Tootfinder

Figure AI's former head of product safety sues the humanoid robot startup, alleging he was unlawfully terminated after warning executives about product safety (Lora Kolodny/CNBC)
https://www.cnbc.com/2025/11/21/figure-ai-sued.html

Figure AI sued by whistleblower who warned that startup's robots could 'fracture a human skull'
A former engineer for Figure AI filed a lawsuit against the company, claiming he was unlawfully terminated after warning executives about product safety.

Our #starwars #Lego Advent calendar brings another droid. ❤️

Documents: Rhoda AI, which raised a $162.6M Series A in April, and Genesis AI, which raised a $105M seed earlier this year, have been developing humanoid robots (Anna Tong/Forbes)
http://www.forbes.com/sites/annatong/2025

Startups Rhoda AI And Genesis AI Are Building Humanoid Robots In Stealth
Flush with hundreds of millions of dollars in new funding, Rhoda AI and Genesis AI are developing humanoids they hope can go head-to-head with robots from Figure AI and Tesla.

Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation
Zhenyu Zhao, Hongyi Jing, Xiawei Liu, Jiageng Mao, Abha Jha, Hanwen Yang, Rong Xue, Sergey Zakharor, Vitor Guizilini, Yue Wang
https://arxiv.org/abs/2510.08807

Humanoid Everyday: A Comprehensive Robotic Dataset for Open-World Humanoid Manipulation
From loco-motion to dextrous manipulation, humanoid robots have made remarkable strides in demonstrating complex full-body capabilities. However, the majority of current robot learning datasets and benchmarks mainly focus on stationary robot arms, and the few existing humanoid datasets are either confined to fixed environments or limited in task diversity, often lacking human-humanoid interaction and lower-body locomotion. Moreover, there are a few standardized evaluation platforms for benchmar…

Une autre bulle spéculative : les robots humanoïdes
https://futurism.com/robots-and-machines/china-officially-scared-robots-bubble

After years of patient investment, China is on the cusp of a robotics revolution.

If embodied intelligence
— think AI-powered robots that can navigate the real world
— is the next frontier of AI, then China appears poised to dominate.
Though the United States still has distinct advantages in software, advanced AI chips and foundational research, China leads in robot hardware, deployment and policy support.

Last year, China installed nearly 300,000 robots in its fact…

The Chinese robots are coming
China is miles ahead in the race to dominate a technology that could define the 21st century.

Towards Proprioception-Aware Embodied Planning for Dual-Arm Humanoid Robots
Boyu Li, Siyuan He, Hang Xu, Haoqi Yuan, Yu Zang, Liwei Hu, Junpeng Yue, Zhenxiong Jiang, Pengbo Hu, B\"orje F. Karlsson, Yehui Tang, Zongqing Lu
https://arxiv.org/abs/2510.07882

Towards Proprioception-Aware Embodied Planning for Dual-Arm Humanoid Robots
In recent years, Multimodal Large Language Models (MLLMs) have demonstrated the ability to serve as high-level planners, enabling robots to follow complex human instructions. However, their effectiveness, especially in long-horizon tasks involving dual-arm humanoid robots, remains limited. This limitation arises from two main challenges: (i) the absence of simulation platforms that systematically support task evaluation and data collection for humanoid robots, and (ii) the insufficient embodime…

A look at data labeling startups like Objectways, whose workers record and annotate repetitive tasks like folding towels to train AI robots for physical tasks (Nilesh Christopher/Los Angeles Times)
https://www.latimes.com/business/story/202…

Inside the race to train AI robots how to act human in the real world
Humanoid robot training is booming around the world. Tech companies are rushing to build the robots for a market projected to reach $38 billion within the next decade.

Humanoid robots, being just around the corner for every household to have one since…
*checks notes*
…1868.
https://en.wikipedia.org/wiki/Zadoc_Dederick

Garbage. Ppl pay for this?
My prompt was `Edward Hopper's American Gothic but with two robots` and it didn't even include a pitchfork.
#microsoft

PolygMap: A Perceptive Locomotion Framework for Humanoid Robot Stair Climbing
Bingquan Li, Ning Wang, Tianwei Zhang, Zhicheng He, Yucong Wu
https://arxiv.org/abs/2510.12346 http…

PolygMap: A Perceptive Locomotion Framework for Humanoid Robot Stair Climbing
Recently, biped robot walking technology has been significantly developed, mainly in the context of a bland walking scheme. To emulate human walking, robots need to step on the positions they see in unknown spaces accurately. In this paper, we present PolyMap, a perception-based locomotion planning framework for humanoid robots to climb stairs. Our core idea is to build a real-time polygonal staircase plane semantic map, followed by a footstep planar using these polygonal plane segments. These …

In the #China Pavilion at the Osaka #Expo, robots dance and #AI sings. But on closer look, these companies on display are the same ones sanctioned by the US for trade, human rights, and geopolitical reasons.

gonna get one of those humanoid robots that's powered by some dude with an Xbox controller for the sole purpose of kicking my door down in the morning and placing a Vyvanse directly into my mouth

Andrew Bosworth says humanoid robots, internally called "Metabot", are Meta's next "AR size bet" and envisions licensing software to other robot makers (Alex Heath/The Verge)
https://www.theverge.com/column/786759/humanoid-robots-meta

Humanoid robots are Meta’s next ‘AR-size bet’
During a recent trip to Meta HQ, I took the opportunity to ask CTO Andrew Bosworth about its new robotics effort.

While China’s older tech pioneers tend to idolize Silicon Valley,
younger founders find their role models in people such as
DeepSeek’s Liang Wenfeng and
Unitree’s Wang Xingxing
— both of whom studied exclusively at Chinese universities and are known to predominantly hire domestic talent.

A December analysis from Citi GPS projected that the world would be populated by 648 million humanlike bots by 2050,
unlocking an enduring production advantage and immen…

The Chinese robots are coming
China is miles ahead in the race to dominate a technology that could define the 21st century.

🦾 Humans sense a collaborating robot as part of their 'extended' body
#robots

Humans sense a collaborating robot as part of their 'extended' body
Researchers from the Istituto Italiano di Tecnologia (IIT) in Genoa (Italy) and Brown University in Providence (U.S.) have discovered that people sense the hand of a humanoid robot as part of their body schema, particularly when it comes to carrying out a task together, like slicing a bar of soap.

Ego-Vision World Model for Humanoid Contact Planning
Hang Liu, Yuman Gao, Sangli Teng, Yufeng Chi, Yakun Sophia Shao, Zhongyu Li, Maani Ghaffari, Koushil Sreenath
https://arxiv.org/abs/2510.11682

Ego-Vision World Model for Humanoid Contact Planning
Enabling humanoid robots to exploit physical contact, rather than simply avoid collisions, is crucial for autonomy in unstructured environments. Traditional optimization-based planners struggle with contact complexity, while on-policy reinforcement learning (RL) is sample-inefficient and has limited multi-task ability. We propose a framework combining a learned world model with sampling-based Model Predictive Control (MPC), trained on a demonstration-free offline dataset to predict future outco…

An in-depth look at the humanoid robotics industry, which currently relies heavily on hype to rally interest and investors, as AI fuels the humanoid boom (James Vincent/Harper's)
https://harpers.org/archive/2025/12/kicking-robots-james-vincent-humanoids/

Kicking Robots, by James Vincent
Humanoids and the tech-­industry hype machine

Embracing Evolution: A Call for Body-Control Co-Design in Embodied Humanoid Robot
Guiliang Liu, Bo Yue, Yi Jin Kim, Kui Jia
https://arxiv.org/abs/2510.03081 https://

Embracing Evolution: A Call for Body-Control Co-Design in Embodied Humanoid Robot
Humanoid robots, as general-purpose physical agents, must integrate both intelligent control and adaptive morphology to operate effectively in diverse real-world environments. While recent research has focused primarily on optimizing control policies for fixed robot structures, this position paper argues for evolving both control strategies and humanoid robots' physical structure under a co-design mechanism. Inspired by biological evolution, this approach enables robots to iteratively adapt bot…

Flexion, which is building a full autonomy stack for humanoid robots, raised a $50M Series A from DST Global Partners, NVentures, and others, after a $7M seed (Mary Ann Azevedo/Crunchbase News)
https://news.crunchbase.com/venture/robotic-brain-building-star…

Exclusive: Founded By Ex-Nvidia Researchers, Flexion Lands $50M To Build The 'Brain' for Humanoid Robots
A startup founded by former Nvidia researchers that’s “building the brain for humanoid and human-capable robots,” Flexion has raised $50 million in funding, it tells Crunchbase News exclusively.

Sources: Tesla abandoned Elon Musk's goal to make thousands of Optimus robots in 2025 due to significant technical challenges, especially with the robots' hands (Theo Wayt/The Information)
https://www.theinformation.com/articles/el…

As Elon Musk Preps Tesla’s Optimus for Prime Time, Big Hurdles Remain
When Elon Musk takes the stage at Tesla’s annual meeting next month, one of the centerpieces of his plan to impress shareholders will be a dancing troupe of Optimus bots, the humanoid machines that he says will eventually eclipse Tesla’s electric vehicle business, which is suffering from ...

Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking
Joao Pedro Araujo, Yanjie Ze, Pei Xu, Jiajun Wu, C. Karen Liu
https://arxiv.org/abs/2510.02252 https…

Retargeting Matters: General Motion Retargeting for Humanoid Motion Tracking
Humanoid motion tracking policies are central to building teleoperation pipelines and hierarchical controllers, yet they face a fundamental challenge: the embodiment gap between humans and humanoid robots. Current approaches address this gap by retargeting human motion data to humanoid embodiments and then training reinforcement learning (RL) policies to imitate these reference trajectories. However, artifacts introduced during retargeting, such as foot sliding, self-penetration, and physically…

Foxconn says it plans to deploy Nvidia's Isaac GR00T N model of humanoid robots at its factory in Houston, Texas, which produces AI servers for Nvidia (Wen-Yee Lee/Reuters)
https://www.reuters.com/business/foxconn-deploy-humanoid-robots…

Q&A with iRobot founder Rodney Brooks on his startup Robust.AI, which builds warehouse robots, unrealistic expectations around humanoid robots and AI, and more (Om Malik/Crazy Stupid Tech)
https://crazystupidtech.com/2025/09/29/irobot-founder-dont…

iRobot Founder: Don’t Believe The (AI & Robotics) Hype!
Rodney Brooks, co-founder of three robotic companies and an AI guru has a pragmatic and honest opinions about the state of AI and Robotics. An interview!

Stability-Aware Retargeting for Humanoid Multi-Contact Teleoperation
Stephen McCrory, Romeo Orsolino, Dhruv Thanki, Luigi Penco, Robert Griffin
https://arxiv.org/abs/2510.04353 …

Stability-Aware Retargeting for Humanoid Multi-Contact Teleoperation
Teleoperation is a powerful method to generate reference motions and enable humanoid robots to perform a broad range of tasks. However, teleoperation becomes challenging when using hand contacts and non-coplanar surfaces, often leading to motor torque saturation or loss of stability through slipping. We propose a centroidal stability-based retargeting method that dynamically adjusts contact points and posture during teleoperation to enhance stability in these difficult scenarios. Central to our…

Source: SoftBank held talks about acquiring Agility Robotics for $900M before participating in Agility's funding round valuing the startup at $1.75B pre-money (Rocket Drew/The Information)
https://www.theinformation.com/articles/softbank-hunts-humanoid-rob…

SoftBank Hunts for Humanoid Robot Startups
SoftBank’s Masayoshi Son has long predicted a future where robots would outnumber people and take over many jobs from humans. But some of SoftBank’s bets in robotics over the past 10 years, such as robot companion Pepper, have not panned out. Now the company is renewing its robot ambitions— ...

Like Playing a Video Game: Spatial-Temporal Optimization of Foot Trajectories for Controlled Football Kicking in Bipedal Robots
Wanyue Li, Ji Ma, Minghao Lu, Peng Lu
https://arxiv.org/abs/2510.01843

Like Playing a Video Game: Spatial-Temporal Optimization of Foot Trajectories for Controlled Football Kicking in Bipedal Robots
Humanoid robot soccer presents several challenges, particularly in maintaining system stability during aggressive kicking motions while achieving precise ball trajectory control. Current solutions, whether traditional position-based control methods or reinforcement learning (RL) approaches, exhibit significant limitations. Model predictive control (MPC) is a prevalent approach for ordinary quadruped and biped robots. While MPC has demonstrated advantages in legged robots, existing studies often…

DEEP Robotics, a Hangzhou-based startup that builds quadruped and humanoid robots, raised a $70M Series C to expand R&D and production capacity (Danielle Popov/South China Morning Post)
https://www.scmp.com/tech/tech-trends/arti

China’s Deep Robotics raises US$70 million as sector draws more investors
Company founder Zhu Qiuguo says the new funding would be used for research and the recruitment of top robotics talent.

OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction
Lujie Yang, Xiaoyu Huang, Zhen Wu, Angjoo Kanazawa, Pieter Abbeel, Carmelo Sferrazza, C. Karen Liu, Rocky Duan, Guanya Shi
https://arxiv.org/abs/2509.26633

OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction
A dominant paradigm for teaching humanoid robots complex skills is to retarget human motions as kinematic references to train reinforcement learning (RL) policies. However, existing retargeting pipelines often struggle with the significant embodiment gap between humans and robots, producing physically implausible artifacts like foot-skating and penetration. More importantly, common retargeting methods neglect the rich human-object and human-environment interactions essential for expressive loco…

DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos
Jhen Hsieh, Kuan-Hsun Tu, Kuo-Han Hung, Tsung-Wei Ke
https://arxiv.org/abs/2510.08475 https://…

DexMan: Learning Bimanual Dexterous Manipulation from Human and Generated Videos
We present DexMan, an automated framework that converts human visual demonstrations into bimanual dexterous manipulation skills for humanoid robots in simulation. Operating directly on third-person videos of humans manipulating rigid objects, DexMan eliminates the need for camera calibration, depth sensors, scanned 3D object assets, or ground-truth hand and object motion annotations. Unlike prior approaches that consider only simplified floating hands, it directly controls a humanoid robot and …

How building robotic hands that match human dexterity remains a major technical obstacle to deploying humanoid robots in factories and for caregiving jobs (Wall Street Journal)
https://www.wsj.com/tech/the-hands-problem

KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control
Jinrui Han, Weiji Xie, Jiakun Zheng, Jiyuan Shi, Weinan Zhang, Ting Xiao, Chenjia Bai
https://arxiv.org/abs/2509.16638

KungfuBot2: Learning Versatile Motion Skills for Humanoid Whole-Body Control
Learning versatile whole-body skills by tracking various human motions is a fundamental step toward general-purpose humanoid robots. This task is particularly challenging because a single policy must master a broad repertoire of motion skills while ensuring stability over long-horizon sequences. To this end, we present VMS, a unified whole-body controller that enables humanoid robots to learn diverse and dynamic behaviors within a single policy. Our framework integrates a hybrid tracking object…

VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation
Shaofeng Yin, Yanjie Ze, Hong-Xing Yu, C. Karen Liu, Jiajun Wu
https://arxiv.org/abs/2509.20322

VisualMimic: Visual Humanoid Loco-Manipulation via Motion Tracking and Generation
Humanoid loco-manipulation in unstructured environments demands tight integration of egocentric perception and whole-body control. However, existing approaches either depend on external motion capture systems or fail to generalize across diverse tasks. We introduce VisualMimic, a visual sim-to-real framework that unifies egocentric vision with hierarchical whole-body control for humanoid robots. VisualMimic combines a task-agnostic low-level keypoint tracker -- trained from human motion data vi…

iRobot co-founder Rodney Brooks details why humanoid robots won't learn human-level dexterity from current methods, how to make them safe for humans, and more (Rodney Brooks)
https://rodneybrooks.com/why-todays-humanoids-wont-learn-dexterity/

A Framework for Optimal Ankle Design of Humanoid Robots
Guglielmo Cervettini, Roberto Mauceri, Alex Coppola, Fabio Bergonti, Luca Fiorio, Marco Maggiali, Daniele Pucci
https://arxiv.org/abs/2509.16469 …

A Framework for Optimal Ankle Design of Humanoid Robots
The design of the humanoid ankle is critical for safe and efficient ground interaction. Key factors such as mechanical compliance and motor mass distribution have driven the adoption of parallel mechanism architectures. However, selecting the optimal configuration depends on both actuator availability and task requirements. We propose a unified methodology for the design and evaluation of parallel ankle mechanisms. A multi-objective optimization synthesizes the mechanism geometry, the resulting…

RuN: Residual Policy for Natural Humanoid Locomotion
Qingpeng Li, Chengrui Zhu, Yanming Wu, Xin Yuan, Zhen Zhang, Jian Yang, Yong Liu
https://arxiv.org/abs/2509.20696 https://…

RuN: Residual Policy for Natural Humanoid Locomotion
Enabling humanoid robots to achieve natural and dynamic locomotion across a wide range of speeds, including smooth transitions from walking to running, presents a significant challenge. Existing deep reinforcement learning methods typically require the policy to directly track a reference motion, forcing a single policy to simultaneously learn motion imitation, velocity tracking, and stability maintenance. To address this, we introduce RuN, a novel decoupled residual learning framework. RuN dec…