Is Apple leading the AR revolution? Unity Technology Open Day x Rokid, talk about the next generation of human-computer interaction new route

The milestone of AR development is engraved with a revolution in the spatial computing era triggered by Apple. The immersive space created by Vision Pro is bringing users a new human-computer interaction experience. For example, it breaks through the limitations of traditional displays. When users browse apps, they can simply look at them and pinch their fingers to select. Drag and click anywhere in the air.

In fact, this is also the direction Rokid has been exploring - integrating people, the real world and the virtual world in a more natural and real way.

At the Rokid Open Day in March this year, Rokid released a new generation of self-developed AR space operating system-YodaOS-Master: based on Rokid Max Pro glasses, open your palm, and the menu will immediately appear in front of you. Click the icon to enter the application and enjoy a flexible and flexible spatial multi-screen interactive experience. Among them, it is the first in the industry to realize capabilities such as SLAM and 3D bare-hand interaction based on a single camera. This new technical route has attracted attention and heated discussions in the industry since its release.

Today, one of the most important annual ceremonies for Chinese developers, the "2023 Unity Technology Open Day", was held for the first time in Beijing. Rokid attended this event. At the meeting, Shi Wenfeng, chief engineer of Rokid system R&D, gave a speech titled "Rokid YodaOS-Master System Introduction and Application Development and Implementation", sharing this much-anticipated technical route, as well as Rokid's latest technological development, and on-site development The researchers had in-depth exchanges and discussions.

Rokid’s new generation of self-developed space AR system

The industry’s first single-camera SLAM technology

At today's game forum, Shi Wenfeng, chief engineer of Rokid system research and development, combined with many years of rich experience in AR industry technology research and development, introduced the much-anticipated YodaOS-Master system to on-site developers, as well as the technical thinking behind Rokid.

Focusing on the five aspects of perception, understanding, interaction, presentation, collaboration and digital creation, YodaOS-Master has made huge upgrades in many aspects such as chip optimization, hardware design, software architecture, AR algorithms and creation tools, or Currently the most complete set of space operating systems for the AR era.

Based on Rokid Max Pro glasses, it is the first to realize SLAM, 3D bare-hand interaction, first-person perspective sharing, visual positioning VPS and other capabilities based on a single camera. It can support multi-tasking, space creation and other AR experiences, providing a more lightweight , Pratt & Whitney AR glasses bring unlimited possibilities.

At the beginning of the birth of the YodaOS operating system, Rokid has adhered to a point of view, empowering developers to release imagination and create value through the YodaOS operating system.

Shi Wenfeng said, "The YodaOS-Master operating system uses a modular approach to 'package' multiple core technologies including Rokid speech recognition, gesture recognition, SLAM, etc., to form an SDK for developers to develop efficiently, such as SDK for Unity allows Unity developers to quickly use Rokid core technology for development."

Rokid has always been committed to a more natural AR interactive experience. Compared with traditional 2D gesture recognition, 3D gesture recognition is more challenging. Teacher Wenfeng focused on the monocular 3D gesture recognition technology currently used by Rokid, which is based on the underlying system capabilities of YodaOS-Master.

Based on deep learning algorithms and a large amount of experimental data, Rokid's self-developed monocular 3D gesture algorithm can reconstruct hand posture parameters in real time on the mobile terminal, including hand 6DoF, hand joint points 26DoF, and Hand Mesh information, providing AR Gesture interaction provides a good algorithm foundation.

Currently, Rokid's gesture recognition can realize a variety of operations in 3D space, including point, pinch, grab, hold, drag, pull, etc., which can fully meet the needs of AR interactive applications. In the case of the Rokid Max Pro, simply put on the headset and extend your hand to bring up the menu in front of your palm.

It is worth mentioning that Rokid’s AR space experience integrating software and hardware has been implemented in many scenes across the country, including the country’s first Yuanverse block project based on AR glasses—Hangzhou Wensan Yuanshi AR digital living block, The first AR glasses navigation solution based on monocular vision SLAM in the cultural tourism industry in China - Dunhuang AR Smart Guide, and the country's first enterprise AR digital exhibition hall created by DingTalk and Rokid, etc.

Ruoqi Digital People AIGC

New upgrade of multi-modal interactive experience

With the accelerated development of the AI ​​era, the development trend of human-computer interaction is multi-modal interaction. In the future, to satisfy people's deeper needs, they need to be more than just keyboard interaction, touch interaction, voice interaction and other methods.

Just imagine, if you want to listen to music while working, you need to first wake up the speaker through voice or touch interaction, and then open the office software through keyboard interaction. If you have a digital artificial assistant, everything becomes easier. You only need to issue a single command to complete both tasks at the same time.

This is also one of the reasons why Rokid is an AI digital human. Shi Wenfeng said that AI digital human technology can connect all the capabilities of the system, including voice assistant AI digital human, SLAM, 3D gestures, 6DOF spatial audio and other Rokid core technologies, thereby bringing users a richer human-computer interaction experience.

Currently, the "Ruoqi" digital human created by Rokid has been fully connected to AIGC. Users can summon "Ruoqi" at any time and discuss any interesting topics with this virtual assistant.

Shi Wenfeng introduced that what is behind this is the AIGC multi-modal digital intelligence driven model, which uses self-developed algorithm technologies such as ASR, NLP, and TTS to drive "Ruoqi" to produce accurate facial expressions, voice expressions, and body movements. And the performance is more real, natural and smooth.

Rokid empowers developers in all aspects

Together we welcome the next era of human-computer interaction

In the future, as AR, MR and other technologies become increasingly mature, there will be unlimited space for innovation in various scenarios such as movie viewing, gaming, office work, and education. The reconstruction of multiple ecological contents urgently requires developers to bring more breakthroughs and innovations.

Unity Technology Open Day is one of the most important annual interactive festivals for Chinese developers. Through several offline tours every year, it builds a technology exchange platform for the creator group, conveys the path of technology evolution, and creates a diverse and active developer community. Community atmosphere, while listening to the voices of developers, empowering content innovation and application extension of real-time 3D technology.

As a leader in the AR industry, Rokid participates in promoting the prosperity of the industry. At the day's event, in addition to bringing the latest technology sharing speeches, Rokid also set up a booth area on site, bringing Rokid's latest AR products and ecological construction scenarios for on-site developers to experience and help them understand Rokid more intuitively. The latest technology and ecology.

In recent years, Rokid has been committed to empowering more developers, creating a dedicated AR open platform (ar.rokid.com), launching the "Ruoqi Space Station" developer assistance program, and holding global AR Application development competitions, etc., encourage developers to participate in ecological co-construction and promote the prosperity of the AR ecosystem.

Wen Feng introduced that Rokid’s “Ruoqi Space Station” developer assistance program tailored for developers provides comprehensive support to developers in terms of hardware equipment, algorithm capabilities, development support, and marketing promotion. At the same time, Rokid has joined forces with several industry leading companies and VCs to establish a RMB 1 billion ecological intelligent investment alliance to directly invest in outstanding developers.

Rokid not only provided strong support to developers, but also successfully hosted the first Global AR Application Development Competition and awarded 11 significant prizes to global developers. Rokid officially launched the first College XR Content Creation Competition in May this year to stimulate the innovation power of colleges and universities across the country.

In the future, Rokid is willing to join hands with more partners to join the construction of the AR ecosystem, create an open and win-win ecosystem, continue to empower the industry, promote the accelerated development of the AR industry, and jointly embrace the next era of human-computer interaction.

The above is the detailed content of Is Apple leading the AR revolution? Unity Technology Open Day x Rokid, talk about the next generation of human-computer interaction new route. For more information, please follow other related articles on the PHP Chinese website!