Technology

Case Study: Using Synthetic Data to Improve Traffic Sign Classification and Achieve Regulatory Compliance

April 20, 2023
This case study explores whether synthetic traffic sign data can improve a perception model’s traffic sign classification performance. Its results show that synthetic data reduces the need for real training data by 90%.
Read more →

Applied’s Log Management Handbook: Log-Based Test Cases (Part 3)

November 10, 2022
Part 3 of our log management handbook series explains how autonomy programs can reproduce and resolve issues by creating simulation test cases from real-world drive data.
Read more →

Applied’s Log Management Handbook: Drive Data Exploration (Part 2)

November 1, 2022
Part 2 of our log management handbook series introduces readers to drive data exploration with a particular emphasis on surfacing interesting events for review.
Read more →

Applied’s Log Management Handbook: Powering Autonomy With Drive Data (Part 1)

October 19, 2022
Drive data is one of the most essential building blocks of autonomous systems development. Our log management handbook discusses the journey of a drive data file from inception to storage and lays out common practices for autonomy programs across industries.
Read more →

Announcing Synthetic Datasets for ML Applications

August 9, 2022
Synthetic Datasets empower users to improve the robustness of their machine learning (ML) models with camera, lidar, radar, and other sensor data.
Read more →

Applied Intuition’s V&V Handbook: Analytics and Reporting (Part 3)

August 2, 2022
Part 3 of our verification and validation (V&V) handbook series discusses how autonomy programs typically measure coverage and analyze their system’s performance depending on their development stage.
Read more →

Applied Intuition’s V&V Handbook: Scenario Creation and Test Execution (Part 2)

July 21, 2022
Part 2 of our verification and validation (V&V) handbook series explains how autonomy programs typically approach scenario creation and test execution depending on their development stage and how they can address common challenges.
Read more →

Applied Intuition’s V&V Handbook: Verification and Validation at Different Stages of ADAS and ADS Development (Part 1)

July 12, 2022
Safely developing and deploying autonomous systems is a challenging task. Applied Intuition’s V&V handbook aims to provide autonomy programs with an active resource to safely develop, test, and deploy autonomous systems for commercialization.
Read more →

Large-Scale Simulation and Validation With CARLA

February 8, 2022
Applied’s continuous integration and verification & validation tools, Orbis and Basis, integrate with CARLA simulator to help AV teams scale and validate their development.
Read more →

Why Suspension Models Are Important for Off-Road AV Simulation

January 11, 2022
Suspension models are crucial for off-road simulation because off-road vehicles often need to handle uneven terrain. Simulations that don’t account for a vehicle’s suspension might lead to results that aren’t fully representative of the real world.
Read more →

Motional’s nuScenes Dataset Now Searchable Through Applied Intuition’s Strada

December 13, 2021
Researchers and development teams can query the nuScenes dataset for specific scenes, events, and anomalies to create curated training datasets or verify and validate on-road issues.
Read more →

Case Study: Improving Object Detection Performance by Leveraging Synthetic Data

December 13, 2021
Applied Intuition’s perception team has conducted a case study that uses Spectral synthetic data to improve a perception algorithm’s object detection performance on underrepresented classes in a real-world dataset.
Read more →

Build Vs. Buy: Strategic Decisions in Procuring Tools for ADAS and AV Development

November 8, 2021
Autonomous vehicle (AV) engineering organizations face the dilemma of building versus buying when it comes to developer tools. This blog post will lay out some of the options that autonomy teams consider when choosing the right tools for their testing and development process.
Read more →

Using Re-Simulation to Verify an AV Stack Against Disengagements

October 18, 2021
This blog post discusses how open-loop log replay and re-simulation evaluate the performance of perception and localization systems and motion planning and control systems, respectively, to comprehensively verify and validate a full AV stack against disengagements.
Read more →

A Primer on ASAM OpenSCENARIO V2.0 and Its Importance for ADAS and AV Development

September 27, 2021
Abstract, logical, and concrete scenarios play an essential role in testing, validating, and certifying the safety of automated driving systems. OpenSCENARIO V2.0 will make it easier to create and transfer abstract scenarios between tools.
Read more →

Announcing Applied’s Re-Simulation Tool Logstream

September 21, 2021
The log re-simulation tool Logstream enables AV and ADAS engineering teams to analyze disengagement events, evaluate stack performance, and bring safe autonomous systems to market faster.
Read more →

How AV and ADAS Systems Engineers Can Use Public Road Drive Data to Verify Requirements Automatically

September 13, 2021
It has been historically difficult to verify requirements using public road drive data. Applied Intuition’s “scenario search” automates the error-prone and time-consuming work involved in existing approaches.
Read more →

Introducing Basis and Strada: Tools for V&V and Drive Data Exploration

September 9, 2021
The V&V platform Basis and the drive data exploration tool Strada allow AV and ADAS engineering teams to prepare for long-tail events and deploy safe automated driving systems to the public.
Read more →

A Computationally Efficient, Machine Learning-Based Approach to Identify Failure Cases for AV Validation

July 1, 2021
An efficient approach to find failing cases in exponentially large parameter spaces is required. Learn about an ML-based approach to complement your existing validation workflows.
Read more →

Approaches to Simulating Autonomous System Coordination and Task Allocation in Multi-Robot Systems

May 10, 2021
There are increasingly more commercial applications for autonomous multi-robot systems. We discuss examples of use cases and testing considerations to ensure the safety and advancement of the system algorithms.
Read more →

Achieving Higher Fidelity Sensor Models with Ray Tracing and Vulkan API

April 5, 2021
The Applied team is building Vulkan rendering capabilities. Learn how ray tracing can improve the fidelity and performance of sensor data for perception system development.
Read more →

From Research to Production: Strategies for Perception Simulation (Part 2 of 2)

March 29, 2021
The Applied team evaluates the common perception simulation approaches against five key requirements. Simulated lidar can be almost indistinguishable from real data through detailed sensor validation.
Read more →

From Research to Production: Strategies for Perception Simulation (Part 1 of 2)

March 25, 2021
There are multiple forms of perception simulations. Which approach is the most suitable for training and validation for production deployment?
Read more →

Open Standards and Their Critical Role in AV/ADAS Development

March 11, 2021
Applied is a supporter of open standards for simulation tests and is an active participant in the ASAM projects. Here’s a look at how Applied works with the standards and addresses their limitations today.
Read more →

Overcoming Rigorous Verification Challenges in Autonomous Systems Development

February 1, 2021
While it is tempting to use formal methods ‘for everything’, it is more effective to use the right mix of methods at the required level of verification and validation for developing and deploying L3+ autonomous systems.
Read more →

Approaches to Requirements Management and Traceability in ADAS & Autonomous Vehicle Development

December 17, 2020
The Applied team discusses approaches taken by traditional and ML-driven companies to manage increasingly more complex requirements throughout the AV development lifecycle.
Read more →

Quantifying Known and Unknown Metrics in ADAS and AV Development

November 4, 2020
With large volumes of data generated in AV development from drives and simulations, making effective use of data can be challenging. The Applied team discusses how to effectively use data to track progress on known requirements and uncover gaps in coverage.
Read more →

Improving Perception Algorithms and Reducing Cost Per Bounding Box Through Synthetic Data

September 12, 2020
Annotating and curating datasets from the real-world driving data is a common approach for training AV algorithms, yet it is expensive, biased, prone to errors, and limited in scale. Learn how to use synthetic data to overcome these challenges.
Read more →

Progression, Regression, and Modular Testing for Level 2 to Level 4 Autonomous Vehicle Systems

August 17, 2020
No company is too early to implement simulation and automated CI testing regardless of their stage of autonomous vehicle development. The Applied team discusses best practices for setting up tests to speed up the deployment of autonomous algorithms.
Read more →

From Procedural Generation to Determinism: Approaches to Simulating Synthetic Perception Data for Autonomous Driving

July 6, 2020
Sensor simulation for autonomous driving systems is an exceedingly difficult task, requiring high-fidelity simulations that could be processed in real-time. There are techniques that could be used to accurately test your perception system.
Read more →

Using Domain Coverage to Measure an Automated Driving System’s Performance in a Given ODD

June 4, 2020
With the limitations of requirements and scenario coverage approaches, domain coverage measured on ODDs may be a practical approach to evaluate progress in the autonomy roadmap.
Read more →

ISO 26262, SOTIF, and Simulation in Autonomy Systems

May 11, 2020
We discuss how simulation fits into frameworks for building safety critical systems, recent standardization efforts around this technology, and the requirements for simulation tools to support this use case.
Read more →

Procedural Generation With Applied Intuition and Toyota

November 8, 2019
Toyota Research Institute - Advanced Development uses Applied’s synthetic data creation capabilities to develop realistic environments for the Lexus LF30 virtual reality experience at the Tokyo Motor Show.
Read more →

Frameworks for Estimating Large-Scale Autonomous Vehicle Deployments

August 10, 2019
There might be a particular sequence of events that must occur to enable mass commercial deployment of self-driving cars.
Read more →