Technically Speaking

By embracing an ML-first approach, Motional is building next-generation ML-based data mining systems inspired by the teacher-student paradigm, where powerful offline models are used for preparation of high-quality datasets required by the lighter, end-to-end AV models running on-car. In this blog post, we introduce Omnitag, an ML-Powered Multimodal Data Mining Framework that transforms the "dark matter" of autonomy into refined, ready-to-use fuel for next-generation AVs.

The ability to reason accurately about a surrounding driving scene and anticipate the behavior of other road users is a vital task required for safe and effective autonomous driving. To achieve fully autonomous driving, AV systems must be equipped with a "world model" that reasons how road users are likely to behave given observed motion states, surrounding road geometry, and vital contextual information such as turn signals, traffic lights and road signs.

The multi-object tracking module in an AV system is responsible for processing various information across a period of time, grouping them into tracks, and providing motion estimations for each track. At Motional, we design a unified tracker model to include all those components, which is flexible enough to introduce additional features such as track management and attribute prediction. This fully data-driven tracking model is also one step closer to our future of an end-to-end ML autonomy system.

By investing in a scalable shell, a high-performance state engine, a maintainable codebase, and workforce management we've created a platform that not only meets the demanding needs of our ML teams, but is also ready to evolve for future needs.

When you combine three dimensions of fused spatial data, one dimension of time samples, and multiple sets of abstract objects and temporal events, you realize you're visualizing at least four dimensions of information simultaneously. This is the fundamental complexity our data annotation platform is designed to manage.

Motional introduces their approach to machine learning and how their Continuous Learning Framework allows them to train their autonomous vehicles faster.

Motional shares how they build a world-class offline perception system to automatically label the data that will train their next-generation vehicles.

Motional's expanded open-source planning dataset will allow our industry and researchers to better understand how a driverless vehicle can find its way through a dynamic environment full of obstacles and ever-changing circumstances.

Motional is using AI to sift through mountains of vehicle data to find the unique driving scenarios needed to make AV tech smarter.

Henggang Cui explains Motional’s approach to prediction, and how we use multimodal prediction models to help reduce the unpredictability of human drivers.

Caglayan Dicle takes a look at how closed-loop testing will strengthen Motional's planning function, making the ride safer and more comfortable for passengers. 

This article explains how we're using machine learning to speed up the process of mapping public roadways prior to launching commercial passenger service. 

Motional is using Transformer Neural Networks to improve AV perception performance. 

Motional employs a technique known as fuzz testing, or fuzzing, which stress tests their autonomous vehicle software through the use of randomized, arbitrary, or unexpected inputs. 

Motional introduces PredictNet, a prediction module that gleans insight from past incidents to better predict the behavior of vehicles, people, and other agents in the driving environment, thereby increasing safety. 

By rethinking system architecture and using machine learning to analyze and process previously discarded low-level radar data, Motional is working on dramatically enhancing radar performance to the point that it rivals the point clouds produced by lidar. 

Yi Wang, Senior Principal Engineer at Motional, does a deep dive into our approach for scaling our ML pipelines, and demonstrates three example design cases.

Motional's approach for an end-to-end machine learning (ML) powered motion planning system