Motion Control & Actuation

Skild AI has unveiled a new post-training approach for embodied intelligence that uses physical self-play to teach humanoid robots highly dynamic skills. In a demonstration centered on soccer, the company showed a robot defending, dribbling past opponents and scoring—abilities acquired largely through self-competition rather than hand-coded rewards. The robot tracks the ball closely and denies the human opponent possession. After briefly losing focus and conceding an interception, it recovers, turns, runs with the ball and finishes into the goal. The significance is not robot soccer itself, but the use of physical self-play. Most robot foundation models are pretrained on human data. Skild’s S1 model, released last month, follows that pattern and can learn tasks from in-context demonstrations, similar to prompt-based...

A humanoid robot weighing 37.15 kg pulled a 1,434 kg car 9.92 metres on two legs in Beijing, setting a Guinness World Record for the heaviest vehicle pulled by a humanoid robot under 40 kg, its developers said. The robot was powered by Thor, a whole-body control model jointly developed by Chinese robotics firm XYZ Embodied AI Co. (XYZ), Ltd. and the Beijing Academy of Artificial Intelligence (BAAI). The challenge took place in Beijing’s Yizhuang. Developers said the feat was not merely a display of brute force. The core difficulty was maintaining balance and coordinating the whole body while withstanding a large, changing external force. Unlike running, jumping or dancing, pulling a car is a strong-interaction task: the robot’s movement...

Boston Dynamics has introduced a new four-fingered hand for its Atlas humanoid, a 13-degree-of-freedom, directly actuated design intended for mass production. The hand marks a strategic shift. Earlier Atlas hands had seven degrees of freedom and were designed to grasp a wide range of objects. The new version focuses on manipulating them. “We considered many, many designs,” said Alberto Rodriguez, director of robot behavior for Atlas. “It boils down to a trade-off of competing objectives.” The design omits a pinky and is tailored for high-fidelity simulation and sim-to-real reinforcement learning. It uses a single actuator type, fully encapsulated joints and no fragile cables crossing joints. Boston Dynamics said the hand can slide the thumb tip along and across the other...

Chinese robotics firms LEJU Robot and Heyman have jointly launched a scene-oriented solution centred on a general-purpose humanoid robot body and a multi-fingered dexterous hand, aiming to eliminate the need for custom end-effector swaps across diverse industrial tasks. The system addresses common pain points such as trade-offs between payload and precision, low gesture-development efficiency, and difficult redeployment, the companies said. The integrated dexterous hand features a variable-configuration design that supports seven plus grip modes – including two-finger pinch, internal expansion, enveloping grasp, and two-handed hold – on the same hardware. It delivers a payload of at least 24 kg and a repeated positioning accuracy of ≤0.03 mm, outperforming the industry norm of 0.2 mm. This allows a single manipulator to...

Lyte, a U.S.-based physical AI perception infrastructure startup, has raised $165 million in a Series C funding round, valuing the company at $1.6 billion post-money, the company said. The round was led by Maverick Silicon, with participation from existing investors including Fidelity Management & Research, Atreides Management, Key1 Capital, and Ora Global. Proceeds will be used to boost sensor chip production, scale its LyteVision integrated perception platform, and expand its workforce. Founded in 2021, Lyte emerged from stealth in January this year and had previously raised approximately $107 million. The company develops chips, multimodal sensors, and spatial perception software to help robots navigate environments more safely. Its flagship unified spatial intelligence platform, LyteGalaxy, integrates sensors, compute, software, and algorithms into...

Psi R1 marks the release of the first reinforcement learning–driven Vision-Language-Action (VLA) model, successfully demonstrating dexterous, long-horizon task execution in an open-ended Mahjong environment. · Millimeter-Level Dexterous Manipulation: PsiBot’s dexterous hand achieves precise coordination across vision, language, and action modalities—executing human-like movements such as flipping, grasping, and organizing tiles with millimeter-level accuracy. · Human-Robot Interaction and Cognitive Decision-Making: The robot must understand Mahjong rules, interpret evolving game states, and dynamically generate strategies for discarding, melds (Pung/Kong), and reactive play—completing a full pipeline from rule interpretation to real-time reasoning and execution. · Reinforcement Learning–Enhanced Long-Horizon Execution: Validated in the Mahjong scenario, Psi R1 maintains a 30-minute+ Chain of Action Thought (CoAT)—breaking traditional limits of robotic task duration and reasoning continuity in...