Google Gemini AI model brings real-time intelligence to bi-arm robots
Google DeepMind has announced the launch of a new artificial intelligence model tailored for robotics, capable of functioning entirely on a local device without requiring an active data connection. NamedGemini Robotics On-Device, the advanced model is designed to enable bi-arm robots to carry out complex tasks in real-world environments by combining voice, language and action (VLA) processing.
In a blog post, Carolina Parada, Senior Director and Head of Robotics at Google DeepMind, introduced the new model, highlighting its low-latency performance and flexibility. As it operates independently of the cloud, the model is especially suited to latency-sensitive environments and real-time applications where constant internet connectivity is not feasible.
Currently, access to the model is restricted to participants of Google's trusted tester programme. Developers can experiment with the AI system through the Gemini Robotics software development kit (SDK) and the company's MuJoCo physics simulator.
Although Google has not disclosed specific details about the model's architecture or training methodology, it has outlined the model's robust capabilities. Designed for bi-arm robotic platforms, Gemini Robotics On-Device requires minimal computing resources. Remarkably, the system can adapt to new tasks using only 50 to 100 demonstrations, a feature that significantly accelerates deployment in diverse settings.
In internal trials, the model demonstrated the ability to interpret natural language commands and perform a wide array of sophisticated tasks, from folding clothes and unzipping bags to handling unfamiliar objects. It also successfully completed precision tasks such as those found in industrial belt assembly, showcasing high levels of dexterity.
Though originally trained on ALOHA robotic systems, Gemini Robotics On-Device has also been adapted to work with other bi-arm robots including Franka Emika's FR3 and Apptronik's Apollo humanoid robot. According to the American tech giant, the model exhibited consistent generalisation performance across different platforms, even when faced with out-of-distribution tasks or multi-step instructions.
Hashtags
Try Our AI Features
Explore what Daily8 AI can do for you:
Comments
No comments yet...
Related Articles
Time of India
an hour ago
- Time of India
Startup CEO says Google had everything ..., yet OpenAI beat them to the LLM Gold Rush, Elon Musk's 'one-word' reply
An online debate over AI race of Silicon Valley reignited recently. Tesla CEO Elon Musk also presented his point of view on the debate with a one-word response. Recently, a US federal judge ruled that Anthropic and AI company did not break any copyright laws while training AI model Claude using books. The judge pointed out that the use of books was a fair step and an AI model does not copy or reproduce books but it learns from them and then generate original content. Soon after the judgement, an online debate started on X (formerly known as Twitter). A startup CEO Luis Batalha has asserted that Google , despite possessing "everything" needed, was ultimately outmaneuvered by OpenAI in the burgeoning Large Language Model (LLM) "gold rush." 'Google had everything: the transformer, massive compute, access to data, even Google Books - yet OpenAI beat them to the LLM gold rush. Having the pieces isn't the same as playing the game,' wrote Batalha. Tesla CEO Elon Musk also supported the sentiment with a one-word reponse 'True'. Originally Google has been at the forefront of AI research. The company has published seminal papers and has also developed advanced models. However, with the launch of ChatGPT , OpenAI managed to capture imagination of millions and ignited the current "LLM Gold Rush," forcing other tech giants to accelerate their own public-facing generative AI initiatives. Critics suggest that Google's cautious approach, perhaps due to its established market position and the potential risks of deploying rapidly evolving AI, allowed a leaner, more focused entity like OpenAI to seize the early lead.
Time of India
an hour ago
- Time of India
UK politics blunts antitrust action against Google
Academy Empower your mind, elevate your skills Britain's competition regulator has finally come up with a plan to control Google's huge search business, but a shift in the political wind in favour of big tech and the money it invests makes it more of a bark than a Competition and Markets Authority spent years setting up a regime to intervene in the operations of tech giants such as Google, Apple and Amazon, saying it needed special expertise and powers to drive competition in the digital just as it received new powers, Britain's Labour government said its need to grow the economy meant tough regulation was now CMA, chaired by a former Amazon executive, has touted a targeted approach as the way to meet its goal of reining in big tech without throttling investment from an industry that has spent tens of billions of pounds in Tuesday, it proposed designating Google as having "strategic market status" in search, giving it the power to impose conditions on the U.S. tech firm such as changing the way it ranks search results or offering users more experts said the designation was no surprise, coming long after similar moves in the United States and the European Union."Everyone has been at the search rodeo for years, there are EC (European Commission) decisions, U.S. judgements," Cristina Caffarra, a competition economist, said. "What the CMA is doing is purely performative."Nonetheless, the CMA's first designation is being closely watched by tech groups, lawyers, and business owners to see how it operates in the new political announcing its proposals, CMA Chief Executive Sarah Cardell was careful to stress its "targeted and proportionate actions" to regulate a sector innovating at breakneck speed via artificial intelligence, and mindful of the political Ronan Scanlan, a partner at Steptoe International and former deputy director at the CMA, said Britain's Digital Markets, Competition and Consumers Act gave the CMA broad powers, but in practice it didn't have the political capital to make grand interventions."The DMCC Act, which was billed as this revolutionary new tool that the CMA could wield, has arrived three years too late and is becoming a bit of an albatross around its neck," he said."It's up against huge players like Google, Apple, Amazon, with a lot of political connections, and now - in a new political reality - somehow has to try to extricate itself with the minimum amount of damage."The CMA's delicate balancing act is made harder by U.S. President Donald Trump's muscular defence of U.S. business interests, and Scanlan said the regulator would want to see what would happen with Google of the measures the CMA is proposing, such as choice screens for consumers to easily opt for alternative search engines, have been around for such as changing the ranking of results to limit Google favouring its own services, could have more impact if they are confirmed in the CMA's final decision in Smith, a competition lawyer at Geradin Partners and a former CMA legal director, said there was a question mark over political support for some of the regulator's tougher proposals, but thought it was trying to stick to its guns."Given the new context, it's still implementing the regime properly," he said, adding that the U.S. Department of Justice had proposed measures that could lead to a breakup of Google, particularly in its search and advertising businesses."The idea that the CMA is going too far by putting in a choice screen, it's quite ludicrous."Despite that, Alphabet-owned Google warned it may not bring new features and services to Britain if the regulator goes ahead with the proposals, and said "proportionate, evidence-based regulation" was needed if Britain was to grow its which employs around 7,000 people in Britain, accounts for more than 90% of all general search queries in the country, with more than 200,000 businesses relying on its search advertising to reach their according to submissions to the CMA from the likes of flights and hotel website Skyscanner and the recommendation platform Checkatrade, that dominance may have enabled it to favour its own services over their offerings, and they want regulatory Valley has been wary of the CMA since 2023, when it blocked Microsoft's $69 billion acquisition of the "Call of Duty" maker Activision-Blizzard. Having sparked fury from the U.S. companies, it then tore up its own rule book to approve the case after Microsoft made some second investigation under its new powers is examining mobile operating systems, targeting Google and CMA investigations had pointed to Amazon as the subject of the third strategic market status investigation that was due to be announced this summer. On Tuesday, however, the CMA pushed the third case back to next year.
Time of India
an hour ago
- Time of India
Google unveils Gemini CLI for developers - 5 critical features of the open-source AI agent
Google has just launched Gemini CLI, an open-source AI assistant designed specifically for developers to have access to the command line interface, according to the company's blog post. For developers who spend a lot of their day in the terminal, it takes AI to where they work, providing quick assistance with a wide range of tasks, from content generation and problem solving to deep research and task management, according to Google's blog post. Google said, "We've also integrated Gemini CLI with Google's AI coding assistant , Gemini Code Assist , so that all developers — on free, Standard, and Enterprise Code Assist plans — get prompt-driven, AI-first coding in both VS Code and Gemini CLI." by Taboola by Taboola Sponsored Links Sponsored Links Promoted Links Promoted Links You May Like Join new Free to Play WWII MMO War Thunder War Thunder Play Now Undo The following are five important features that set Gemini CLI apart: 1. Generous free-tier usage Individual developers can utilise Gemini CLI for free by simply logging in with a personal Google account, as per the report. This grants access to Gemini 2.5 Pro and a massive 1 million token context window, and for the preview period, Google is providing "60 model requests per minute and 1,000 requests per day at no charge," according to the blog post. Live Events ALSO READ: Gas relief coming? Oil now cheaper than it was before Iran-Israel war — what it means for your wallet 2. Seamless integration with Gemini Code Assist Gemini CLI is integrated with Gemini Code Assist, Google's AI coding assistant in VS Code, as per Google's blog post. This means that developers on any plan have the same AI assistance in both their terminal and their IDE, as per the report. Code Assist utilises agent mode to author tests, debug problems, create features, and even work on complicated things like code migration, according to the blog. Google said, "Based on your prompt, Code Assist's agent will build a multi-step plan, auto-recover from failed implementation paths and recommend solutions you may not have even imagined." 3. Total AI power in your terminal The CLI will streamline a developer's workflow in natural language that allows the user to code, debug, work with files, and execute commands, as per Google's blog post. The tech giant said that the Gemini CLI provides powerful AI capabilities, which include, ground prompts with Google Search, extend Gemini CLI's capabilities, customize prompts and instructions and automate tasks and integrate with existing workflows. ALSO READ: McDonald's dumps Krispy Kreme — no more Doughnuts with your fries? Fans react to abrupt breakup 4. Extensible and customizable Google said, "We also built Gemini CLI to be extensible, building on emerging standards like MCP, system prompts (via and settings for both personal and team configuration. We know the terminal is a personal space, and everyone deserves the autonomy to make theirs unique." 5. Completely open source and developer-friendly Gemini CLI is open-source under the Apache 2.0 license , as per the blog post. Developers can view the code, see how it functions, and contribute via GitHub, according to the report. Google invites the community to report bugs, propose features, and enhance security. FAQs What is Gemini CLI? It's an open-source AI assistant that brings Google's Gemini AI model directly into your terminal. Can Gemini CLI help me write and debug code? Yes, it's designed to assist with coding, debugging, running commands, and automating tasks, all through natural language.
