Immersive Driving Assistance with LPVIZ

22/02/2024
Blog, Product, カテゴリーなし, Use Cases

How LPVIZ Augments Driving Reality

Going beyond a simple screen replacement, LPVIZ is an augmented reality driving assistance solution for the car. It allows displaying related content to a driver or passenger in 3D, superimposed to reality. Content can be placed anywhere inside the car, such as a virtual speedometer over the dashboard, and anywhere outside of the car, such as point-of-interest markers or navigation guidance.

The video on top of this post shows what a drive around the block in Azabujuban, Tokyo with LPVIZ looks like. A virtual dashboard is projected onto the center console of the vehicle. Arrows on the ground show lane guidance to the driver. Red Google Maps-style markers show points of interest. The virtual dashboard stays fixed to the same location in the car, even when the vehicle turns. The navigation arrows move smoothly and the point-of-interest markers are globally anchored.

Perfectly Tuned Components

LPVIZ consists of several components that all have to interact perfectly to create a compelling and safe augmentation experience. The below illustration shows a block diagram of how the hardware components are connected.

Accurate tracking is required to display useful content to the driver: the HMD pose in the local car coordinate system and the vehicle pose in a globally anchored frame. Precise calibration of all components of the solution is essential to provide the highest visual fidelity and driver safety. Our LPVIZ product makes all parts of the system available in a compact form factor, ready to be integrated with any vehicle.

The Past, Present and the Future

In the current development stage we’re focusing on the most essential aspects of the solution: displaying a virtual dashboard, navigation information and points-of-interest. While this is our proprietary content, we’re opening our software to work with 3rd party developers to create their own content building on our platform.

Currently we’re offering LPVIZ as a B2B solution for prototyping, design and research. However, we’re working on reducing system complexity to make it work as a consumer facing automotive after-market solution to be released later this year.

Towards a Consumer Product

We are very proud of the progress our team has made in the past months. We’re moving closer to making our vision of an augmented reality driving assistance system a reality for everyone. One very important take-away from our recent developments is that it’s indeed possible to provide real utility to the driver using technology that is readily available. It might still be early days, but we’re edging towards a product that could appeal to a wider consumer market. This is just the beginning.

Machine Learning for Context Analysis

06/08/2019
カテゴリーなし

Deterministic Analysis vs. Machine Learning

Machine learning and artificial intelligence (AI) are important methods that allow machines to classify information about their environment. Today’s smart devices integrate an array of sensors that constantly measure and save data. On the first thought one would image that the more data is available, the easier it is to draw conlusions from this information. But, in fact larger amounts of data become harder to analyze using deterministic methods (e.g. thresholding). Whereas such methods by themselves can work efficiently, it is difficult to decide which analysis parameters to apply to which parts of the data.

Using machine learning techniques on the other hand this procedure of finding the right parameters can be greatly simplified. By teaching an algorithm which data corresponds to a certain outcome using training and verification data, analysis parameters can be determined automatically or at least semi-automatically. There exists a wide range of machine learning algorithms including the currently very popular convolutional neural networks.

Context analysis setup overview

Context Analysis

Many health care applications rely on the correct classification of a user’s daily activities, as these reflect strongly his lifestyle and possibly involved health risks. One way of detecting human activity is monitoring their body motion using motion sensors such as gyroscopes, accelerometers etc. In the application described here we monitor a person’s mode of transportation, specifically

  1. Rest
  2. Walking
  3. Running
  4. In car
  5. On train

To illustrate the results for deterministic analysis vs. machine learning approach we first implemented a state machine based on deterministic analysis parameters.

Deterministic approach overview

The result is a relatively complicated state machine that needs to be very carefully tuned. This might have been because of our lack of patience, but in spite of our best efforts we were not able to reach detection accuracies of more than around 60%. Before spending a lot more time on manual tuning of this algorithm we switched to a machine learning approach.

Machine learning approach overview

The eventual system structure looks noticeably simpler than the deterministic state machine. Besides standard feature extraction, a central part of the algorithm is the data logging and training module. We sampled over 1 milion of training samples to generate the parameters for our detection network. As a a result, even though we used a relatively simple machine learning algorithm, we were able to reach a detection accuracy of more than 90%. A comparison between ground truth data and classification results from raw data is displayed below.

Context analysis algorithm result

Conclusion

We strongly belief in the use of machine learning / AI techniques for sensor data classification. In combination with LP-RESEARCH sensor fusion algorithms, these methods add a further layer of insight for our data anlysis customers.

If this topic sounds familiar to you and you are looking for a solution to a related problem, contact us for further discussion.

IMUcore Sensor Fusion

06/08/2019
Use Cases, カテゴリーなし

Introducing IMUcore

IMUcore is the central algorithm working inside all LP-RESEARCH IMUs. It collects orientation data from several sources and combines them into fast and drift-free tilt and direction information. To work with any type of MEMS sensor, various online and offline calibration methods have been implemented to guarantee high quality data output. The algorithm is very versatile and performance-saving. It can be implemented on embedded MCUs with minimum power consumption.

IMUcore is now available as a solution from LP-RESEARCH. Please contact us here for more information or a price quotation.

Overview of embedded sensor fusion in LPMS devices

Sensor Fusion Filter Overview

IMUcore uses gyroscope data as basis information to calculate orientation. Errors introduced through measurement noise are corrected by accelerometer and compass data. Optionally the sensor fusion can be extended with an optical (or other) tracking system to additionally provide position information.

All aspects of the IMUcore algorithm in one image

If this topic sounds familiar to you and you are looking for a solution to a related problem, contact us for further discussion.