![A man holds the hands of two small children while crossing a road](/sites/default/files/2023-12/techspeakssv%20thumb.jpg)
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.
![An illustration showing how a Motional AV analyzes how another vehicle may move next](/sites/default/files/2023-11/TS_Prediction_v2_Thumb.png)
Technically Speaking: Improving Multi-task Agent Behavior Prediction
Motional's PredictNet approach to prediction uses machine learning principles and a multi-task learning architecture to more accurately predict the future behaviors of surrounding agents.
![Fuzz Test](/sites/default/files/2023-08/fuzzing.jpg)
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.
![Bird's Eye View (BEV)](/sites/default/files/2023-06/BEV_0.jpg)
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.
![An image showing the internal map a robotaxi uses to drive safely](/sites/default/files/2023-05/technicallyspeaking_planning_roadmarkings_thumb.jpg)
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.
![Thumbnail showing closed loop testing](/sites/default/files/2023-02/Screenshot%202023-02-07%20093505.png)
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.
![Motional President & CEO Karl Iagnemma stands in front of two IONIQ 5 robotaxis inside a garage addressing a seated crowd](/sites/default/files/2022-09/20220908_101254.jpg)
Motional Walks Transportation Planners Through Progress on AVs
Motional President and CEO Karl Iagnemma, Chief Technology Officer Laura Major, and others told NACTO attendees about the company’s driverless technology, approach to safety and accessibility, and the IONIQ 5 robotaxi.
![Path drawing thumb](/sites/default/files/2022-09/PathDrawing%20thumb.jpg)
A Path Forward: Using AI to Improve Remote Vehicle Assistance for AVs
As Motional’s robotaxis drive more, our vehicle assistance system will use machine learning principles to become smarter and require less human intervention over time.
![Thumbnail of Motional delivery vehicle](/sites/default/files/2022-09/UberEats-engineeringdelivery-1-031522%20thumb.jpg)
Engineering For Delivery: How Motional designed the IONIQ 5 robotaxi to move people – and goods
Motional engineers and product designers are creating an AV capable of serving dual purposes without losing functionality for either.
![Driverless Ed Chapter 3](/sites/default/files/2022-09/Driverless%20Ed%20Chapter%203.jpg)
DriverlessEd Chapter 3: Enjoying the Driverless Ride
Chapter 3 of Motional's DriverlessEd series explains how AV companies like Motional are using research to understand what makes a ride comfortable, the types of features passengers expect, ways to make the vehicles accessible, and even how AVs can communicate with people.
![Thumbnail for the robotaxi app](/sites/default/files/2022-09/waitforme%20app_thumb.png)
"Wait For Me": Improving robotaxi accessibility through the push of a button
Motional researchers are developing an app-based feature that lets riders with disabilities ask their robotaxi for more time while being picked up.
![A Motional vehicle operator sits in the backseat of an IONIQ 5 robotaxi working on a tablet](/sites/default/files/2022-09/ride%20quality%20VO%20-thumb.png)
Enjoying The Driverless Ride: How Motional Is Creating A Ride Quality Metric For Its AVs
Motional is learning how to measure whether a ride in a driverless vehicle feels safe, comfortable, or both.
![thumb video cut in prediction](/sites/default/files/2022-09/cutin_2.png)
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.
![Thumb data mining chart](/sites/default/files/2022-09/Screen%20Shot%202022-01-14%20at%2011.29.31%20AM%20%281%29.png)
Technically Speaking: Mining For Scenarios To Help Better Train Our AVs
Motional is using AI to sift through mountains of vehicle data to find the unique driving scenarios needed to make AV tech smarter.