Duke University engineers and computer scientists develop a new computer processor specially designed for robotic motion planning
Once they’ve mastered the skills of toddlerhood, humans are pretty good at what roboticists call “motion planning” — reaching around obstacles to precisely pick up a soda in a crowded fridge, or slipping their hands around a screen to connect an unseen cable.
But for robots with multi-jointed arms, motion planning is a hard problem that requires time-consuming computation. Simply picking an object up in an environment that has not been pre-engineered for the robot may require several seconds of computation.
Duke University researchers have introduced a specially-designed computer processor for motion planning that can plan up to 10,000 times faster than existing approaches while consuming a small fraction of the power. The new processor is fast enough to plan and operate in real time, and power-efficient enough to be used in large-scale manufacturing environments with thousands of robots.
“When you think about a car assembly line, the entire environment is carefully controlled so that the robots can blindly repeat the same movements over and over again,” said George Konidaris, assistant professor of computer science and electrical and computer engineering at Duke. “The car parts are in exactly the same place every time, and the robots are contained within cages so that humans don’t wander past. But if your robot is using motion planning in real time and a part is in a different place, or there’s some unexpected clutter, or a human walks by, it’ll do the right thing.”
Speedy motion planning saves the time and expense of engineering the environment around the robot, said Konidaris, who will be presenting the new work June 20 at a conference called Robotics: Science and Systems in Ann Arbor, Mich.
Motion planning has been studied for 30 years, and recent advances have brought the time required to find a plan for a sophisticated robot down to a few seconds. With few exceptions, these existing approaches rely on general-purpose CPUs or computationally faster but more power-hungry graphics processors (GPUs).
The Duke team designed a new processor specifically for motion planning.
“While a general-purpose CPU is good at many tasks, it cannot compete with a processor specially designed for just a single task,” said Daniel Sorin, professor of electrical and computer engineering and computer science at Duke.
Konidaris and Sorin’s team designed their new processor to perform collision detection — the most time-consuming aspect of motion planning — such that the processor performs thousands of collision checks in parallel.
“We streamlined our design and focused our hardware and power budgets on just the specific tasks that matter for motion planning,” Sorin said.
The technology works by breaking down the arm’s operating space into thousands of 3D volumes called voxels. The algorithm then determines whether or not an object is present in one of the voxels contained within pre-programmed motion paths. Thanks to the specially designed hardware, the technology can check thousands of motion paths simultaneously, and then stitch together the shortest motion path possible using the “safe” options remaining.
“The state of the art prior to our work used high-performance, commodity graphics processors that consume 200 to 300 watts,” said Konidaris. “And even then, it was taking hundreds of milliseconds, or even as much as a second, to find a plan. We’re at less than a millisecond, and less than 10 watts. Even if we weren’t faster, the power savings alone will add up in factories with thousands, or even millions, of robots.”
Konidaris also notes that the technology opens up new ways to use motion planning.
“Previously, planning was done once per movement, because it was so slow,” said Konidaris, “but now it is fast enough that it could be used as a component of a more complex planning algorithm, perhaps one that sequences several simpler motions or plans ahead to reason about the movement of several objects.”
The new processor’s speed and power efficiency could create many opportunities for automation. Konidaris, Sorin and their students are counting on it, and have incorporated a spinoff company, Realtime Robotics, to commercialize the technology.
“Real-time motion planning could really be a game-changer for robotics,” said Konidaris.
Learn more: Robotic motion planning in real-time
The Latest on: Robotic motion planning
[google_news title=”” keyword=”carbon capture” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Robotic motion planning
- A miniature wireless robot that can effectively move through tubular structureson May 1, 2024 at 3:50 am
Robots have already proved to be promising tools to complete complex and demanding maintenance tasks. While engineers have developed a wide range of robots that could help to maintain and repair ...
- Interview: Suzanne Gildert leaves Sanctuary to focus on AI consciousnesson April 30, 2024 at 2:26 am
Earlier this month, co-founder and CTO Suzanne Gildert left humanoid robotics company Sanctuary AI and her beloved Phoenix robot to focus full-time on AI safety, ethics and consciousness. We spoke to ...
- Researchers use ChatGPT for choreographies with flying robotson April 29, 2024 at 11:57 am
Angela Schoellig from the Technical University of Munich (TUM) uses ChatGPT to develop choreographies for swarms of drones to perform along to music. An additional safety filter prevents mid-air ...
- Manufacturing in space, the final frontieron April 19, 2024 at 10:18 am
Southwest Research Institute (SwRI) is redefining the future of robotics with its research on in-space servicing, assembly and manufacturing (ISAM).
- MCH Now offers the VELYS Robotic-Assisted Solution for Total Knee Replacementon April 18, 2024 at 9:25 pm
With the new Velys robotic solution, MCH is hoping to keep patients in the Permian basin to receive the proper knee treatment they need rather than travel elsewhere.
- Boston Dynamics unveils "stronger," fully electric humanoid robot in new videoon April 18, 2024 at 8:58 am
WALTHAM - Boston Dynamics ' latest robot is ready to "exceed human capabilities," the Waltham, Massachusetts-based company announced Wednesday. The newest version of the Atlas "humanoid" robot is ...
- Boston Dynamics’ new humanoid moves like no robot you’ve ever seenon April 17, 2024 at 2:08 pm
They don't look like much in the video since, when closed, they form nondescript blocks, but these look just like the three sets of spindly fingers that were shown off in February. The fingers started ...
- RIP Atlas, the world’s beefiest humanoid roboton April 17, 2024 at 8:08 am
Boston Dynamics is retiring its iconic 330-pound bipedal robot and replacing it with a lighter, all electric little sibling.
- Boston Dynamics’ Atlas humanoid robot goes electricon April 17, 2024 at 6:07 am
“That’s a huge range of motion. That really packs the power ... the company is finally ready to begin showing off what the robot can do — or at least the early stages of what it’s planning with the ...
- New Method Improves Human-Robot Interactionon April 17, 2024 at 6:01 am
Engineers at the Massachusetts Institute of Technology (MIT) have developed a safety check technique that can prove with 100 percent accuracy that a robot’s trajectory will remain collision-free.
via Bing News