This sensed information will then be used to improve prediction systems and enable safer V2X communications.

This one-year project, which was active from 2023 to 2024, led to the development of several proof-of-concept validations, as well as functional prototypes that are available for usage today.

Some publicly available results from this project. From left to right, we have Looking, which we briefly tested as proof-of-concept but did not follow through due to licensing questions.

2023

  1. appl.sci
    A survey on datasets for emotion recognition from vision: Limitations and in-the-wild applicability
    Willams Costa, Estefanı́a Talavera, Renato Oliveira, and 4 more authors
    Applied Sciences, 2023
    HTML

References