Competitions

Waymo Open dataset challenge

We're now accepting submissions for Waymo’s first-ever autonomous driving challenges! There’s a wealth of autonomous driving data and prizes to incentivize your research efforts. Sub-challenges include 2D/3D detection/tracking and a domain adaptation task. Please visit https://waymo.com/open/challenges.

Berkeley interaction motion prediction

It is a consensus in both academia and industry that behavior prediction is one of the most challenging problems blocking the realization of fully autonomous vehicles. One of the reasons is the lack of benchmarks and appropriate evaluation metrics. Therefore, we organize a prediction challenge based on the INTERACTION dataset, i.e., the INTERACTION-Dataset-based PREdicTion Challenge (INTERPRET) which offers multiple evaluation metrics. The first round of the competition includes three tracks: a regular track, a data-efficiency track, and a transfer learning track. Participants are welcome to attend competitions via multiple tracks. For more details, please visit the challenge website at http://challenge.interaction-dataset.com/prediction-challenge.

NightOwls Detection Challenge

Pedestrian detection at night from a RGB camera is an under-represented yet very important problem, where current state-of-the-art vision algorithms fail. Computer vision methods for detection at night have not received much attention, despite the fact they are a critical building block of many systems such as safe and robust autonomous cars. The competition aims to bridge this gap by utilizing the NightOwls dataset – the dataset consists of 279k fully-annotated night images captured in three countries in real traffic by an industry-standard camera, making the data as realistic as possible.

https://www.nightowls-dataset.org/nightowls-competition-2020