17 June 2024  |  Press release

Wayve unveils PRISM-1 for Advanced Autonomous Driving Simulation

Wayve unveils PRISM-1, a cutting-edge scene reconstruction model that enables realistic 4D simulations of dynamic driving scenarios. This model advances the testing and training of Wayve’s ADAS and autonomous driving technology.

  • PRISM-1 is a cutting-edge scene reconstruction model that enables realistic 4D simulations of dynamic driving scenarios. It advances the testing and training of Wayve’s ADAS and autonomous driving technology.
  • Leveraging camera-only inputs, PRISM-1 avoids traditional reliance on LiDAR and 3D bounding boxes to reconstruct accurate scene depictions and can effectively reconstruct dynamic and deformable elements like cyclists, pedestrians, brake lights, opening car doors, and road debris.
  • Accompanying PRISM-1’s launch, Wayve publicly releases WayveScenes101, a benchmark dataset of 101 diverse driving scenarios, to support the research community in developing novel view synthesis models for driving. 

LONDON – Wayve, a leader in Embodied AI for self-driving technologies, has launched PRISM-1, a novel 4D reconstruction model that enhances the testing and training of its ADAS and autonomous driving technology. PRISM-1 marks a significant leap forward in the 4D reconstruction field by enabling scalable realistic resimulations of complex driving scenes with minimal engineering or labelling input.

Initially showcased In December 2023 through its Ghost Gym neural simulator, Wayve has used novel view synthesis to create precise 4D scene reconstructions (3D in space plus time) using only camera inputs and a method that promises to revolutionizes simulation for autonomous driving by accurately and efficiently simulating the dynamics of complex and unstructured real-world environments. PRISM-1 is the model that powers the next generation of Ghost Gym simulations. Unlike traditional methods that rely on LiDAR and 3D bounding boxes, PRISM-1 utilizess novel view synthesis techniques to accurately depict moving elements such as pedestrians, cyclists, vehicles and traffic lights including precise details like clothing patterns, brake lights and windshield wipers. 

Achieving realism is critical for building an effective training simulator and evaluating driving technologies. Traditional simulation technologies treat vehicles as rigid entities and fail to capture safety-critical dynamic behaviours like indicator lights or sudden braking. PRISM-1, however, uses a flexible framework that excels at identifying and tracking changes in the appearance of scene elements over time, enabling it to precisely resimulate complex dynamic scenarios with elements that change in shape and move throughout the scene. It distinguishes between static and dynamic elements in a self-supervised manner, avoiding the need for explicit labels, scene graphs and bounding boxes to define the configuration of a busy street. This approach maintains efficiency, even as scene complexity increases, ensuring that more complex scenarios do not require additional engineering effort. This makes PRISM-1 a scalable and efficient solution for simulating complex urban environments. 

Jamie Shotton, Chief Scientist at Wayve: “PRISM-1 bridges the gap between the real world and our simulator. By enhancing our simulation platform with accurate dynamic representations, Wayve can extensively test, validate and fine-tune our AI models at scale. 

“We are building Embodied AI technology that generalizes and scales. To achieve this, we continue to advance our end-to-end AI capabilities, not only in our driving models but also through enabling technologies like PRISM-1. We are also excited to publicly release our WayveScenes101 dataset, developed in conjunction with PRISM-1, to foster more innovation and research in novel view synthesis for driving.”

Accompanying PRISM-1’s launch, Wayve is also releasing its WayveScenes101 Benchmark, a dataset comprising 101 diverse driving scenarios from the UK and US, including urban, suburban, and highway scenes under various weather and lighting conditions. Wayve aims for this dataset to support the AI research community in advancing novel view synthesis models and the development of more robust and accurate scene representation models for driving.

For more information on PRISM-1, please check out Wayve’s blog.

Back to top