Today we are sharing a new approach to prediction in dynamic urban driving scenes, one of driving's hardest problems. Our algorithm, FIERY, is able to predict multimodal futures in bird's eye view from monocular cameras. Blog, research paper and code here: wayve.ai/blog/fiery-fut…
We use the problem's geometric structure to lift monocular perception features to 3D and apply a conditional variational auto-encoder trained end-to-end for modelling the future distribution. 
Our model can predict complex multi-agent behaviours in urban environments, such as navigating double-parked vehicles or a U-turn of the vehicle in front of us.
If you're interested in building the most adaptable and intelligent autonomous driving system with an end-to-end deep learning approach, get in touch with us here: wayve.ai/join-us/
• • •
Missing some Tweet in this thread? You can try to
force a refresh
