Technically Speaking: Second-Stage Vision Adds Needed Context to Unique Scenarios
Motional has developed a Second-Stage Vision Network that uses machine learning principles to add important context to our object classifications -- additional fine-grain classification then flows downstream improving our perception, prediction, planning, and control substacks.
Technically Speaking: How Continuous Fuzzing Secures Software While Increasing Developer Productivity
Motional uses continuous fuzzing to make sure that our software is as safe and secure as possible before deploying it – or if there is a glitch, that the system can handle it gracefully.
Minds of Motional: Pat Karnchanachari
Pat Karnchanachari, a Senior Engineer with Motional and our nuPlan™ Team Lead, talks about why he loves working in the AV space, his favorite project, and how he decompresses.
Technically Speaking: Improving AV Perception Through Transformative Machine Learning
Transformer Neural Networks are receiving increased attention about how they can improve AI-driven technology. Our latest Technically Speaking blog explores how Motional has been using Transformers to make our perception function better.
Technically Speaking: Using Machine Learning to Map Roadways Faster
Motional's latest Technically Speaking blog explains how we're using machine learning to speed up the process of mapping public roadways prior to launching commercial passenger service.
Technically Speaking: Closing The Loop To Travel Back And Help AVs Plan Better
Motional's latest Technically Speaking blog focuses on Planning, and how using closed-loop training will help refine the modeling AVs use to create a safe path forward quicker.
Winning Together: Motional's Publicly Released AVCDL Kickstarts Building Security Into AV Products
Motional is making its Autonomous Vehicle Cybersecurity Development Lifecycle (AVCDL) publicly available for others to review and adopt, in order to help the industry secure against cybersecurity threats.
Motional Opens New Singapore Operations Facility, Expands International Testing
Motional recently completed a multi-million dollar expansion project that doubled the amount of office and garage space located in the heart of Singapore’s high-tech district, growing the company's R&D and Operations footprint in the country
Polar Stream: Simultaneous Object Detection and Semantic Segmentation Algorithm for Streaming Lidar
Motional’s research has unlocked an approach to streaming object detection that reduces latency while increasing accuracy, giving AVs even better data needed to make safe decisions.
Technically Speaking: Predicting the future in real time for safer autonomous driving
Motional uses multi-modal prediction models to more accurately predict and anticipate what agents around our AVs are going to do next.
Technically Speaking: Auto-labeling With Offline Perception
Motional is building a world-class offline perception system that will automatically label the data required to train our next-generation vehicles.