Earlier this month, Realtime Robotics unveiled its RapidPlan software, which helps manufacturers increase the speed, efficiency and performance of industrial automation machines.
Despite continuous advances in the field of robotics, complex motion through space still presents a stumbling block for bots. In oftentimes hectic industrial settings, complex motion that entails a robot getting from point A to point B to perform a task is a feat that generally involves weeks to months of programming time, resulting in movement that’s relatively slow and collision-prone.
It’s a challenge that George Konidaris, cofounder and chief roboticist of Realtime Robotics, says has been a persistent hurdle for robotics researchers since 1979—and he thinks RapidPlan represents a significant leap of progress.
“This software represents a technology breakthrough of the kind that we’re going to need to take automation to the next level,” says Konidaris. “I really do think that this is the future of automation and it’s going to drastically expand the envelope of what can be done.”
Realtime sought to overcome the limitations with RapidPlan, which autonomously creates and choreographs all robot movements and removes the need for brand-specific robot programming. In RapidPlan’s programming interface, users visualize tasks for robots and plan how the bots will execute them in a simulated environment. Realtime claims that the tool can save weeks to months’ worth of time from the programming, design and deployment process.
Part of the software’s promise is enabling robots to more quickly determine the best path of movement in dynamic environments like factories, which Konidaris says so far hasn’t been accomplished. Software users start with RapidPlan Create, which guides them through the robotic programming phase. Then RapidPlan Control runs the robots’ operations.
Data from Realtime indicates that the software can reduce programming time by 70-80 percent, increase throughput rate by 10-30 percent and decrease a bot’s life cycle cost by up to 50 percent.
“Something that used to take many weeks now takes just one week,” Konidaris says. “The programming task is much quicker. The robots’ performance is better, so that helps your throughput.”
He adds that performance is especially enhanced in multi-robot scenarios such as when there are three to six arms working in a cell. Generally, adding more robots doesn’t significantly increase throughput if their movements impede each other’s speed. However, Konidaris says the RapidPlan-enabled robots can move faster, more efficiently and with fewer collisions, boosting the throughput of multiple robots working in tandem. The software reportedly supplies the bots with basic physical intelligence so that they can adapt their movements to changing environments, by either using information from programmable logic controllers (PLCs) or from dedicated 3D sensors.
Another added benefit of RapidPlan, according to Konidaris, is that it’s compatible with all major robotic brands, removing the need for brand-specific programming. This was accomplished through painstaking engineering to understand brand-specific programming languages. It’s something that Realtime will reportedly repeat for any robotic product line that achieves market significance.
To showcase the software, Realtime held a demonstration at Automate 2022. During the demo, Mitsubishi Electric Automation’s RV-7FRL, RV-8CRL and ASSISTA Collaborative Robots showed the RapidPlan software in action. Onlookers, many of whom were experienced in the field of robots, were excited to see the bots operating at such high speeds and getting close to one another without crashing.
Additionally, Realtime has partnered with Kawasaki Robotics, which also participated in a demonstration at Automate 2022. Two RapidPlan-enabled Kawasaki BX100N robots simulated a car door welding using ARO 3G modular spot-welding guns, reportedly without needing reprogramming or manual verification of motion planning.
Realtime Robotics’ technology has the ability to speed deployment, operations and production for manufacturers, helping to improve their cost structures and time-to-market,” says Patrick Varley, product marketing manager for Mechatronics at Mitsubishi Electric Automation. “It is through collaboration with the most innovative technology providers that we can truly be ‘better together.’”
While Realtime’s technology could eventually pave the way for more generalist robots, there’s more work to be done to get there. Automation tends to gravitate toward functions that are more structured and less specialist, and Konidaris says the field will only gradually progress toward less structured and less specialist capabilities.
“We should view this as a spectrum and it’s going to happen over a long period of time,” Konidaris says. “For AGI [Artificial general intelligence], we should be talking about decades to centuries. For robotics reaching its full capacity in terms of changing the way we live through autonomy, I think that revolution is on the cusp.”
However, he also says that robotic movement in the real world is particularly challenging and that advancement in industrial automation will be iterative and won’t happen overnight.
“It’s not just whether you can do something; it’s also can you do it with a very good ROI, throughput, and do it multiple times with reliability,” Konidaris adds. “I think what we’re going to see over the next 10 years in the robotics industry is this progressive explosion of what can be done, and it’s tremendously exciting.”
The explosion is already underway. For example, Amazon’s $1 billion Industrial Innovation Fund is part of an effort to deploy an army of fulfillment robots to work alongside humans in warehouses. Startup Sanctuary has raised $58.5 million in funding, promising to develop a robot that’s as capable as humans both physically and mentally. Meanwhile, Ford launched a platform that enables its Carbon 3D printers and KUKA robots to communicate in a common language.
Konidaris says the concept of such inter-machine communication is especially relevant to Realtime goals with RapidPlan. When operating together at high speeds, the software is integral to equipping the bots with sufficient spatial communication skills to fulfill their respective functions without impeding the other. In essence, RapidPlan is about equipping robots with the ability to function relationally within their environment, which could ultimately become a foundational technology for the field.
“We’re waiting for the automation revolution,” says Konidaris. “We’re waiting for robots to change the way that everything around us is structured. But that revolution isn’t going to happen until there is a fundamental technological shift.”
Realtime is planning to build on its RapidPlan software through greater integration. At the heart of that effort is entering into partnerships with companies that can help make the shift happen, taking the technology to the next level.
In addition to the partnerships with Mitsubishi and Kawasaki, Realtime entered into a collaboration with Siemens in 2020 to pair the latter’s Tecnomatix Process Simulate with the Realtime Controller to significantly simplify the programming of automated robotic responses and help reduce deployment and adaptation time.
Konidaris says that the partnership aims to expand to other simulation tools, optimizing robot layout, and automating for full stack solutions.
“One way to think about the industry at the moment is that there’s a chunk of the stack still missing and humans have to fill in by thinking very hard,” says Konidaris. “If we can automate it, then we have a full stack solution that goes all the way from design to control on the floor.”