Category Archives: Robotics

The collaboration stems from a shared recognition of the critical role that robotics can play in addressing challenges in agriculture and food production, such as increased demand for food and the need for precision agriculture practices. By leveraging resources from both agencies, NSF and USDA seek to foster interdisciplinary research that will tackle agricultural challenges and increase sustainability.

Under the joint funding opportunity, proposals will be solicited to support research projects that align with the goals of both the NSF Foundational Research in Robotics program and USDA NIFA. Proposals submitted under this initiative will undergo rigorous evaluation by both agencies.

This partnership represents a unique opportunity to harness the power of robotics to address pressing challenges in agriculture, said Michael Littman, director for the NSF Division of Information and Intelligent Systems. Daniel Linzell, director of the NSF Division of Civil, Mechanical and Manufacturing Innovation added, This new collaboration between NIFA and NSF underscores the value of our long-standing partnership and our commitment to foundational robotics research for the agriculture sector.

More here:

NSF and USDA join forces to boost innovation in agricultural robotics - Future Farming

Powered by 24 NVIDIA GPUs, Carbon Robotics vehicles use deep-learning-based computer vision models to autonomously identify and eliminate weeds via CO2 lasers. LaserWeeder, as the product is called, processes 4.7 million high-resolution images per hour, zapping 5,000 weeds per minute, according to the company. To date, its dataset includes 25 million labeled plants and more than 30,000 crop and weed models.

Carbon Robotics currently provides machines for multiple big-name growers in the US including Taylor Farms, Cal-Organic and Braga Fresh.

The relationship with NVIDIAs NVenture team began when Carbon robotics included NVIDIA GPUs in LaserWeeder to showcase a new approach to precision weeding, Carbon Robotics CEO Paul Mikesell tells AgFunderNews.

This demonstration highlighted the profound potential of AI and GPU technology to transform the agriculture industry, enhancing farming operations and economics through advanced technologies.

Weeding is the most popular task to automate on the farm right now for speciality crop growers, according to a 2023 Western Growers survey. For farmers, the biggest challenge around weeds isnt so much the plants but finding enough labor to manage them.

Carbon Robotics is one of several startups tackling these challenges; others include Stout, Verdant RoboticsandFarmWise.[Disclosure: AFNs parent company,AgFunder, is an investor in Verdant Robotics.]

Carbon Robotics will use the NVenture investment to accelerate product development and expand internationally, according to Mikesell.

More specific details are under wraps, he says. We are dedicated to continuous innovation in our product lines, and we plan to introduce more advanced features and capabilities that will further enhance efficiency and sustainability in farming.

The NVentures portfolio currently includes companies working in therapeutics, AI medical imaging and autonomous building management, among other areas. The investment in Carbon Robotics highlights [NVIDIAs] leadership position in delivering AI-driven solutions to the agriculture industry, using its expertise in GPUs and AI technologies, says Mikesell.

He adds that the collaboration with NVentures enhances the LaserWeeders capabilities, processing millions of images per hour for precise weed control, and demonstrates the real-world applications of NVIDIAs AI solutions in improving agricultural efficiency and sustainability.

Read the rest here:

Brief: NVIDIA's venture arm invests in autonomous weeding startup Carbon Robotics - AgFunderNews

Chinas LimX Dynamics has brought about a revolution in the field of robotics with the W1 quadruped robot being able to stand up and walk on its two feet.

W1 was released just last year, and it was inspired by the ETH-Zurich-designed Swiss-Mile robot. Quite similar to the earlier bot, this one also has four legs and each of them is powered with a powered wheel on the end.

The W1 has this innate capability to travel on smooth roads, sidewalks, floors, and whatnot. It can simply roll along on its wheels for optimum speed and energy efficiency. In case it needs to step over obstacles, travel through rough terrain or ascend/descend the stairs it stops and locks up its wheels.

Later it uses those wheels as feet while taking on a quadruped walking style. One of the main differences between the Swiss-Mile and W1 is the fact that the former can adopt a human-like form for certain tasks. These include giving or taking packages where it could stand up and either walk or roll on its hind legs. Now, the W1 can do that as well.

The robot when standing can additionally rotate 360 degrees on the spot, make 90-degree turns and also make its way between obstacles like shelving units, and also recover fast without causing any collisions. It also switches from quadruped to biped mode in less than one second, standing 152 cm tall in one go.

In a recently released video, LimX has revealed that the W1 can walk on two feet across a smooth floor. In the future it might also climb stairs bipedally as with other robots in the company.

In the future, the W1 can be also seen performing tasks like grasping items using its front legs while standing. More when the future unfolds.

Based on real-time enviornment perception, W1 demonstrates agile perceptive locomotion to overcome challenging discrete terrains. The well-defined multiple high-performing actuators further allow W1 to fully unleash its comprehensive mobility potentials. According to LimX Dynamics, as an innovative product, W1 is the best form of all-terrain mobility.

This robots design can flexibly adapt to various scenarios, with a wheeled movement speed of maximum 10m/s, stable endurance of 4 hours, 16 actuated degrees of freedom and autonomous switching of multiple motion modes.

NEWSLETTER

Stay up-to-date on engineering, tech, space, and science news with The Blueprint.

Gairika Mitra Gairika is a technology nerd, an introvert, and an avid reader. Lock her up in a room full of books, and you'll never hear her complain.

Originally posted here:

LimX Dynamics' W1 robot can stand, walk and roll on its hind 'legs' - Interesting Engineering

Welcome back to the latest episode of The Future of Automotive on CBT News, where we put recent automotive and mobility news into the context of the broader themes impacting the industry.

Im Steve Greenfield from Automotive Ventures, and Im glad that you could join us.

One of our investment theses at Automotive Ventures is that AI and robotics are going to reduce repetitive processes and, over time, eliminate many mundane, boring tasks for humans. And weve been putting our money where our mouth is with automation investments like WarrCloud, that automates a dealerships warranty processing back to the OEM, RoboTire that uses robotic arms to automate the tire replacement process, and more recently Kinetic, which automates ADAS calibrations.

This week we got news that Lear Corporation, a global automotive technology leader in seating and electronics systems for cars, will acquire WIP Industrial Automation, a privately held systems integrator based in Spain that specializes in advanced automation solutions for industrial applications.

Lear is a global automotive technology leader, with employees in 38 countries is driven by a commitment to innovation, operational excellence, and sustainability. Lear, headquartered in Southfield, Michigan, serves every major automaker in the world and ranks 189 on the Fortune 500.

Like other suppliers, Lear has faced increased labor costs and scarcity pressures in the wake of the supply chain crisis and, more recently, from the ripple effects of the contracts the UAW reached with the Detroit 3 last fall.

A year ago, Lear said labor had emerged as the suppliers top issue, causing the company to accelerate the integration of robotics at its factories. Through the adoption of robotics and automation, Lear is looking to combat wage inflation, which is one of the biggest pain points for the automotive seating and electronics supplier.

WIP, the target of Lears acquisition, is a long-time Lear supplier with 25 years of automation experience, that develops, integrates, and deploys cutting-edge technologies to create customized automation solutions for manufacturing applications. WIP brings strong robotics and AI-based computer vision capabilities to Lear, which are important for safety, quality, and efficiency in a modern manufacturing environment. WIP positions Lear to operate more efficiently, thus allowing the company to navigate current macroeconomic challenges, such as elevated wage inflation, more effectively.

This acquisition will be the latest of Lears strategic investments designed to broaden its global automation and digital capabilities and will equip Lear with a robust portfolio of automation solutions and technical knowledge that span all critical areas of the manufacturing process and will accelerate innovation in the development of next-generation automation technologies.

As automakers and suppliers focus on taking out costs from their operations, I expect to continue to see innovation and acquisitions around robotics and process automation to enable companies to streamline processes and ultimately do more work with fewer employees.

Process automation, the use of robotics and of AI will continue to be a core focus of our investment funds, and we expect these trends to have a strong positive force on shaping the future of automotive.

So, with that, lets transition to Our Companies to Watch.

Every week we highlight interesting companies in the automotive technology space to keep an eye on. If you read my weekly Intel Report, we showcase a company to watch, and take the opportunity here to share that company with you.

Today, our new company to watch is P1 Fuels.

P1 Fuels produces a fossil-free fuel that works in any combustion engine with no need for modifications.

Their goal is to decarbonize the mobility sector, and theyve started this journey with motorsports.

Motorsports have always been the driving force behind automotive technology advancement. It is with this commitment to innovation that at P1 Fuels, they are pioneering the production of entirely fossil-free fuels.

P1 Fuel emits 80% less C02 compared to normal fuel. And their fuels are high-performance: The power of P1 Fuels matches the power of regular gasoline.

If youd like to learn more about P1 Fuels, you can check them out at http://www.p1fuels.com

So thats it for this weeks Future of Automotive segment.

If youre an AutoTech entrepreneur working on a solution that helps car dealerships, we want to hear from you. We are actively investing out of our DealerFund.

If youre interested in joining our Investment Club to make direct investments into AutoTech and Mobility startups, please join. There is no obligation to start seeing our deal flow, and we continue to have attractive investment deals available to our members.

Dont forget to check out my book, The Future of Automotive Retail, which is available on Amazon.com. And keep an eye out for my new book, The Future of Mobility, which is almost done, and will be out soon.

Thanks (as always) for your ongoing support and for tuning into CBT News for this weeks Future of Automotive segment. Well see you next week!

See the rest here:

Lear Corporation's acquisition showcases the industry's use of robotics and AI for efficiency and innovation - CBT Automotive News

Summary

OMRON and Neura Robotics to unveil new line of cognitive robots and advanced AI-driven automation technologies at Automate.

May 2, 2024 -OMRON, a leading solution provider in industrial automation, and Neura Robotics GmbH, an innovation leader in cognitive robotics, recently announced their strategic partnership aimed at revolutionizing manufacturing efficiency through advanced AI-driven cognitive automation technologies. This collaboration will be highlighted at the upcoming Automate trade show in Chicago May 6-9 at McCormick Place, booth #2267, where the two companies will introduce the new OMRON intelligent Cognitive Robot (iCR) series.

The OMRON iCR, derived from NEURA Robotics MAiRA line, leverages integrated sensors and AI technologies to address the needs of industrial customers for flexibility, productivity, and efficiency. These robots boast an optional integrated 3D vision sensor, intuitive user-friendly interface, and NEURAs advanced safety architecture for improved performance and safety.

The potential of the new robot will be showcased at Automate through a 3D bin-picking demonstration. This demo will provide an insight into how AI-enabled, cognitive automation can enhance and redefine the efficiency and flexibility of manufacturing processes. It will also showcase the impressive integration of OMRONs all-in-one Sysmac control platform, highlighting its ability to streamline complex operations.

David Reger, founder, CEO and visionary at NEURA Robotics, reflected on the partnership by saying, Our strategic alliance with Omron marks the beginning of a new era in industrial automation. This is another important step towards our goal of revolutionizing the global robotics market. With the intelligent Cognitive Robot iCR we are removing usage barriers and multiplying possible applications for robotics in automation because they can act autonomously, recognize people safely and anticipate their actions. Thanks to our technology, these key requirements for the humanoid future of robotics are already a reality in industry today. By launching the iCR, we aim to significantly influence the future of manufacturing across all geographies and establish new benchmarks in the industry.

Olivier Welker, president and CEO of Omron Robotics and Safety Technologies Inc.Also expressed his enthusiasm, "We are thrilled to announce this next step in our partnership with NEURA. The OMRON iCR represents our commitment to pushing the boundaries of industrial automation and driving innovation in the manufacturing sector. We are confident in our ability to deliver state-of-the-art solutions that will meet the evolving needs of our customers and further establish OMRON as a leader in automation."

Omron and NEURA Robotics invite all attendees at Automate to engage with their technologies, share insights, and discuss the future potential of automation in their manufacturing environments.

OMRON Automation Americas is a division of OMRON, an industrial automation leader that creates, sells, and services fully integrated automation solutions including sensing, control, safety, vision, motion, robotics, and more. Established in 1933, OMRONs team of more than 30,000 employees helps businesses solve problems with creativity in more than 110 countries around the world.

NEURA Robotics was founded in 2019 by David Reger in Metzingen, southern Germany, with the goal of bridging important innovation gaps in robotics and establishing the age of cognitive robots. Like a smartphone manufacturer, NEURA Robotics combines all components and sensors as well as artificial intelligence in one device and offers partners a platform for the joint development of apps for a wide range of specialist areas. The resulting and steadily growing NEURAverse offers unmatched flexibility and cost efficiency in automation and attracts many international market leaders. NEURA's cognitive robots can see, hear, and have a sense of touch; they act completely autonomously and learn from experience.

Check out our free e-newsletters to read more great articles..

See the rest here:

OMRON and NEURA Robotics Partner to Unveil New Cognitive Robot at Automate 2024 - Automation.com

The Cesar Chavez Ravenswood Middle School robotics team in Dallas, Texas at the VEX World Championship in April 2024. Courtesy Ravenswood City School District. Ravenswood robotics team makes it to world championship

The Cesar Chavez Ravenswood Middle School robotics team students made the division finals at the VEX World Championship in Dallas, Texas at the end of April.

The best part of the trip is when they unveil the new game and I go to dinner with the students and listen to all the ideas flying around the table and they start drawing pictures on napkins, said teacher Tina Collier, who leads the team, in a Ravenswood City School District newsletter. I carry a small sketchbook now to allow for everyone to participate in their first unofficial brainstorming session.

Senior citizens who own property in the Las Lomitas School District have until June 3 to apply for an exemption from the $311 parcel tax passed by voters in March 2007.

To qualify for the exemption, the property owner must be over 65 years old by July 1, 2024 and live on the property they own within district boundaries.

Contact district administration at 650-854-6311 for the application form.

The Menlo Park Safe Routes to School Program, in collaboration with the city library, will hold a Bike to the Library Day on Thursday, May 16, from 2-5:30 p.m. at Menlo Park Central Library, 800 Alma St. May is National Bike Month.

There will be helmet giveaways, bike skills courses, reading sessions, pedal-powered spin art, a bike repair station, helmet fitting station, food from local vendors, a SamTrans bus and more.

Representatives from SamTrans, Caltrain, WheelKids and others will be onsite.

More information is available at menlopark.gov.

Angela Swartz

Sudden Oak Death is an exotic disease that threatens the survival of tanoak and several oak species in California coastal forests. The SOD Blitz Project will be surveying the trees of Woodside, Portola Valley and Los Altos Hills from May 17 at 10 a.m. through May 20 at 6 p.m.

SOD Blitz invites the community and local citizen scientists to get involved in detecting the disease on bay laurel and tanoak leaves by collecting samples. All participants are required to take a 30-minute training course. To sign up and participate, visit tinyurl.com/SODBlitzProject.

Jennifer Yoshikoshi

Grab some free, nutritious compost for your Garden at the City of Menlo Parks compost giveaway event all day Saturday, May 11, and Sunday, May 12. Free compost is available while supplies last.

You can find the compost in the Burgess Park parking lot at the intersection of Alma Street and Burgess Drive. Compost is self-serve, so bring your own containers, trowels and gloves.

This compost comes from your residential green organic carts at home and at work, according to a city of Menlo Park event listing. The food scraps collected from the green carts are sent to two commercial composting facilities where it goes through a process where it breaks down back into a soil-like product.

Learn more about housing resources at the city of Menlo Parks Housing Resource Fair on Saturday, May 11, from 1-4 p.m. The event will be held at the Ivy Plaza, located at 410 Ivy Drive in the outdoor space near the Belle Haven Child Development Center.

The event will offer information on affordable housing in Menlo Park, housing rehabilitation support, and more. Housing organizations at the event will include the Samaritan House, Project Sentinel, Habitat for Humanity Greater San Francisco, Rebuilding Together Peninsula and HIP Housing.

There will also be raffle prizes, a childrens activity table and snacks.

Eleanor Raab

Continued here:

Community briefs: Ravenswood robotics at world championship, Bike to the Library Day - The Almanac Online

State Alabama Alaska Arizona Arkansas California Colorado Connecticut Delaware Florida Georgia Hawaii Idaho Illinois Indiana Iowa Kansas Kentucky Louisiana Maine Maryland Massachusetts Michigan Minnesota Mississippi Missouri Montana Nebraska Nevada New Hampshire New Jersey New Mexico New York North Carolina North Dakota Ohio Oklahoma Oregon Pennsylvania Rhode Island South Carolina South Dakota Tennessee Texas Utah Vermont Virginia Washington Washington D.C. West Virginia Wisconsin Wyoming Puerto Rico US Virgin Islands Armed Forces Americas Armed Forces Pacific Armed Forces Europe Northern Mariana Islands Marshall Islands American Samoa Federated States of Micronesia Guam Palau Alberta, Canada British Columbia, Canada Manitoba, Canada New Brunswick, Canada Newfoundland, Canada Nova Scotia, Canada Northwest Territories, Canada Nunavut, Canada Ontario, Canada Prince Edward Island, Canada Quebec, Canada Saskatchewan, Canada Yukon Territory, Canada

Zip Code

Country United States of America US Virgin Islands United States Minor Outlying Islands Canada Mexico, United Mexican States Bahamas, Commonwealth of the Cuba, Republic of Dominican Republic Haiti, Republic of Jamaica Afghanistan Albania, People's Socialist Republic of Algeria, People's Democratic Republic of American Samoa Andorra, Principality of Angola, Republic of Anguilla Antarctica (the territory South of 60 deg S) Antigua and Barbuda Argentina, Argentine Republic Armenia Aruba Australia, Commonwealth of Austria, Republic of Azerbaijan, Republic of Bahrain, Kingdom of Bangladesh, People's Republic of Barbados Belarus Belgium, Kingdom of Belize Benin, People's Republic of Bermuda Bhutan, Kingdom of Bolivia, Republic of Bosnia and Herzegovina Botswana, Republic of Bouvet Island (Bouvetoya) Brazil, Federative Republic of British Indian Ocean Territory (Chagos Archipelago) British Virgin Islands Brunei Darussalam Bulgaria, People's Republic of Burkina Faso Burundi, Republic of Cambodia, Kingdom of Cameroon, United Republic of Cape Verde, Republic of Cayman Islands Central African Republic Chad, Republic of Chile, Republic of China, People's Republic of Christmas Island Cocos (Keeling) Islands Colombia, Republic of Comoros, Union of the Congo, Democratic Republic of Congo, People's Republic of Cook Islands Costa Rica, Republic of Cote D'Ivoire, Ivory Coast, Republic of the Cyprus, Republic of Czech Republic Denmark, Kingdom of Djibouti, Republic of Dominica, Commonwealth of Ecuador, Republic of Egypt, Arab Republic of El Salvador, Republic of Equatorial Guinea, Republic of Eritrea Estonia Ethiopia Faeroe Islands Falkland Islands (Malvinas) Fiji, Republic of the Fiji Islands Finland, Republic of France, French Republic French Guiana French Polynesia French Southern Territories Gabon, Gabonese Republic Gambia, Republic of the Georgia Germany Ghana, Republic of Gibraltar Greece, Hellenic Republic Greenland Grenada Guadaloupe Guam Guatemala, Republic of Guinea, Revolutionary People's Rep'c of Guinea-Bissau, Republic of Guyana, Republic of Heard and McDonald Islands Holy See (Vatican City State) Honduras, Republic of Hong Kong, Special Administrative Region of China Hrvatska (Croatia) Hungary, Hungarian People's Republic Iceland, Republic of India, Republic of Indonesia, Republic of Iran, Islamic Republic of Iraq, Republic of Ireland Israel, State of Italy, Italian Republic Japan Jordan, Hashemite Kingdom of Kazakhstan, Republic of Kenya, Republic of Kiribati, Republic of Korea, Democratic People's Republic of Korea, Republic of Kuwait, State of Kyrgyz Republic Lao People's Democratic Republic Latvia Lebanon, Lebanese Republic Lesotho, Kingdom of Liberia, Republic of Libyan Arab Jamahiriya Liechtenstein, Principality of Lithuania Luxembourg, Grand Duchy of Macao, Special Administrative Region of China Macedonia, the former Yugoslav Republic of Madagascar, Republic of Malawi, Republic of Malaysia Maldives, Republic of Mali, Republic of Malta, Republic of Marshall Islands Martinique Mauritania, Islamic Republic of Mauritius Mayotte Micronesia, Federated States of Moldova, Republic of Monaco, Principality of Mongolia, Mongolian People's Republic Montserrat Morocco, Kingdom of Mozambique, People's Republic of Myanmar Namibia Nauru, Republic of Nepal, Kingdom of Netherlands Antilles Netherlands, Kingdom of the New Caledonia New Zealand Nicaragua, Republic of Niger, Republic of the Nigeria, Federal Republic of Niue, Republic of Norfolk Island Northern Mariana Islands Norway, Kingdom of Oman, Sultanate of Pakistan, Islamic Republic of Palau Palestinian Territory, Occupied Panama, Republic of Papua New Guinea Paraguay, Republic of Peru, Republic of Philippines, Republic of the Pitcairn Island Poland, Polish People's Republic Portugal, Portuguese Republic Puerto Rico Qatar, State of Reunion Romania, Socialist Republic of Russian Federation Rwanda, Rwandese Republic Samoa, Independent State of San Marino, Republic of Sao Tome and Principe, Democratic Republic of Saudi Arabia, Kingdom of Senegal, Republic of Serbia and Montenegro Seychelles, Republic of Sierra Leone, Republic of Singapore, Republic of Slovakia (Slovak Republic) Slovenia Solomon Islands Somalia, Somali Republic South Africa, Republic of South Georgia and the South Sandwich Islands Spain, Spanish State Sri Lanka, Democratic Socialist Republic of St. Helena St. Kitts and Nevis St. Lucia St. Pierre and Miquelon St. Vincent and the Grenadines Sudan, Democratic Republic of the Suriname, Republic of Svalbard & Jan Mayen Islands Swaziland, Kingdom of Sweden, Kingdom of Switzerland, Swiss Confederation Syrian Arab Republic Taiwan, Province of China Tajikistan Tanzania, United Republic of Thailand, Kingdom of Timor-Leste, Democratic Republic of Togo, Togolese Republic Tokelau (Tokelau Islands) Tonga, Kingdom of Trinidad and Tobago, Republic of Tunisia, Republic of Turkey, Republic of Turkmenistan Turks and Caicos Islands Tuvalu Uganda, Republic of Ukraine United Arab Emirates United Kingdom of Great Britain & N. Ireland Uruguay, Eastern Republic of Uzbekistan Vanuatu Venezuela, Bolivarian Republic of Viet Nam, Socialist Republic of Wallis and Futuna Islands Western Sahara Yemen Zambia, Republic of Zimbabwe

Visit link:

JCHS Robotics shimes at VEX World Competition | Community News - The Tomahawk

Join us in returning to NYC on June 5th to collaborate with executive leaders in exploring comprehensive methods for auditing AI models regarding bias, performance, and ethical compliance across diverse organizations. Find out how you can attend here.

Large language models (LLMs) can accelerate the training of robotics systems in super-human ways, according to a new study by scientists at Nvidia, the University of Pennsylvania and the University of Texas, Austin.

The study introduces DrEureka, a technique that can automatically create reward functions and randomization distributions for robotics systems. DrEureka stands for Domain Randomization Eureka. DrEureka only requires a high-level description of the target task and is faster and more efficient than human-designed rewards in transferring learned policies from simulated environments to the real world.

The implications can be great for the fast-moving world of robotics, which has recently gotten a renewed boost from the advances in language and vision models.

When designing robotics models for new tasks, a policy is usually trained in a simulated environment and deployed to the real world. The difference between simulation and real-world environments, referred to as the sim-to-real gap, is one of the big challenges of any robotics system. Configuring and fine-tuning the policy for optimal performance usually requires a bit of back and forth between simulation and real-world environments.

The AI Impact Tour: The AI Audit

Join us as we return to NYC on June 5th to engage with top executive leaders, delving into strategies for auditing AI models to ensure fairness, optimal performance, and ethical compliance across diverse organizations. Secure your attendance for this exclusive invite-only event.

Recent works have shown that LLMs can combine their vast world knowledge and reasoning capabilities with the physics engines of virtual simulators to learn complex low-level skills. For example, LLMs can be used to design reward functions, the components that steer the robotics reinforcement learning (RL) system to find the correct sequences of actions for the desired task.

However, once a policy is learned in simulation, transferring it to the real world requires a lot of manual tweaking of the reward functions and simulation parameters.

The goal of DrEureka is to use LLMs to automate the intensive human efforts required in the sim-to-real transfer process.

DrEureka builds on Eureka, a technique that was introduced in October 2023. Eureka takes a robotic task description and uses an LLM to generate software implementations for a reward function that measures success in that task. These reward functions are then run in simulation and the results are returned to the LLM, which reflects on the outcome and modifies it to the reward function. The advantage of this technique is that it can be run in parallel with hundreds of reward functions, all generated by the LLM. It can then pick the best functions and continue to improve them.

While the reward functions of Eureka are great for training RL policies in simulation, it does not account for the messiness of the real world and therefore requires manual sim-to-real transfer. DrEureka addresses this shortcoming by automatically configuring domain randomization (DR) parameters.

DR techniques randomize the physical parameters of the simulation environment so that the RL policy can generalize to the unpredictable perturbances it meets in the real world. One of the important challenges of DR is choosing the right parameters and range of perturbations. Adjusting parameters requires commonsense physical reasoning and knowledge of the target robot.

These characteristics of designing DR parameters make it an ideal problem for LLMs to tackle because of their strong grasp of physical knowledge and effectiveness in generating hypotheses, providing good initializations to complex search and black-box optimization problems in a zero-shot manner, the researchers wrote.

DrEureka uses a multi-step process to break down the complexity of optimizing reward functions and domain randomization parameters at the same time. First, an LLM generates reward functions based on a task description and safety instructions about the robot and the environment. DrEureka uses these instructions to create an initial reward function and learn a policy as in the original Eureka. The model then runs tests with the policy and reward function to determine the suitable range of physics parameters, such as friction and gravity.

The LLM then uses this information to select the optimal domain randomization configurations. Finally, the policy is retrained with the DR configurations to become robust against the noisiness of the real world.

The researchers described DrEureka as a language-model driven pipeline for sim-to-real transfer with minimal human intervention.

The researchers evaluated DrEureka on quadruped and dexterous manipulator platforms, although the method is general and applicable to diverse robots and tasks. Their findings show that in quadruped locomotion, policies trained with DrEureka outperform the classic human-designed systems by 34% in forward velocity and 20% in distance traveled across various real-world evaluation terrains. They also tested DrEureka on dexterous manipulation with robotic hands. Given a fixed amount of time, the best policy trained by DrEureka performed 300% more cube rotations than human-developed policies.

But the most interesting finding was the application of DrEureka on the novel task of having a robo-dog balancing and walking on a yoga ball. The LLM was able to design a reward function and DR configurations that allowed the trained policy to be transferred to the real world with no extra configurations and perform well enough on diverse indoor and outdoor terrains with minimal safety support.

Interestingly the study found that the safety instruction included in the task description plays an important role in ensuring that the LLM generates logical instructions that transfer to the real world.

We believe that DrEureka demonstrates the potential of accelerating robot learning research by using foundation models to automate the difficult design aspects of low-level skill learning, the researchers wrote.

VB Daily

Stay in the know! Get the latest news in your inbox daily

By subscribing, you agree to VentureBeat's Terms of Service.

Thanks for subscribing. Check out more VB newsletters here.

An error occured.

Read the rest here:

Nvidia's DrEureka outperforms humans in training robotics systems - VentureBeat

Robotics & Automation INSIDER

While the adoption of autonomous mobile robots (AMRs) and collaborative robots (cobots) has increased in logistics and manufacturing industries, mobile manipulation robots (MMRs) or humanoid robots still seem like a distant reality. Manufacturing and logistics operations have some of the most advanced automated solutions, but many have been deployed in silos and have created islands of automation. MMRs provide an opportunity to address the remaining gaps between islands of automation and tackle new workflows that needed more flexible automation, believes Melonee Wise, Chief Product Officer at Agility Robotics (Corvallis, OR).

Wise presented her insights about MMRs at Automate 2024 during the session titled The Next Frontier of Automation: Human-Centric Robots, where she talked about how to prepare your facility for the next phase of robotics human-centric, humanoid robots and how to connect existing islands of automation.

Wise also shared several real-life use cases of how Agilitys humanoid robot named Digit can effectively handle typical payloads found in most logistics and manufacturing operations, particularly the manipulation, movement, and placement of totes and cases. Digit is suitable for these industries that are facing significant labor shortages, and are plagued by operations that are repetitive, taxing, and injury prone.

Agility is working on the use of reinforcement-learning and generative AI models to refine and enhance Digits capabilities, enabling it to acquire and hone useful skills over time. The integration of large language models (LLMs) for natural language commands allows for intuitive and effective human-robot interactions.

I think it becomes super compelling long term when we can build expert versions of LLMs or multimodal models that allow us to take all of the information all the things that we've done with any one robot and combine that into a larger database, that helps us optimize, said Wise. So instead of someone telling Digit to do a task through a LLM model, they could just prompt the model to say: I'm trying to solve this problem, can you tell me the best way to do this? and then it will, basically program Digit to do it, she added.

Its important to not forget about safety, said Wise. One of the next things we are going to see with MMRs is the real practical application for safety. Currently there is one R15.08 standard for governing industrial mobile robots that includes AMRs and MMRs. One of the big challenges of this standard, according to her, is that its somewhat silent on dynamically stable robots.

Here is an exclusive Tech Briefs interview with Wise, edited for length and clarity.

Tech Briefs: Do you see the adoption of humanoid robots in manufacturing and logistics industries growing? Which other applications will use MMRs?

Melonee Wise: I think what you'll see is a progression from industrial spaces to light industrial spaces to public spaces. Thats the kind of the approach we are taking. Industrial spaces are manufacturing, logistics, construction, and inspection. Light industrial spaces are things like back of house retail back of your grocery store or hotels and hospitals. Then general public is the front of the house and hotel, the front of the house grocery store in urban settings. We are very focused right now on being very good at logistics and manufacturing and tackling the problems in those spaces and then generalizing. We are trying to become the App Store for labor we have a standardized robot that you then deploy new capabilities to. So, imagine a world in which you eventually one day have your own home robot, and you want Digit to do a new task, so you just pull up your phone and you flick the new capability to Digit. Thats the grand vision we have but we see that the practical steps are to first start in spaces where we can be successful.

Tech Briefs: Are there any specific technological challenges that could prevent adoption of humanoid robots in industrial spaces?

Wise: The biggest barrier to entry to any of this is how do we make this technology safe? When you look at industrial environments or light industrial environments, all of that in the United States is regulated by OSHA. In the European market, it's regulated by different equivalent bodies for worker safety. And then when we get outside of these environments, it really comes down to just general public safety. That would most likely be governed by consumer safety laws in the United States . The biggest challenge is that right now we have a standard for industrial mobile robots, which covers MMRs, but it's somewhat silent on how you deal with robots like Digit. So, first thing that we have to do right now is help to work to improve that standard. And second, figure out a technology solution to engineer a safe solution.

Tech Briefs: Are there any enabling technologies in the humanoid robot space which are exciting right now?

Wise: There are a lot of exciting technologies that are related to the kind of large language models and foundation models that allow us to basically learn new behaviors and skills for the robot very rapidly. So that we can just train the robot and to learn policies for how to grab the tote in different ways or do new tasks like manipulate boxes versus totes or, or open doors. LLMs are very good at taking a high-level directive and then composing a set of tasks to be done. Right now, we have a visual programming language, but we hope in the near future, someone could just through natural language describe what they want the robot to do. Then it will compose the programming for the user behind the scenes and run that program.

Tech Briefs: Moving forward how do you see Digit evolving?

Wise: The big things that we are focused on in the next few years is full collaborative safety. This means being able to be side by side with people on the production floor and increasing some of the capabilities of Digit. Right now, its payload is 16 kgs and we want to go to 25 kgs. We want to be able to charge it faster and run for longer. I think thats the hardware focus. But when we think about the skills that we want Digit to have going forward, we are focused on it being able to pick up new skill sets that are beyond tote handling, box handling, and go to machine tending. Those are software advances.

Tech Briefs: When will humanoid robots become part of our lives?

Wise: I think it's important to reflect on how long it has taken for autonomous cars to become part of our daily lives because it's very similar in that nature. We started talking about autonomous cars being part of our daily lives in 2004. Twenty years later, we are still probably 10 years from that. In the next two years, MMRs will be part of everyday worker lives. Today, Agility is already deploying with customers. Over the next two to five years, you will see a large swath of adoption, very similar to AMRs. I think it will take a lot longer after that to go out to your home, but before that MMRs will get to construction and hospitals probably in the next 10 years.

This article was written by Chitra Sethi, Editorial Director, SAE Media Group. For more information, visit http://www.agilityrobotics.com.

More:

Humanoid Robots: The Next-Generation Robotic Workforce - Tech Briefs

The Howard D. McMillan Middle School robotics teams from Miami-Dade County Public Schools (M-DCPS) recently traveled to Dallas, TX, to compete in the VEX Robotics World Championship thanks to the generosity of the Kiwanis Club of Miami.

This is exactly the type of function we get involved in, said Bruce Ross, president of the 102-year Kiwanis Club of Miami, one of South Floridas most active community service organizations. Were so happy you qualified for this international competition in Dallas that we wanted to help you with this journey.

With that, Ross, Kiwanis treasurer Chuck Little and Kiwanis secretary Diana Morrell unwrapped a surprise oversized check for $6,000 that drew audible gasps from members of the robotics program.

The check topped off the year-around fundraising efforts of the West Kendall school and enabled it to send four four-person teams to compete, including the top team in Florida comprised of Ellis Lee, Rowan Liro, Andrew Rothen and Sirius Harmon. In addition, another four members of the program traveled with the competitors.

We were so excited to welcome the Kiwanis Club of Miami, said McMillan Middle School principal Dr. Justin Koren. This was an incredible opportunity for 20 of our students to travel to Dallas for the World Championship. Without a doubt, this is another reason Howard D. McMillan Middle School is the best choice for education.

Following the check presentation, members of the robotics teams demonstrated their robots to the Kiwanis officials and answered questions from the media.

As a way of saying thank you to the Kiwanis Club of Miami, the McMillan robotics teams placed Kiwanis International logos on their robots.

What the Kiwanis Club of Miami has done is simply fantastic, said robotics coach Dale Adamson. Not only did it allow us to send more teams that qualified but overall showed the students that people in the community care. That is an invaluable lesson that will stick with them forever.

ABOUT US:

For more Miami community news, look no further than Miami Community Newspapers. This Miami online group of newspapers covers a variety of topics about the local community and beyond. Miamis Community Newspapers offers daily news, online resources, podcasts and other multimedia content to keep readers informed. With topics ranging from local news to community events, Miamis Community Newspapers is the ideal source for staying up to date with the latest news and happenings in the area.

This family-owned media company publishes more than a dozen neighborhood publications, magazines, special sections on their websites, newsletters, as well as distributing them in print throughout Miami Dade County from Aventura, Sunny Isles Beach, Miami Beach, Coral Gables, Brickell, Coconut Grove, Pinecrest, South Miami, Kendall, Palmetto Bay, Cutler Bay and Homestead. Each online publication and print editions provide comprehensive coverage of local news, events, business updates, lifestyle features, and local initiatives within its respective community.

Additionally, the newspaper has exclusive Miami community podcasts, providing listeners with an in-depth look into Miamis culture. Whether youre looking for local Miami news, or podcasts, Miamis Community Newspapers has you covered. For more information, be sure to check out: https://communitynewspapers.com.

If you have any questions, feel free to email Michael@communitynewspapers.com or Grant@communitynewspapers.com.

Connect To Your Customers & Grow Your Business

Visit link:

Kiwanis Club of Miami helps fund McMillan MS robotics team trip - Miami's Community Newspapers