New AI agent evolves algorithms for math and practical applications in computing by combining the creativity of large language models with automated evaluators

Amazon has just unveiled its newest warehouse robot called Vulcan, which has a "sense of touch." Designed to gently stow items using pressure-sensitive gripping and artificial intelligence (AI), Vulcan is now being tested in two Amazon facilities, in Spokane, Washington state, US, and Hamburg, Germany.

With major tech players investing heavily in this next generation of robotics, construction leaders are beginning to ask: could humanoid robots soon find a place in the industry. And, if so, what would that mean for workers, safety, and the economics of the job site?

Kushal Kedia (left) and Prithwish Dan (right) are members of the development team behind RHyME, a system that allows robots to learn tasks by watching a single how-to video.

By Louis DiPietro

Cornell researchers have developed a new robotic framework powered by artificial intelligence – called RHyME (Retrieval for Hybrid Imitation under Mismatched Execution) – that allows robots to learn tasks by watching a single how-to video. RHyME could fast-track the development and deployment of robotic systems by significantly reducing the time, energy and money needed to train them, the researchers said.

“One of the annoying things about working with robots is collecting so much data on the robot doing different tasks,” said Kushal Kedia, a doctoral student in the field of computer science and lead author of a corresponding paper on RHyME. “That’s not how humans do tasks. We look at other people as inspiration.”

Kedia will present the paper, One-Shot Imitation under Mismatched Execution, in May at the Institute of Electrical and Electronics Engineers’ International Conference on Robotics and Automation, in Atlanta.

Home robot assistants are still a long way off – it is a very difficult task to train robots to deal with all the potential scenarios that they could encounter in the real world. To get robots up to speed, researchers like Kedia are training them with what amounts to how-to videos – human demonstrations of various tasks in a lab setting. The hope with this approach, a branch of machine learning called “imitation learning,” is that robots will learn a sequence of tasks faster and be able to adapt to real-world environments.

“Our work is like translating French to English – we’re translating any given task from human to robot,” said senior author Sanjiban Choudhury, assistant professor of computer science in the Cornell Ann S. Bowers College of Computing and Information Science.

This translation task still faces a broader challenge, however: Humans move too fluidly for a robot to track and mimic, and training robots with video requires gobs of it. Further, video demonstrations – of, say, picking up a napkin or stacking dinner plates – must be performed slowly and flawlessly, since any mismatch in actions between the video and the robot has historically spelled doom for robot learning, the researchers said.

“If a human moves in a way that’s any different from how a robot moves, the method immediately falls apart,” Choudhury said. “Our thinking was, ‘Can we find a principled way to deal with this mismatch between how humans and robots do tasks?’”

RHyME is the team’s answer – a scalable approach that makes robots less finicky and more adaptive. It trains a robotic system to store previous examples in its memory bank and connect the dots when performing tasks it has viewed only once by drawing on videos it has seen. For example, a RHyME-equipped robot shown a video of a human fetching a mug from the counter and placing it in a nearby sink will comb its bank of videos and draw inspiration from similar actions – like grasping a cup and lowering a utensil.

RHyME paves the way for robots to learn multiple-step sequences while significantly lowering the amount of robot data needed for training, the researchers said. They claim that RHyME requires just 30 minutes of robot data; in a lab setting, robots trained using the system achieved a more than 50% increase in task success compared to previous methods.

“This work is a departure from how robots are programmed today. The status quo of programming robots is thousands of hours of tele-operation to teach the robot how to do tasks. That’s just impossible,” Choudhury said. “With RHyME, we’re moving away from that and learning to train robots in a more scalable way.”

This research was supported by Google, OpenAI, the U.S. Office of Naval Research and the National Science Foundation.

Read the work in full

One-Shot Imitation under Mismatched Execution, Kushal Kedia, Prithwish Dan, Angela Chao, Maximus Adrian Pace, Sanjiban Choudhury.

Engineers built E-BAR, a mobile robot designed to physically support the elderly and prevent them from falling as they move around their homes. E-BAR acts as a set of robotic handlebars that follows a person from behind, allowing them to walk independently or lean on the robot's arms for support.

As demand for robotic delivery grows worldwide, an Australian-made design is leading the charge into a new era of temperature-controlled food delivery.

At less than one and a half inches tall, roughly the same height as a LEGO minifigure, the world's smallest self-contained bipedal robot can self-start from standstill, walk faster than a half mile per hour, turn, skip, and ascend small steps with just the power of its on-board battery, actuator, and control system.

A robotic hand can pick up 24 different objects with human-like movements that emerge spontaneously, thanks to compliant materials and structures rather than programming.

A robotic hand developed at EPFL can pick up 24 different objects with human-like movements that emerge spontaneously, thanks to compliant materials and structures rather than programming.

The United States population is older than it has ever been. Today, the country's median age is 38.9, which is nearly a decade older than it was in 1980. And the number of adults older than 65 is expected to balloon from 58 million to 82 million by 2050. The challenge of caring for the elderly, amid shortages of care workers, rising health care costs, and evolving family structures, is an increasingly urgent societal issue.

Pick and place robots perform repetitive handling tasks with speed and consistency, making them invaluable across industries. These robots depend heavily on the right camera setup. Get insights about the challenges faced by cameras, use cases, and their biggest benefits.

Engineers have taught a simple submarine robot to take advantage of turbulent forces to propel itself through water.

With a novel simulation method, robots can guess the weight, softness, and other physical properties of an object just by picking it up.

Photo credit: Muntaka Chasant, reproduced under a CC BY-SA 4.0 license.

By Kaja Šeruga

Just outside the historic German town of Goslar, a sprawling industrial complex receives an endless stream of discarded electronics. On arrival, this electronic waste is laboriously prepared for recycling. 

Electrocycling GmbH is one of the largest e-waste recycling facilities in Europe. Every year, it processes up to 80 000 tonnes of electronic waste, which comes in all shapes and forms.

Manual dismantling

Despite an impressive array of machinery, more than half of the site’s employees manually prepare the discarded items for recycling. They do this by sorting the incoming waste and removing batteries, which are a fire hazard and a major challenge in e-waste recycling.

“There are more and more devices, they are getting smaller, and they all contain lithium batteries, some of which are permanently installed, soldered or glued in place,” said Hannes Fröhlich, Electrocycling’s managing director. 

“It’s not a dream job, dismantling these appliances every day with hammers and pliers. I think we can do better.”

Some of these tedious tasks could be performed by robots. However, the problem is that every time there is a change in the product or the process, the hardware and software need to be restructured. This can be costly and time-consuming.

To address this issue, an EU-funded research initiative named ReconCycle has managed to automate the process by creating robots that can reconfigure themselves for different tasks. 

New territory for robotics

Researchers from Slovenia, Germany and Italy worked together on this issue at the Jožef Stefan Institute, Slovenia’s leading research facility, from 2020 to 2024.

The team developed adaptable AI-supported robots that are able to remove batteries from smoke detectors and radiator heat metres.

These two products can be found in most households and are replaced every five to eight years, creating large amounts of waste.

“The main challenge is that there are so many different versions of each device. Just think how many different remote controls there are,” said Dr Aleš Ude. He is head of the Department of Automatics, Biocybernetics and Robotics at the Jožef Stefan Institute and coordinates the ReconCycle research team. 

In industrial settings, robots are usually programmed for one specific task, repeating exactly the same series of movements in a predictable environment. 

Instead, the researchers set out to create a robot that can adapt to many different tasks, using state-of-the-art AI. 

“We wanted to expand robotics, introduce robots where there aren’t any yet,” Ude said.

A growing problem

Working with Electrocycling, Ude’s international research team created an adaptable robotic work cell. This is a workspace that consists of at least one robot, its tools and equipment, and its controller.

The novelty here is that this closed system autonomously adapts itself to various tasks, with the help of complex AI-driven software and modular hardware that can be quickly reconfigured. It also uses soft components like SoftHand, a human-like hand that can manipulate objects with great precision.

There are also safety features like collaborative robots and emergency stop buttons.

International collaboration was crucial in securing the right expertise, said Ude. 

“Robotics is very interdisciplinary, so it’s difficult to find the right partners in one country.” 

Thankfully, the new robots are arriving just at the right time, as the amount of e-waste produced every year continues to grow. Almost 5 million tonnes of e-waste are produced in the EU each year, amounting to about 11 kilograms per person. Less than 40% of that is recycled, the European Parliament has warned. 

Globally, around 62 million tonnes of e-waste were produced in 2022 alone, enough to fill 1.5 million 40-tonne trucks, according to UN data. Even more worryingly, the amount of e-waste is rising five times faster than the amount that is being recycled.

The EU is working to reduce e-waste through the Waste from Electrical and Electronic Equipment Directive, which sets the standards for collection and recycling. 

The work of Ude’s team is also aligned with the EU’s digital strategy, which encourages the use of AI in manufacturing to improve efficiency and help achieve climate neutrality by 2050.

Throwing away money

E-waste also has serious economic implications. An estimated €84 billion is lost each year when valuable metals like copper, iron and gold are discarded instead of being reused, according to the UN’s global e-waste monitor. 

At Electrocycling, 80% of the e-waste is recovered as raw materials, such as iron, zinc, gold, silver and palladium – some 35 materials in all.

“People need to understand that this is not just waste, but also raw materials that need to be recycled and kept in circulation, both for economic efficiency and a reduction of CO2,” said Fröhlich. 

New technology can make it even more efficient, and Fröhlich sees a lot of potential in it. 

“I was surprised by how far the technology and AI have already come,” he said. “They even recreated a human hand for the robot.”

Ude hopes to continue working with Electrocycling to improve e-waste solutions further. The hope is also that adaptable robots which can handle changing environments will have applications far beyond e-waste recycling. 

Given more time and development, these robots could even handle general housekeeping, or support carers in senior homes, said Ude. 

“Robotics could be of great help in such areas.”

This article was originally published in Horizon, the EU Research and Innovation magazine.

But Experimental Alternatives Have Problems

While ChatGPT-4o – the default AI engine for writing, research and similar work – remains formidable, some problems are cropping up with experimental models.

Specifically, ChatGPT-o3, ChatGPT-o4 mini and ChatGPT-o4 mini high – which use advanced reasoning – ‘make-up-facts’ more often when responding to questions from users.

Bottom line: If you want to be sure ChatGPT sticks-to-the-facts when auto-writing your emails and other text, there’s a prompt you can use that eliminates such hallucinations.

For the prompt, simply check-out the free sample read of “Auto Writing World-Class Emails With ChatGPT,” by Joe Dysart, available on Amazon.

Once you’re on the Amazon book page, click the free sample read button, scroll to Chapter 6 and grab the free prompt there that deep-sixes hallucinations.

In other news and analysis on AI writing:

*Mark Zuckerberg Releases ChatGPT-Competitor: Facebook inventor Mark Zuckerberg has released a direct competitor to ChatGPT, dubbed ‘Meta AI.’

While Zuckerberg – CEO of Facebook parent company Meta – has already infused many of his company’s apps with artificial intelligence, this is the first time he’s going in a head-to-head competition against today’s major chatbot competitors with a stand-alone AI chatbot.

Designed with the look and feel of ChatGPT, Meta AI “enables users to have natural, back-and-forth voice conversations with AI, edit and generate images — and discover new use cases through a curated Discover feed featuring prompts and ideas shared by the community,” according to writer Carl Franzen.

*ChatGPT: Matching the Right AI Engine for Your Task: ChatGPT runs on a number of different AI engines these days – each optimized for specific tasks.

Here’s the breakdown:

–Everyday writing: ChatGPT-4o is the go-to alternative for everyday writing tasks and heavily tried, true and tested.

–Advanced Creative Writing: ChatGPT-4.5 is billed as an advanced creative writing tool – especially for users looking for AI with advanced emotional intelligence. The only downside: If you’re on ChatGPT Plus, you can only send 20 messages to ChatGPT-4.5 each month.

–Advanced Reasoning: ChatGPT-3o, ChatGPT-o4 mini and ChatGPT-o4 mini high

*Google Rolls-Out AI for the ’Under-13’ Crowd: In a controversial move, Google is allowing kids to access its Gemini Chatbot under their parent-managed Google accounts.

Observes writer Natasha Singer: “Google acknowledged some risks in its email to families this week, alerting parents that Gemini can make mistakes and suggesting they help your child think critically about the chatbot.”

You mean help your five-year-old think critically about what an AI chatbot – which can be interacted with via voice conversation – says to your five-year-old when you might not be around?

Sure. That’ll work.

*ChatGPT-Maker Pitches Itself as the Solution for Democracies: In another sign that much of the free world may run on its own version of AI, ChatGPT’s maker OpenAI is marketing itself as the solution for democracies.

Observes an OpenAI blog post: “This is a moment when we need to act to support countries around the world that would prefer to build on democratic AI rails, and provide a clear alternative to authoritarian versions of AI that would deploy it to consolidate power.”

*Study: AI Writer/Editor Grammarly Boosts Productivity: Grammarly is out with a new study revealing that customers using its AI tools experience a 17% boost in productivity.

The reason: Customer service agents that used Grammarly in their writing interactions with customers found that their writing was clearer, more mistake-free, sounded more on brand – and was easier to finish, according to writer Esther Shittu.

Grammarly was able to prove the new efficiencies by putting its AI writer/editor to an A/B test at companies, in which half of employees in the test had access to Grammarly — while the other half did not.

*Top AI Writing Tools for Students: The Houston Press has come up with its list of preferred tools for student writing.

Along with general-use tools like Grammarly and Rytr, Houston Press also likes the following for academic-focused writing:

–StudyPro: All-in-one academic platform specializing in research, writing, and editing

–Paperpal: Good for research-based academic writing and journal formatting

–Samwell.ai: Good for guided essay planning and structured development

–Quarkle.ai: Good for idea brainstorming and fast topic exploration

*AI News Summarizer Promises to Bring Readers to News Outlets: Particle, a new Web app that offers AI-powered summaries of breaking news, is promising to bring readers to the news outlets that are the sources of those summaries.

Observes writer Sarah Perez: Particle “highlights the news outlets covering a story by sharing links to their stories directly alongside its AI summaries.

“In early tests on mobile, the company found that readers were clicking through to the publishers’ sites via these links, leading Particle to begin partnering with specific publishers like Reuters, Fortune, and the AFP to display their links more prominently.”

*Many Journalists Remain Fearful of AI: Years after being cast as an ‘AI collaboration buddy,’ AI-automated writing and similar apps available with AI still leave many journalists fearing for their jobs.

Specifically, a new study finds that 57.2% of journalists believe AI could displace even more jobs in coming years.

Even so, the study revealed a silver lining: “Approximately 50% believe that AI could create new roles within journalism, particularly in managing and overseeing AI tools,” according to writer Chris Price.

*AI Big Picture: People Are Falling in Love With AI Companions: In a world often starved for intimacy, AI companions are stepping up as solutions – often with unintended consequences.

This riveting video from “60 Minutes Australia” finds that growing numbers of people are coupling with AI, insisting that their AI companions are more trustworthy than many humans.

There’s also a darkside to the trend: One male teenager committed suicide in an attempt to be closer to his “AI lover.”

Share a Link:  Please consider sharing a link to https://RobotWritersAI.com from your blog, social media post, publication or emails. More links leading to RobotWritersAI.com helps everyone interested in AI-generated writing.

–Joe Dysart is editor of RobotWritersAI.com and a tech journalist with 20+ years experience. His work has appeared in 150+ publications, including The New York Times and the Financial Times of London.

The post ChatGPT’s Workhorse AI Engine Still Solid Choice appeared first on Robot Writers AI.