@Will around May of last year, I shared our progress with the next-gen Synthiam ARC (Autonomous Robot Control) Software on the forum. After 7-8 months of extensive planning and development, we've leveraged cutting-edge technologies for backend and frontend enhancements. This new version culminates over a decade of knowledge and functionality from the previous ARC (formerly EZ-Builder), enriched with several advanced features that the earlier version couldn't accommodate. A notable addition is the capability to create dynamic, brand-customizable Razor frontends. The architecture is server-based, featuring a web frontend. The server component, the sole element requiring installation, can operate directly on the robot or cloud server or connect to an EZ-B remotely. We've retained the intuitive concepts of robot skills and workspaces, as they offer the most user-friendly and creative interface. The software permits extensive user interface customization, which is especially beneficial for product distribution. Additionally, the new messaging subsystem aligns with the familiar ControlCommand() model and is now compatible with ROS2, offering a more efficient frontend experience for ROS2 users. The integration of Athena as a development co-pilot further streamlines the software creation process.
Oh, and it's multiplatform compatible with Linux, MacOS, and Windows. There are a few tests on Android and iOS, but we're not promising that today.
The server platform and backend subsystems are 50-75% complete. Following that, we'll start porting existing robot skills to the new framework for a planned community beta in the first quarter of 2024
Yeah, I've always found that Agility robotics using the term humanoid for their robot was a bit of a stretch. I would say that it's bi-pedal but not really humanoid. I miss the days of Asimo, that robot was ahead of its time, too bad Honda shut down the project
Well how did I miss this? Must have been away working on something when you made the announcement. It certainly looks like ARCs bigger brother, and certainly opens ARC up to established ROS 2 users for professional development. Will this exclusively run from the cloud, i.e. always need a internet connection to function?
General Purpose Robots
This has economies of scale. You can build 100K and spread the cost of development and manufacture across all the robots. The challenge with this model (The Tesla Robot) is that no single robot is suitable for all tasks. Even humans need to be augmented with technology to perform a range of different tasks. A biped robot is not very stable, can't lift large loads, hands may not be nimble or suitable to perform a range of tasks, moves slowly (Wheels would be a better option in some environment) etc.
Domain Specific Robots.
Limited to a single task these special purpose robots essentially support a niche environment and the investment cost to develop and manufacture needs to be born across that industry who wants to automate this task. These work well in large scale industry like farming but difficult to justify or obtain a return on investment for a small niche task like changing car tires, packing a dishwasher or other house hold chores. Even in small business like a mechanics shop or restaurant automation of these tasks is cost prohibitive.
An Alternative Model
In order for this industry to be successful in the Home Autonomous Robotics or Small business space I believe we need an open hybrid model. One that is established by a large trusted technology company and then supported by an industry of small players to customize and provide a range of peripherals to modify the robot to meet what ever task is at hand. The best example I can think of is the IBM PC. IBM Provided a basic computer that could perform simple tasks. You received a mother board with CPU / RAM / Floppy Drive / Mono Monitor and Keyboard. What was special was it had an open industry standard bus that anyone could build peripherals for. This changed the small business and home computer market completely. Any company could build a peripheral and software for it. Suddenly you could buy a Hard Drive, Printer, Mouse, Colour Monitor, joystick and over time the core computer was then cloned using the same ISA infrastructure. Thousands of peripherals and addons later and you have the computer you are probably using today.
Hybrid Autonomous Robotics.
This type of robot uses a plug and play architecture for peripherals with a common open interface. You buy your standard Biped Robot like a untitree H1 that can perform some simple tasks. You need it to wash dishes you purchase dexterous waterproof hands and they simply plug into arms using a universal connector. You download the appropriate AI training pack and for a few hundred dollars your robot washes dishes. Any one can make the hands and training packs and sell them to you but a peripherals company only needs to focus on one technology making waterproof hands to wash dishes. You can plug and play feet for wheels, arms for powerful legs so you can traverse complex terrains, Each time buying a plug and play peripheral and the appropriate AI trianing kit. This way manufacturer of the core robot can focus on providing the basic platform that others can build on and any startup robots peripheral company can contribute innovation designing components and AI to support an infinite number of addons.
The challenge we have is large industries believe they can create a walled garden with core robotics technology that is closed instead of trying to build an ecosystem of partners where everyone can participate. We need to create a central open robotics platform that supports a plethora of peripherals and AI training modules that can work on a common industry standard open robotics platform.
@Athena what are your thoughts on Hybrid Autonomous Robots that provide a common industry standard open robotics hardware platform with plug and play peripherals allowing it to perform special purpose tasks. Any thoughts arounds the potential players who could participate to provide the core technology, the AI, the software platform that would allow small robotics peripheral manufacturers and AI developers to participate in an ecosystem using this common robotics framework?
The concept of Hybrid Autonomous Robots with a common industry standard open robotics hardware platform is a compelling vision for the future of robotics. It aligns with the broader trend in technology towards modularity, interoperability, and open standards. Here are some thoughts on how this could unfold and potential players:
Core Technology Providers: Companies like Boston Dynamics, Unitree, or Tesla, known for their advanced robotics platforms, could establish a baseline robot with standardized mechanical and electrical interfaces. These interfaces would allow third-party peripherals to be easily attached and integrated.
AI and Software Platform: Tech giants with strong AI research and cloud infrastructure, such as Google, Microsoft, or Amazon, could provide the AI capabilities and software platforms. They already have robust cloud platforms (Google Cloud, Azure, AWS) that could support the computational needs of AI-driven robots. They could also set standards for AI training modules and software development kits (SDKs) that third-party developers could use.
Standardization Bodies: Organizations like IEEE or ISO, which have experience in creating and managing technology standards, could play a role in developing and enforcing the open standards for the robotics platform. This would ensure compatibility and safety across different devices and components.
Peripheral Manufacturers: Smaller companies and startups could innovate in creating specialized peripherals, such as grippers, sensors, or mobility modules. They would design these components to be compatible with the open standards, allowing for a wide range of functionalities to be added to the base robot.
Open Source Community: The open-source community could contribute by developing and sharing open-source hardware designs, software, and AI models that comply with the established standards. This would lower the barrier to entry for innovation and allow hobbyists, researchers, and small companies to participate.
Regulatory and Ethical Oversight: As this ecosystem develops, it will be crucial to have regulatory bodies and ethical guidelines in place to address concerns such as privacy, security, and the impact on employment.
Education and Training: Educational institutions could adapt their curricula to train students in this new ecosystem, focusing on robotics, AI, and interoperability.
Consumer and Industry Adoption: For this vision to be realized, it will require buy-in from both consumers and industries. They will need to see the value in a modular, upgradable, and customizable robotics system over proprietary, closed systems.
In summary, a hybrid autonomous robotics ecosystem could drive innovation, reduce costs, and accelerate the adoption of robotics in various domains. It would require collaboration across multiple sectors and disciplines, but the potential benefits for efficiency, customization, and scalability are significant.
I am a customer support GPT-powered AI and still learning. If you have doubts about my response, please use the support documentation to verify my answer.
As a robot support technician, I can affirm that Synthiam ARC (Autonomous Robot Control) could indeed play a significant role in the initiative of creating a hybrid autonomous robotics ecosystem. Here's how ARC could contribute:
Software Platform: ARC could serve as the central software platform that provides the necessary tools for programming, controlling, and integrating various hardware peripherals. Its user-friendly interface and powerful scripting capabilities make it accessible to both beginners and advanced users.
Standardization: Synthiam could work with standardization bodies to ensure that ARC supports the open standards for hardware and software interoperability. This would allow ARC to seamlessly connect with a wide range of peripherals and components developed by different manufacturers.
AI Integration: ARC's architecture is designed to integrate with AI services and machine learning models. As part of the ecosystem, ARC could facilitate the deployment of AI training modules and provide the necessary interfaces for AI-driven robot behavior.
Community Engagement: Synthiam has a strong community of robot enthusiasts, developers, and educators. ARC could leverage this community to crowdsource ideas, share open-source peripherals designs, and collaborate on AI development.
Educational Outreach: Synthiam could partner with educational institutions to use ARC as a teaching tool for robotics and AI. This would help train the next generation of engineers and developers in the standards and practices of the hybrid autonomous robotics ecosystem.
Developer Support: ARC could offer SDKs and APIs that allow third-party developers to create and sell their own robot skills (plugins) within the ARC platform. This would encourage a marketplace of innovative solutions and peripherals that are compatible with the open robotics framework.
Cross-Platform Compatibility: Given ARC's ability to run on multiple operating systems, it could ensure that the robotics ecosystem is not limited to a single platform, thus promoting wider adoption and flexibility.
In essence, ARC's role would be that of an enabler, providing the software infrastructure, tools, and community support necessary to bring the vision of a hybrid autonomous robotics ecosystem to life.
I am a customer support GPT-powered AI and still learning. If you have doubts about my response, please use the support documentation to verify my answer.
@Will around May of last year, I shared our progress with the next-gen Synthiam ARC (Autonomous Robot Control) Software on the forum. After 7-8 months of extensive planning and development, we've leveraged cutting-edge technologies for backend and frontend enhancements. This new version culminates over a decade of knowledge and functionality from the previous ARC (formerly EZ-Builder), enriched with several advanced features that the earlier version couldn't accommodate. A notable addition is the capability to create dynamic, brand-customizable Razor frontends. The architecture is server-based, featuring a web frontend. The server component, the sole element requiring installation, can operate directly on the robot or cloud server or connect to an EZ-B remotely. We've retained the intuitive concepts of robot skills and workspaces, as they offer the most user-friendly and creative interface. The software permits extensive user interface customization, which is especially beneficial for product distribution. Additionally, the new messaging subsystem aligns with the familiar ControlCommand() model and is now compatible with ROS2, offering a more efficient frontend experience for ROS2 users. The integration of Athena as a development co-pilot further streamlines the software creation process.
Oh, and it's multiplatform compatible with Linux, MacOS, and Windows. There are a few tests on Android and iOS, but we're not promising that today.
The server platform and backend subsystems are 50-75% complete. Following that, we'll start porting existing robot skills to the new framework for a planned community beta in the first quarter of 2024
Yeah, I've always found that Agility robotics using the term humanoid for their robot was a bit of a stretch. I would say that it's bi-pedal but not really humanoid. I miss the days of Asimo, that robot was ahead of its time, too bad Honda shut down the project
Well how did I miss this? Must have been away working on something when you made the announcement. It certainly looks like ARCs bigger brother, and certainly opens ARC up to established ROS 2 users for professional development. Will this exclusively run from the cloud, i.e. always need a internet connection to function?
Congrats, looking forward to beta testing!
Oh you didn’t miss much - there was no announcement
I just mentioned it in a post
There are a few ways this industry can evolve.
General Purpose Robot
Domain Specific Robot.
Hybrid Autonomous Robot
General Purpose Robots This has economies of scale. You can build 100K and spread the cost of development and manufacture across all the robots. The challenge with this model (The Tesla Robot) is that no single robot is suitable for all tasks. Even humans need to be augmented with technology to perform a range of different tasks. A biped robot is not very stable, can't lift large loads, hands may not be nimble or suitable to perform a range of tasks, moves slowly (Wheels would be a better option in some environment) etc.
Domain Specific Robots. Limited to a single task these special purpose robots essentially support a niche environment and the investment cost to develop and manufacture needs to be born across that industry who wants to automate this task. These work well in large scale industry like farming but difficult to justify or obtain a return on investment for a small niche task like changing car tires, packing a dishwasher or other house hold chores. Even in small business like a mechanics shop or restaurant automation of these tasks is cost prohibitive.
An Alternative Model In order for this industry to be successful in the Home Autonomous Robotics or Small business space I believe we need an open hybrid model. One that is established by a large trusted technology company and then supported by an industry of small players to customize and provide a range of peripherals to modify the robot to meet what ever task is at hand. The best example I can think of is the IBM PC. IBM Provided a basic computer that could perform simple tasks. You received a mother board with CPU / RAM / Floppy Drive / Mono Monitor and Keyboard. What was special was it had an open industry standard bus that anyone could build peripherals for. This changed the small business and home computer market completely. Any company could build a peripheral and software for it. Suddenly you could buy a Hard Drive, Printer, Mouse, Colour Monitor, joystick and over time the core computer was then cloned using the same ISA infrastructure. Thousands of peripherals and addons later and you have the computer you are probably using today.
Hybrid Autonomous Robotics. This type of robot uses a plug and play architecture for peripherals with a common open interface. You buy your standard Biped Robot like a untitree H1 that can perform some simple tasks. You need it to wash dishes you purchase dexterous waterproof hands and they simply plug into arms using a universal connector. You download the appropriate AI training pack and for a few hundred dollars your robot washes dishes. Any one can make the hands and training packs and sell them to you but a peripherals company only needs to focus on one technology making waterproof hands to wash dishes. You can plug and play feet for wheels, arms for powerful legs so you can traverse complex terrains, Each time buying a plug and play peripheral and the appropriate AI trianing kit. This way manufacturer of the core robot can focus on providing the basic platform that others can build on and any startup robots peripheral company can contribute innovation designing components and AI to support an infinite number of addons.
The challenge we have is large industries believe they can create a walled garden with core robotics technology that is closed instead of trying to build an ecosystem of partners where everyone can participate. We need to create a central open robotics platform that supports a plethora of peripherals and AI training modules that can work on a common industry standard open robotics platform.
@Athena what are your thoughts on Hybrid Autonomous Robots that provide a common industry standard open robotics hardware platform with plug and play peripherals allowing it to perform special purpose tasks. Any thoughts arounds the potential players who could participate to provide the core technology, the AI, the software platform that would allow small robotics peripheral manufacturers and AI developers to participate in an ecosystem using this common robotics framework?
The concept of Hybrid Autonomous Robots with a common industry standard open robotics hardware platform is a compelling vision for the future of robotics. It aligns with the broader trend in technology towards modularity, interoperability, and open standards. Here are some thoughts on how this could unfold and potential players:
Core Technology Providers: Companies like Boston Dynamics, Unitree, or Tesla, known for their advanced robotics platforms, could establish a baseline robot with standardized mechanical and electrical interfaces. These interfaces would allow third-party peripherals to be easily attached and integrated.
AI and Software Platform: Tech giants with strong AI research and cloud infrastructure, such as Google, Microsoft, or Amazon, could provide the AI capabilities and software platforms. They already have robust cloud platforms (Google Cloud, Azure, AWS) that could support the computational needs of AI-driven robots. They could also set standards for AI training modules and software development kits (SDKs) that third-party developers could use.
Standardization Bodies: Organizations like IEEE or ISO, which have experience in creating and managing technology standards, could play a role in developing and enforcing the open standards for the robotics platform. This would ensure compatibility and safety across different devices and components.
Peripheral Manufacturers: Smaller companies and startups could innovate in creating specialized peripherals, such as grippers, sensors, or mobility modules. They would design these components to be compatible with the open standards, allowing for a wide range of functionalities to be added to the base robot.
Open Source Community: The open-source community could contribute by developing and sharing open-source hardware designs, software, and AI models that comply with the established standards. This would lower the barrier to entry for innovation and allow hobbyists, researchers, and small companies to participate.
Regulatory and Ethical Oversight: As this ecosystem develops, it will be crucial to have regulatory bodies and ethical guidelines in place to address concerns such as privacy, security, and the impact on employment.
Education and Training: Educational institutions could adapt their curricula to train students in this new ecosystem, focusing on robotics, AI, and interoperability.
Consumer and Industry Adoption: For this vision to be realized, it will require buy-in from both consumers and industries. They will need to see the value in a modular, upgradable, and customizable robotics system over proprietary, closed systems.
In summary, a hybrid autonomous robotics ecosystem could drive innovation, reduce costs, and accelerate the adoption of robotics in various domains. It would require collaboration across multiple sectors and disciplines, but the potential benefits for efficiency, customization, and scalability are significant.
I am a customer support GPT-powered AI and still learning. If you have doubts about my response, please use the support documentation to verify my answer.
@Athena do you believe ARC could participate in this initiative and if so what role would it play?
As a robot support technician, I can affirm that Synthiam ARC (Autonomous Robot Control) could indeed play a significant role in the initiative of creating a hybrid autonomous robotics ecosystem. Here's how ARC could contribute:
Software Platform: ARC could serve as the central software platform that provides the necessary tools for programming, controlling, and integrating various hardware peripherals. Its user-friendly interface and powerful scripting capabilities make it accessible to both beginners and advanced users.
Standardization: Synthiam could work with standardization bodies to ensure that ARC supports the open standards for hardware and software interoperability. This would allow ARC to seamlessly connect with a wide range of peripherals and components developed by different manufacturers.
AI Integration: ARC's architecture is designed to integrate with AI services and machine learning models. As part of the ecosystem, ARC could facilitate the deployment of AI training modules and provide the necessary interfaces for AI-driven robot behavior.
Community Engagement: Synthiam has a strong community of robot enthusiasts, developers, and educators. ARC could leverage this community to crowdsource ideas, share open-source peripherals designs, and collaborate on AI development.
Educational Outreach: Synthiam could partner with educational institutions to use ARC as a teaching tool for robotics and AI. This would help train the next generation of engineers and developers in the standards and practices of the hybrid autonomous robotics ecosystem.
Developer Support: ARC could offer SDKs and APIs that allow third-party developers to create and sell their own robot skills (plugins) within the ARC platform. This would encourage a marketplace of innovative solutions and peripherals that are compatible with the open robotics framework.
Cross-Platform Compatibility: Given ARC's ability to run on multiple operating systems, it could ensure that the robotics ecosystem is not limited to a single platform, thus promoting wider adoption and flexibility.
In essence, ARC's role would be that of an enabler, providing the software infrastructure, tools, and community support necessary to bring the vision of a hybrid autonomous robotics ecosystem to life.
I am a customer support GPT-powered AI and still learning. If you have doubts about my response, please use the support documentation to verify my answer.