Ivan Hernandez Dalas - Mechatronics

The AGIBOT G2 wheeled robot provided subway guidance at WAIC 2026. Source: AGIBOT Embodied AI including humanoid robots are moving toward wider production and deployment. AGIBOT yesterday unveiled four new products at the World Artificial Intelligence Conference, or WAIC. The company said they expand its portfolio across full-size humanoid platforms, heavy-payload industrial task robots, and direct-drive dexterous manipulation systems. “The industry should no longer judge embodied AI by whether a robot can complete an impressive demonstration once, but by whether it can be manufactured, delivered and integrated reliably into real operating environments,” stated Peng Zhihui, AGIBOT co-founder, president, and chief technology officer. “AGIBOT A3 Ultra, G2 Max, and OmniHand 3 Ultra-M address three essential layers of that challenge: the humanoid platform, industrial task execution, and dexterous manipulation,” he added. “Together with our recent production and factory-deploy...

Imagine you want to teach a robot to push an object on a table. The standard recipe in robot learning is to collect hundreds of expert demonstrations on a real robot, train an imitation learning policy on that data, and then evaluate the policy by running it many times on the same real robot. Both stages (data collection and evaluation) are slow, expensive, and hard to reproduce: hardware breaks, lighting changes, objects drift out of place, and every new task means more hours in the lab. A natural question is whether we can replace some of this real-robot work with a simulator. Classical physics-based simulators are powerful, but building one for a new task means manually modeling geometries, contacts, friction, and deformation, and the resulting simulator often still does not match reality closely enough for policies trained inside it to transfer. In our work, we take a different route. We build an Interactive World Simulator : a learned, action-conditioned video prediction model ...

Flexion is building a reinforcement learning and sim-to-real platform for humanoid robots. Source: Flexion In the past 18 months, humanoid robotics companies have raised billions of dollars – a majority of which is quietly funding hiring humans to operate robots. This means the robotics industry has a teleoperation and data problem it keeps describing as a labor solution. Teleoperation and human demonstration at scale have become the dominant method for training physical AI systems, attracting serious capital, recruiting workers across lower-wage economies, and earning enthusiastic coverage as evidence of progress. The assumption underneath all of it is that enough demonstrations will eventually produce robots capable of generalizing across real environments. I believe that assumption deserves a lot more scrutiny than it’s getting. Teleoperation hits a structural wall Language models trained on text can draw from decades of writing, articles, and books. With robots, there...

Coherence Guard is designed to enable service robots to behave appropriately around people, says Palm Garden AI. Source: aivora studio AI, via Adobe Stock As so-called general-purpose robots and humanoids continue to evolve, so is the software stack to enable them to conduct useful tasks around people. Palm Garden AI is developing Coherence Guard, which it described as a “platform-agnostic relational decision layer for human-facing robots.” “The aim is not to replace perception, motion planning, reinforcement learning, or existing robot control stacks,” said Joachim Scheuerer, CEO of Palm Garden AI. “Rather, it functions as an additional pre-action evaluation layer: Before a robot executes an action, the layer can evaluate whether the action is relationally coherent in a real human environment.” “This includes signals such as timing, proximity, boundary requests, emotional tone, trust preservation, respectful withdrawal, and the difference be...

The Robot Report Podcast · Transforming Solar Construction Through Robotics with Deise Yumi Asami In Episode 253 of The Robot Report Podcast, Deise Yumi Asami shares how her AI-enabled robotics startup, Maximo, is making solar panel installation faster, safer, and more efficient. She talks about how robotics, AI vision, and smart field deployment are helping reshape the future of renewable energy infrastructure. Yumi Asami also shares her experiences with starting a new company from the ground up while being incubated within parent company The AES Corp. Learn how a large organization can encourage and celebrate innovation and how AES organized its innovation group. Deise Yumi Asami, founder of Maximo. Deise Yumi Asami is the founder of Maximo at AES. Drawing on her engineering background, she led the development and incubation of Maximo, an AI-enabled robotic platform transforming utility-scale solar construction by automating the installation of solar modules using AI -base...

Weave Robotics plans to begin Isaac 1 deliveries this fall. | Credit: Weave Robotics Weave Robotics has introduced Isaac 1, a wheeled home humanoid designed to take on everyday chores such as folding laundry, tidying rooms, making beds, and putting away toys. The San Francisco-based startup is launching Isaac 1 as a consumer robot priced at $7,999, or $449 per month. The robot is meant to look approachable rather than intimidating, with a cartoon-like face and a body wrapped in soft fabric. Its friendly exterior is paired with a wheeled base, two arms, and two-finger parallel grippers designed for common household manipulation tasks. Issac 1 is intentionally designed to be non-intimidating and friendly. | Credit: Weave Robotics Isaac 1 can adjust from 3 ft. (0.9 m) tall to 5 ft. 9 in. (1.7 m), giving it enough range to pick items up from the floor, work at counter height, and place objects on higher shelves. It also features autonomous navigation , allowing it to move from room t...