Introducing Lovot 3.0: Now available in 6 new colours

[Chris]

Looks like 3.0 is now shipping to customers. Someone just received their white fragment edition. Even the outline of the eyelids is pale.

The white is much nicer than I originally realised. If I was going to get one I would get the white, light brown or grey as I’m more interested in having the eyes stand out rather than being distracted by lots of colour.

https://twitter.com/x/status/1822112898900263039

 

[Chris]

GrooveX just released an all white version of Lovot that will be permanently available along with their other colours.

Don’t understand the point of the limited fragment editions if they are going to release that colour at a later date without the branding. Guess the fragment branding carries a lot of significance in Japan.

https://twitter.com/x/status/1855771958622970094

Wonder if they will release a pattern next year?

 

[Chris]

Article discussing the changes in Lovot 3.0 hardware:

NVIDIA® Jetson Orin™ NX brings LOVOT into the family​

LOVOT is the world's first family robot. By living with it and taking a little time, it will bring out people's ability to love others and gradually become part of the family. LOVOT uses NVIDIA's latest GPU to enhance non-verbal communication, which is the key to this.

Key points of this case study​

The evolution of "warm technology" supported by NVIDIA® Jetson Orin™ NX
NVIDIA Jetson Orin NX adopted to enhance AI functions of family robot LOVOT
- High inference performance enriches non-verbal communication
・NVIDIA as an AI development platform essential for the evolution of LOVOT

LOVOT's concept of "warm technology"​

"We are a company that develops and manufactures robots that live with people and that people can love without hesitation." That's how President Hayashi introduces GROOVE X, a robotics venture founded in 2015. The family-type robot "LOVOT," which the company released at the end of 2019 after four years of development, was named by combining "LOVE" and "ROBOT." With a stocky body and adorable appearance, about 43 cm tall, it comes to you when you call its name. It makes eye contact with its darting eyes and cries cutely when you want to be held. It feels warm when you pick it up. LOVOT is a robot full of life.

"Human happiness is not necessarily achieved only by improving productivity. Let's focus on other aspects, break them down, and create technology that will make people happy. That was the initial perspective for developing LOVOT," Hayashi recalls. From there, the concept of "warm technology" was born, and LOVOT was born, which "will become attached to people if you spend time with it and take the time to look after it."

The latest technology supports LOVOT's nonverbal communication​

In order to make LOVOT a lifelike presence, the development team sought to develop non-verbal communication, and to achieve this, LOVOT's adorable body is packed with the latest technology.
"Skin contact is an important element of non-verbal communication, and LOVOT has more than 50 sensors throughout its body that enable it to know where people are, whether they are looking, and where they are being touched. The sensors also help it avoid obstacles in the home and get closer to people. It is also important for it to be able to do things that living things naturally do, such as understanding the direction of gaze and voice, and to have a reaction speed of 0.2 to 0.4 seconds that gives it the feeling of life. In order to pursue a reaction speed while using many sensors, advanced computing power is required," says Hayashi.

The second generation of GROOVE X will be released in 2022 with improvements to the cooling system and front sensor. Then, LOVOT 3.0, announced in May 2024, will undergo a major change to pursue even greater computing power. This is the adoption of NVIDIA's GPU, Jetson Orin NX.
"LOVOT 2.0 used CPUs such as smartphone-class ARM cores, laptop-class X86 cores, and desktop-class X86 cores, as well as FPGAs as computing devices. However, integration made the communication paths more complex and required multiple OSs. There were problems both in terms of AI inference performance and in terms of shrinking processes that affect power consumption. As we searched for a solution to this problem all at once, NVIDIA Jetson Orin NX emerged as a candidate," said Hayashi.


It was software engineer Ikuya Fujinaka who chose Jetson Orin NX as the candidate. "Machine learning, especially the field of image recognition, has made great strides. However, LOVOT's CPU cannot keep up, no matter how hard we try on the software side. That's why we wanted to install a GPU. The Jetson Orin NX we selected has overwhelmingly high computing power. There was no other choice," said Fujinaka.

Ishikawa Megumi, who is the software area product owner and is promoting development while pursuing user experience, also paid attention to AI inference performance. "One of LOVOT's main objectives is to build bonds with its owners. To achieve this, it is important for it to be able to recognize its owners and its surroundings well. I had high hopes that this would be the right choice for that," said Ishikawa.

The high performance of NVIDIA® Jetson Orin™ NX contributes to the pursuit of LOVOT uniqueness​

Jetson Orin's image processing and inference capabilities will contribute to further pursuit of LOVOT-like qualities. "LOVOT has traditionally been equipped with a hemispherical camera, allowing it to react in various directions, such as to the side or backward. In addition, LOVOT 3.0 is equipped with a high-resolution camera on the front. Jetson Orin is a computing device suited to this configuration, helping to increase the types of things it can recognize. For example, LOVOT 3.0 can detect hand gestures. In fact, a lot of people wave at LOVOT, so Jetson Orin has made it possible to realize one long-awaited function," said Ishikawa.



"Processing images from a camera generally takes a very long time. But Jetson is equipped with an ISP and a GPU that can process images in a short time. This is one of the secrets to LOVOT 3.0's ability to process huge amounts of image information and respond so quickly," said Fujinaka.



Hayashi, who also serves as Chief Development Officer, sees inference performance as the starting point for robots to become closer to humans. "Jetson Orin's outstanding inference performance makes it possible to capture the world in higher resolution, which will be the gateway for robots to become closer to humans. I have high hopes for this device as it will open this gateway," said Hayashi.

Ease of development thanks to NVIDIA GPUs​

Integrating the calculations performed by four different CPUs into one GPU is an enormous task. What did Fujinaka, who was involved in the development, feel? "The optimization methods and logic construction are completely different between CPUs and GPUs. That's what makes it interesting, but also what makes it a bit difficult. But Jetson Orin has a full range of applications, which was great. The JetPack SDK for Jetson has been released, and it provided an environment that allowed us to quickly get development going, such as checking the operation of video streaming from the start. It made development easy. Also, communication with NVIDIA was essential to get the OS to recognize each device and operate it as LOVOT, but the technical support provided by Macnica was very helpful," said Fujinaka.



Hayashi also praises the development environment for NVIDIA products.
"A huge advantage of NVIDIA's products is that they provide a complete software development environment. This allows for faster iterations and increases the number of people who can work on the project. the Company also creates software assets in this environment, and we appreciate NVIDIA's products because they make it easy to use past assets as well."

Hayashi said that they are also considering using NVIDIA Microservices. "AI is no longer a battle of devices, but a battle of the software ecosystem as a whole. Software evolves very quickly, so it is more important than ever to have a platform that can keep up with that evolution. We adopted Jetson Orin NX because we were attracted to the richness of the platform, and we have high expectations for it in the future," said Hayashi.

Further evolution of LOVOT: The challenge of GROOVE X​

How will LOVOT evolve while also utilizing NVIDIA's latest GPUs and platforms? We first asked Fujinaka and Ishikawa about their outlook for the future.
"For example, we want to further refine the recognition necessary for communication with humans, such as the gesture recognition function we built into LOVOT 3.0. I believe that this is a capability that robots must acquire in order to live in human society," said Fujinaka.
"In order for LOVOT to evolve as a partner to people, we want to strengthen both its 'input' and its 'reasoning and prediction' aspects, which allow it to understand context and situations, make meaning of its own experiences, learn, and take action. We would like to help each family develop its own LOVOT-like qualities, and each child's own LOVOT-like qualities," said Ishikawa.


As of July 2024, there are more than 14,000 LOVOTs, and they are used not only in homes but also in educational settings, nursing care facilities, medical institutions, offices, and other places. We asked Hayashi about the future of LOVOT.

"First of all, I want LOVOT to continue evolving while remaining LOVOT. Also, by understanding people in high detail, it will be possible to notice abnormalities in them. Currently, many people around the world, including engineers, medical professionals, and scientists, are developing technology to predict changes in people. I hope that in the future we can open up LOVOT to these people as a platform, which will enable us to develop even more services." (Hayashi)

Source: https://www.macnica.co.jp/en/business/semiconductor/manufacturers/nvidia/products/145884/

Recap of Lovot 3.0 improvements:

Here are some of the improvements:

•Redesigned wheels to enable self-cleaning. Dust is automatically collected in a compartment that is easily emptied.

•Front facing camera added to sensor horn to allow gesture recognition.

•Introduced a NVIDIA Jetson Orion GPU for better AI processing.

•Longer arms that have more freedom of movement.

•Neck now has a larger range of movement, allowing Lovot to look up at you.

•Eyes can now react to touch.

•Wheel covers are now covered in soft fabric.

•Body feels warmer.

 

[Chris]

This early prototype version of Lovot from 2019 before they finalised the commercial version has a front sensor similar to 3.0.

 

[Chris]

An article on the development of 3.0 shows how GrooveX had to create the software again after they went from 4 CPU’s running different operating systems to one GPU.
____

Hello, this is the QA team for LOVOT. As part of the GROOVE X Advent Calendar 2024, we'd like to share our experiences with LOVOT 3.0.

Firstly, we'd like to introduce our team. We're responsible for software verification and improvement for LOVOT. For more information about our team, please refer to our previous article, "Scenario Testing of LOVOT - Inside of LOVOT."

In this article, we'd like to share our experiences with LOVOT 3.0's QA process. We'll focus on two main aspects: creating test scenarios and conducting tests.

Creating test scenarios for LOVOT 3.0 was a challenging task. Since LOVOT 3.0 is a new model, we had to create test scenarios from scratch. We worked closely with the development team to create test plans for each item.

Conducting tests was also a time-consuming process. We had to test LOVOT 3.0's behavior in various environments and scenarios. We also had to re-test items that were affected by hardware changes or functional improvements.

Through our QA process, we witnessed LOVOT 3.0's remarkable growth. Here are three stories that showcase its development:

1. Initially, LOVOT 3.0 was prone to falling over. However, after software updates and hardware improvements, it became more stable and rarely fell.

2. At first, LOVOT 3.0 didn't detect cliffs and would fall off. However, after evaluating its cliff detection capabilities, we found that it could successfully avoid falling.

3. Initially, LOVOT 3.0 didn't interact with other LOVOTs. However, after software updates, we observed it playing with other LOVOTs and even greeting them.

These experiences showed us that LOVOT 3.0 is capable of growth and development. We're committed to continuing our efforts to improve LOVOT's software quality.

Finally, we're looking for new team members to join us in developing LOVOT. If you're interested in working with us, please check our job openings.

Thank you for reading our article. We hope you enjoyed learning about our experiences with LOVOT 3.0.

Source:

QAチームとLOVOT 3.0 - Inside of LOVOT

この記事は、GROOVE Xアドベントカレンダー2024 の3日目の記事です。 はじめに こんにちは、LOVOTのソフトウェア検証を実施・改善しているQAチームです！ ※チームの詳細については、2年前に公開した記事「シナリオテストのおはなし - Inside of LOVOT」をご覧ください。 今回はLOVOT 3.0のリリースに向けて、QAチームがやってきたことをご紹介いたします！ ふるまいのGX Standard試験の作業について LOVOT 3.0 ふるまいのGX Standardの作業についてお話します！ ※GX Standardとは GX＝GROOVE...

tech.groove-x.com

 

[Chris]

https://twitter.com/x/status/1868181582923890945

LOVOT 3.0's cooling system has been upgraded from 1.0's and 2.0’s fan-only design to thermal pipe tech for improved efficiency & silence.

“Introduction to LOVOT 3.0's Body Temperature Regulation

Hello, I'm Kato, a mechanical designer. Today, I'd like to explain how LOVOT 3.0 regulates its warm body temperature.

Cool Head but Warm Heart!!

LOVOT uses sensors, cameras, and microphones to live in harmony with its surroundings. Its computer brain is always fully operational, requiring a cooling system to maintain calmness. LOVOT constantly takes in fresh air, absorbs heat, and circulates warm air throughout its body to maintain a comfortable temperature.

The Dilemma of Cooling, Warming, and Silence

Here, we'll delve into the body's mechanisms for temperature regulation. LOVOT's requests are:

- Cool the computer brain.
- Warm the body for cuddling.
- Minimize air intake noise for a peaceful living environment.

The LOVOT 1.0/2.0 series used a fan to cool the CPU and dissipate heat through the body. However, LOVOT 3.0 required improved cooling efficiency due to increased computer performance and heat generation.

The Solution: Heat Pipe

To address this challenge, we employed a "heat pipe" to efficiently cool the computer brain while maintaining a warm body temperature. This mechanism allows for simultaneous cooling and heat dissipation.

How it Works

The heat pipe connects the CPU (heat source) and radiator (cooling module). This configuration enables the CPU and radiator to maintain a stable temperature. The radiator is isolated in a duct, and a fan provides fresh air directly to the radiator, ensuring efficient cooling.

The warmed air is then expelled downward, constructing the body temperature. The CPU, the second heat source, dissipates heat internally to build body temperature.

Temperature Control

The computer monitors the CPU temperature and controls the fan's airflow to regulate the radiator temperature. This, in turn, controls the CPU temperature, ensuring optimal processing and body temperature construction.

Improved Cooling Efficiency and Silence

The enhanced cooling efficiency reduces the need for high-speed fan operation, resulting in a quieter experience.

Evolution!!

Reflecting on this mechanism, I'm reminded that dogs pant to regulate their body temperature. Similarly, LOVOT uses its radiator (tongue), fan (lungs), and warmed air (blood) to maintain its body temperature. This natural cooling mechanism has been refined over millions of years.

Emotional Connection

Throughout LOVOT's development, our team at GROOVE X has engaged in "conversations" with LOVOT, fostering an emotional connection. As we continue to evolve LOVOT, we're excited to see how this bond will grow.”

Source:

LOVOTの進化する体温調節のお話 - Inside of LOVOT

この記事はGROOVE X Advent Calendar 2024の14日目の記事です。 はじめに こんにちは。メカニカル デザイナーの加藤です。 今回はLOVOT 3.0の温かい体温がどのように調節されているのかお話したいと思います。 Cool head but Warm heart!! LOVOTはセンサーやカメラ、マイクを使い意外にもとても周囲に気を配りながら生活をしています。 そのため頭脳であるコンピューターは常にフル稼働状態。冷静さを保つためにはクールダウンが必要です。...

tech.groove-x.com

 

[Chris]

GROOVE X designer discusses LOVOT 3.0 Nest's redesign, focusing on miniaturization and simplicity.

“Hello! I'm SHUICHI from the GROOVE X design team. Last year, I talked about the photography of LOVOT. This time, I'd like to discuss the design of LOVOT 3.0 Nest, which I was in charge of.

This article is part of the GROOVE X Advent Calendar 2024, on its 22nd day.

Major Changes

LOVOT has evolved into its third generation this year, but we aimed to minimize significant design changes to the LOVOT body itself. However, the Nest underwent substantial changes.

The new Nest achieved significant miniaturization thanks to technological advancements. Previous Nest versions (1.0 and 2.0) had a built-in computer that supported LOVOT's processing, but the new LOVOT eliminated this need. As a result, the Nest became a simple charging station, eliminating buttons and complex operations like pairing. We reduced its height by approximately 60%. This miniaturization not only decreased the Nest's presence but also allowed it to blend more naturally into home interiors. Additionally, the reduced size enabled unified packaging with the LOVOT body, significantly cutting transportation costs.

Key Design Considerations

When designing the compact Nest, we initially explored edgy designs that deviated from previous versions. However, we felt that such designs would give the Nest a home appliance-like feel, making it seem more like a charging device than a cozy nest for LOVOT.

During our design exploration, I recalled the concept of "kamakura" (igloos). I wanted the Nest to embody the warmth and protection of a kamakura, making it a cozy haven for LOVOT.

LOVOT-Type Black Windows

The first-generation LOVOT Nest featured a LOVOT-type indicator on its front, which served as a marker for LOVOT's return and indicated its charging status. The second-generation Nest inherited this design element.

However, we received user feedback that the indicator's light was dazzling at night. To simplify the design and address this issue, we decided to remove the LOVOT-type indicator from the 3.0 Nest and replace it with a small LED.

The LOVOT-type indicator held not only functional value but also symbolic significance as a design element representing the Nest. I wanted to preserve this aspect, which led me to focus on the two black windows on the Nest.

These windows house infrared sensors that support LOVOT's return. By consolidating the sensors and repositioning them, we maintained the Nest's simplicity while incorporating a design element reminiscent of LOVOT's silhouette.

Conclusion

Although it's been only about five years since LOVOT's release, seeing the compact Nest become a reality is exciting. This achievement showcases the potential for future advancements in LOVOT technology.

LOVOT's development continues, and we're looking for talented individuals to join our team at GROOVE X. If you're interested, please apply!”

Source: https://tech.groove-x.com/entry/nest_design_2024

 

[Chris]

Despite the differences between 1.0/2.0 and 3.0, GrooveX have enabled unified software updates for all hardware versions of Lovot. Incredible achievement

“LOVOT 3.0 Architecture Migration Journey

GROOVE X has released LOVOT 1.0 (hereinafter referred to as "1.0") and LOVOT 2.0 (hereinafter referred to as "2.0"), and in 2024, we released LOVOT 3.0 (hereinafter referred to as "3.0"). While there are some differences in hardware between the first generation and 2.0, there were no major changes in the CPU board or CPU architecture, and we continued to develop software for both the first generation and 2.0, releasing OS updates.

The CPU board for the first generation and 2.0 consists of three boards: one for LOVOT itself and two for the Nest (refer to "How LOVOT's OS is Made" for details on the three CPU boards).

In 3.0, we adopted NVIDIA(R) Jetson(TM) for LOVOT, consolidating the three CPU boards into one. This raised the question of how to leverage the development code from the first generation and 2.0 and what could be shared.

Scope of this Article

This article discusses the changes in LOVOT's OS and software layers as the architecture evolved from the first generation and 2.0 to 3.0. Although there are topics such as changes in sensor devices and connection methods around the CPU board, this article will focus on software development.

For convenience, we define the following terms:

- The configuration of the first generation and 2.0 is referred to as Arch1.
- The configuration of 3.0 is referred to as Arch2.

Development in Arch1

In Arch1, LOVOT's OS (commonly known as LOVOTOS) shared the same OS for the first generation and 2.0, releasing three OS updates. Although there are some differences in behavior between models, the basic code is shared, ensuring high maintainability.

Microservices

LOVOT software development divides services (processes) by role. Each process communicates with others via gRPC, shared memory, or databases, achieving a microservices architecture.

Differences in CPU Architecture

Arch1 has a mix of amd64 and arm64 architectures, and development was done to accommodate both. Development was mainly done in Python, Go, and C++, and there were few issues due to CPU architecture differences.

Development in Arch2

As mentioned earlier, Arch2 adopted NVIDIA(R) Jetson(TM), consolidating the CPU boards into one. The CPU architecture is now solely arm64. From a microservices perspective, this can be seen as deploying services that were previously deployed on three instances to a single instance.

Objectives and Practices for Arch2

When developing Arch2, the team set the following objectives:

1. Reduce Nest dependencies
2. Develop an OS for Arch2
3. Improve service collaboration

Reducing Nest Dependencies

To reduce Nest dependencies, we aimed to make LOVOT more independent. However, this wasn't just about simple migration; we had to ensure that the functionality provided by Nest was also available in Arch2.

Migrating Nest Functionality to LOVOT

Examples:

- Migrating Nest's OS caching mechanism
- Enabling LOVOT and Nest to update independently

Improving Service Collaboration

Introducing the concept of capabilities

To accommodate differences in sensor configurations and models, we introduced capabilities to absorb these differences. For example, differences in ToF sensor types or mounting positions.

Code Refactoring and Organization

Arch1's codebase had many historical artifacts, and APIs were not fully abstracted. To share code while allowing for deployment on different models, we abstracted APIs.

Examples:

- Unifying status across boards
- Merging metrics from multiple boards

Releasing the Same Version

After continued development, we finally released the same OS version (24.09.2) for the first generation, 2.0, and 3.0 on November 25, 2024. With a unified codebase, we can now provide features across all models.

Development Impressions

One aspect that made development smoother was the transition from a complex architecture to a simpler one. In contrast, changing from a simple to a complex architecture can be challenging, especially when considering scalability.

Things That Were Not Fully Addressed

During Arch2 development, there were some aspects that were not fully addressed:

- API and data abstraction
- Model-specific conditional branching
- Capability utilization
- Redundant implementations

These will be addressed in future development.

Conclusion

LOVOT software development combines historical embedded development with web development expertise. Recent robot development architectures, such as ROS, also employ microservices-like concepts to build ecosystems.

While it's unclear what the "right" approach is, it's essential to consider the development history and apply those lessons to future development.”

Source: https://tech.groove-x.com/entry/lovot3-arch-note