Connect with us

Uncategorized

MIT aims to speed up robot movements to match robot thoughts using custom chips

Published

on

MIT researchers are looking to address the significant gap between how quickly robots can process information (relatively slowly), and how fast they can move (very quickly thanks to modern hardware advances), and they’re using something called ‘robomorphic computing’ to do it. The method, designed by MIT Computer Science and Artificial Intelligence (CSAIL) graduate Dr. Sabrina Neuman, results in custom computer chips that can offer hardware acceleration as a means to faster response times.

Custom-built chips tailored to a very specific purpose are not new – if you’re using a modern iPhone, you have one in that device right now. But they have become more popular as companies and technologists look to do more local computing on devices with more conservative power and computing constraints, rather than round-tripping data to large data centers via network connections.

In this case, the method involves creating hyper-specific chips that are designed based on a robot’s physical layout and and its intended use. By taking into account the requirements a robot has in terms of its perception of its surroundings, its mapping and understanding of its position within those surroundings, and its motion planning resulting from said mapping and its required actions, researchers can design processing chips that greatly increase the efficiency of that last stage by supplementing software algorithms with hardware acceleration.

The classic example of hardware acceleration that most people encounter on a regular basis is a graphics processing unit, or GPU. A GPU is essentially a processor designed specifically for the task of handling graphical computing operations – like display rendering and video playback. GPUs are popular because almost all modern computers run into graphics-intensive applications, but custom chips for a range of different functions have become much more popular lately thanks to the advent of more customizable and efficient small-run chip fabrication techniques.

Here’s a description of how Neuman’s system works specifically in the case of optimizing a hardware chip design for robot control, per MIT News:

The system creates a customized hardware design to best serve a particular robot’s computing needs. The user inputs the parameters of a robot, like its limb layout and how its various joints can move. Neuman’s system translates these physical properties into mathematical matrices. These matrices are “sparse,” meaning they contain many zero values that roughly correspond to movements that are impossible given a robot’s particular anatomy. (Similarly, your arm’s movements are limited because it can only bend at certain joints — it’s not an infinitely pliable spaghetti noodle.)

The system then designs a hardware architecture specialized to run calculations only on the non-zero values in the matrices. The resulting chip design is therefore tailored to maximize efficiency for the robot’s computing needs. And that customization paid off in testing.

Neuman’s team used an field-programmable gate array (FPGA), which is sort of like a midpoint between a fully custom chip and an off-the-shelf CPU, and it achieved significantly better performance than the latter. That means that were you to actually custom manufacture a chip from scratch, you could expect much more significant performance improvements.

Making robots react faster to their environments isn’t just about increase manufacturing speed and efficiency – though it will do that. It’s also about making robots even safer to work with in situations where people are working directly alongside and in collaboration with them. That remains a significant barrier to more widespread use of robotics in everyday life, meaning this research could help unlock the sci-fi future of humans and robots living in integrated harmony.

Continue Reading
Comments

Uncategorized

Qualcomm veteran to replace Alain Crozier as Microsoft Greater China boss

Published

on

Microsoft gets a new leader for its Greater China business. Yang Hou, a former executive at Qualcomm, will take over Alain Crozier as the chairman and chief executive officer for Microsoft Greater China Region, according to a company announcement released Monday.

More to come…

Continue Reading

Uncategorized

Autonomous drone maker Skydio raises $170M led by Andreessen Horowitz

Published

on

Skydio has raised $170 million in a Series D funding round led by Andreessen Horowitz’s Growth Fund. That pushes it into unicorn territory, with $340 million in total funding and a post-money valuation north of $1 billion. Skydio’s fresh capital comes on the heels of its expansion last year into the enterprise market, and it intends to use the considerable pile of cash to help it expand globally and accelerate product development.

In July of last year, Skydio announced its $100 million Series C financing, and also debuted the X2, its first dedicated enterprise drone. The company also launched a suite of software for commercial and enterprise customers, its first departure from the consumer drone market where it had been focused prior to that raise since its founding in 2014.

Skydio’s debut drone, the R1, received a lot of accolades and praise for its autonomous capabilities. Unlike other consumer drones at the time, including from recreational drone maker DJI, the R1 could track a target and film them while avoiding obstacles without any human intervention required. Skydio then released the Skydio 2 in 2019, its second drone, cutting off more than half the price while improving on it its autonomous tracking and video capabilities.

Late last year, Skydio brought on additional senior talent to help it address enterprise and government customers, including a software development lead who had experience at Tesla and 3D printing company Carbon. Skydio also hired two Samsara executives at the same time to work on product and engineering. Samsara provides a platform for managing cloud-based fleet operations for large enterprises.

The applications of Skydio’s technology for commercial, public sector and enterprise organizations are many and varied. Already, the company works with public utilities, fire departments, construction firms and more to do work including remote inspection, emergency response, urban planning and more. Skydio’s U.S. pedigree also puts it in prime position to capitalize on the growing interest in applications from the defense sector.

a16z previously led Skydio’s Series A round. Other investors who participated in this Series D include Lines Capital, Next47, IVP and UP.Partners.

Continue Reading

Uncategorized

Space startup Gitai raises $17.1M to help build the robotic workforce of commercial space

Published

on

Japanese space startup Gitai has raised a $17.1 million funding round, a Series B financing for the robotics startup. This new funding will be used for hiring, as well as funding the development and execution of an on-orbit demonstration mission for the company’s robotic technology, which will show its efficacy in performing in-space satellite servicing work. That mission is currently set to take place in 2023.

Gitai will also be staffing up in the U.S., specifically, as it seeks to expand its stateside presence in a bid to attract more business from that market.

“We are proceeding well in the Japanese market, and we’ve already contracted missions from Japanese companies, but we haven’t expanded to the U.S. market yet,” explained Gitai founder and CEO Sho Nakanose in an interview. So we would like to get missions from U.S. commercial space companies, as a subcontractor first. We’re especially interested in on-orbit servicing, and we would like to provide general-purpose robotic solutions for an orbital service provider in the U.S.”

Nakanose told me that Gitai has plenty of experience under its belt developing robots which are specifically able to install hardware on satellites on-orbit, which could potentially be useful for upgrading existing satellites and constellations with new capabilities, for changing out batteries to keep satellites operational beyond their service life, or for repairing satellites if they should malfunction.

Gitai’s focus isn’t exclusively on extra-vehicular activity in the vacuum of space, however. It’s also performing a demonstration mission of its technical capabilities in partnership with Nanoracks using the Bishop Airlock, which is the first permanent commercial addition to the International Space Station. Gitai’s robot, codenamed S1, is an arm–style robot not unlike industrial robots here on Earth, and it’ll be showing off a number of its capabilities, including operating a control panel and changing out cables.

Long-term, Gitai’s goal is to create a robotic workforce that can assist with establishing bases and colonies on the Moon and Mars, as well as in orbit. With NASA’s plans to build a more permanent research presence on orbit at the Moon, as well as on the surface, with the eventual goal of reaching Mars, and private companies like SpaceX and Blue Origin looking ahead to more permanent colonies on Mars, as well as large in-space habitats hosting humans as well as commercial activity, Nakanose suggests that there’s going to be ample need for low-cost, efficient robotic labor – particularly in environments that are inhospitable to human life.

Nakanose told me that he actually got started with Gitai after the loss of his mother – an unfortunate passing he said he firmly believes could have been avoided with the aid of robotic intervention. He began developing robots that could expand and augment human capability, and then researched what was likely the most useful and needed application of this technology from a commercial perspective. That research led Nakanose to conclude that space was the best long-term opportunity for a new robotics startup, and Gitai was born.

This funding was led by SPARX Innovation for the Future Co. Ltd, and includes funding form DcI Venture Growth Fund, the Dai-ichi Life Insurance Company, and EP-GB (Epson’s venture investment arm).

Continue Reading

Trending