Google's humanoids are now capable of carrying out complex, multi-step tasks using the newly released Gemini 1.5 model family.
Google DeepMind released a video on YouTube on September 25, revealing how their humanoids are now capable of performing multi-step, complex tasks using multimodal reasoning. In a series of tests carried out by engineers, Google ’s robots passed the banana test, which involved serving different fruits into plates based on color.
The humanoids’ thinking capabilities are derived from the Gemini Robotics 1.5 family of models, allowing the machines to perceive, think, and execute complex, real-world tasks autonomously.The Gemini Robotics 1.5 family consists of two models: Gemini Robotics 1.5, which turns visuals and instructions into robot actions, and Gemini Robotics-ER 1.5, which reasons about the world and creates step-by-step plans to solve tasks.The banana test: Before and afterIn the previous version of Gemini Robotics, the main task was to have the robot pick up a banana and place it in a bowl. It enabled these humanoids to follow and execute one instruction at a time.With Gemini Robotics 1.5, the humanoids sorted three different fruits, including a banana, into different plates based on color. Jie Tan, a Senior Staff Research Specialist at Google DeepMind, demonstrated the experiment.In doing so, the bi-arm Franka robot demonstrated its ability to follow multi-step instructions and execute them one by one with precision.Sorting laundryAnother test involved Apptronik’s humanoid, Apollo, sorting laundry. In this scenario, the humanoid sorted clothes based on color in two different baskets – white and black.To make it more challenging after the first successful attempt, the engineers rotated the baskets. They changed their positions to check if the robot could sense this positional change mid-operation and act as necessary. Apollo successfully recognized the change and sorted the clothes accordingly.Exploring agentic capabilitiesGemini Robotics 1.5 also allows robots to study their environments using embodiment learning and take actions based on their observations. For instance, Google’s ALOHA 2 robot did most of the tasks in the experiments, but the same can also be carried out by Apollo and the bi-arm Franka robot. The new AI models also unlock agentic capabilities for robots. For example, a robot might be asked to sort objects into the correct compost, recycling, and trash bins based on local rules.To do this, it would first need to search online for the area’s recycling guidelines, then visually inspect the objects, decide where each item belongs, and finally carry out the full sequence of steps to put them away.This type of multi-step reasoning and execution is made possible through an agentic framework. The two models work together to help robots complete real-world tasks with greater transparency and reliability. One focuses on perception-to-action, and the other on reasoning and planning. The responsibility for safetyGoogle is emphasizing safety in its Gemini Robotics 1.5 models by teaching robots to think about risks before acting, respect human rules, and avoid accidents.With support from dedicated safety teams and the updated ASIMOV benchmark, Gemini Robotics-ER 1.5 achieved state-of-the-art results in safety tests, ensuring safer real-world deployment.
AI Model Google Google Deepmind Humanoid Humanoids Multimodal AI Multimodal Robot New AI Model Robot Robots
United States Latest News, United States Headlines
Similar News:You can also read news stories similar to this one that we have collected from other news sources.
How the outcome of antitrust lawsuits could save consumers moneyBoth Google and Amazon have been in court recently, in cases brought forward by the federal government.In Google's case, a federal judge ordered Google to shar
Read more »
Hidden Google Photos Code Suggests Return Of Missing Search FeatureGoogle Photos tests return of missing “More Like This” feature, helping you find and manage similar photos in your library
Read more »
Google Clock App Compatibility Issue on Galaxy Watch and OnePlus WatchUsers of Galaxy Watch and OnePlus Watch smartwatches are reporting that Google's Clock app is no longer installable, making them incompatible with the app. This issue is impacting non-Pixel Wear OS devices, with no available workaround currently. Google has not yet commented on the problem.
Read more »
How the outcome of antitrust lawsuits could save consumers moneyBoth Google and Amazon have been in court recently, in cases brought forward by the federal government.In Google's case, a federal judge ordered Google to shar
Read more »
XXKK Exchange Launches App on Google Play, Bringing a Better Mobile Trading ExperienceDenver, United States, 29th September 2025, Chainwire
Read more »
What To Expect From Google’s Big October Hardware LaunchGemini for Home will land on a bunch of new smart home tech on 1st October.
Read more »