iCub
Child-sized open research humanoid developed from the EU RobotCub project (started 2004) and built by IIT for embodied-AI and cognition research labs worldwide.
Machines, companies, technologies, industries, applications, components, people, research, rules, glossary terms and attributed news, ranked in one list.
72 results for “embodied AI research”
Also matched: humanoid, foundation model, learningChild-sized open research humanoid developed from the EU RobotCub project (started 2004) and built by IIT for embodied-AI and cognition research labs worldwide.
An open-source wheeled humanoid with two 7-DOF arms on an omnidirectional base, aimed at manipulation and embodied-AI research.
A lightweight single-arm mobile manipulator with a telescoping arm on a lift, released in 2024 for research and assistive robotics; succeeded by Stretch 4.
A dual-arm humanoid upper body on an omnidirectional wheeled base, revealed by Shenzhen's Astribot (Stardust Intelligence) in April 2024. It is designed for fast…
A smaller wheeled dual-arm platform in Galaxea's R1 series with 6-DOF arms and a 3-DOF torso, listed by the maker as a general mobile manipulation platform within its…
A 1.7 m wheeled dual-arm humanoid from Galaxea Dynamics with 7-DOF arms, a 4-DOF torso and an omnidirectional chassis. It is sold as a mobile manipulation and real-robot…
Unitree's full-size bipedal humanoid, about 1.8 m tall and 47 kg, built around high-torque leg joints; the later H1-2 variant is heavier, adds arm and leg joints (27 DOF…
arXiv:2604.26509v5 Announce Type: replace Abstract: Embodied AI and robotic systems increasingly depend on scalable, diverse, and physically grounded 3D content for…
arXiv:2610.33745v1 Announce Type: new Abstract: Embodied perception requires positional representations that capture both physical geometry and the spatial and temporal…
Configurable bipedal humanoid platform from PAL Robotics for locomotion and reinforcement-learning research, offered with 4-, 5- or 7-DoF arms and ROS 2 software.
arXiv:2610.33317v1 Announce Type: new Abstract: Deploying humanoid task policies requires reliable runtime monitors that anticipate unrecoverable falls in time to…
arXiv:2610.32277v1 Announce Type: new Abstract: Learned humanoid controllers are usually trained in one simulator and then checked in a second one before they go near…
arXiv:2611.08577v1 Announce Type: new Abstract: We present Meituan-Robotics-0 (MR0), a vision-language-action foundation model and embodied-agent system for…
arXiv:2610.31762v1 Announce Type: new Abstract: What visual representation should a navigation policy act on? Navigation policies built on vision foundation models…
arXiv:2611.08857v1 Announce Type: new Abstract: Learning locomotion directly on a humanoid robot is a promising direction to avoid the sim-to-real gap. However…
arXiv:2611.09041v1 Announce Type: new Abstract: Language-guided embodied person tracking requires a mobile agent to identify a target from a referring description and…
Wheeled dual-arm humanoid from Suzhou-based UniX AI with a lifting torso and 8-DoF arms ending in two-finger grippers. The company says it delivers about 100 units a…
Unitree's compact bipedal humanoid, about 1.32 m tall and 35 kg, sold in a base version and an EDU version that adds dexterous hands, extra waist/wrist joints and…
Leju's full-size bipedal humanoid offered as a research and service platform, available in 22-, 30- and 40-DOF configurations. Leju's spec sheet lists hot-swappable…
A soft upper-body humanoid from Toyota Research Institute for research on carrying large objects with its arms and chest as well as its hands. Soft tactile covers go…
arXiv:2611.19616v1 Announce Type: new Abstract: Reinforcement learning (RL) enables robots to acquire complex skills, but standard RL formulations do not guarantee that…
A lower-body bipedal platform from EngineAI for research and education, released in July 2024 with open-source software access. It has 12 degrees of freedom (six per…
arXiv:2611.05738v1 Announce Type: new Abstract: Olfaction provides critical information about airborne chemical cues, yet it remains largely underexplored in embodied…
arXiv:2611.19131v1 Announce Type: new Abstract: Vision-language-action (VLA) models enable embodied artificial intelligence (AI) by translating visual observations and…
arXiv:2611.09124v1 Announce Type: new Abstract: Foundation models increasingly guide robot actions, yet sustained autonomy requires efficient control and failure…
Full-size bipedal humanoid from the Beijing Humanoid Robot Innovation Center, offered in LITE, PLUS and PRO configurations. The maker describes hot-swappable batteries…
Fourier's first-generation full-size bipedal humanoid, shown at the 2023 World Artificial Intelligence Conference in Shanghai. Its developer documentation lists up to 44…
A small 3D-printed, servo-driven open-source humanoid for sim-to-real and reinforcement-learning experiments, with a published bill of materials starting around $350…
arXiv:2610.41320v1 Announce Type: new Abstract: Recent multimodal foundation models exhibit strong perception, reasoning, and in-context learning capabilities, but…
arXiv:2610.33508v1 Announce Type: new Abstract: Humanoid motion trackers reproduce diverse behaviors, but sharing a policy across bodies requires accounting for…
arXiv:2611.23916v1 Announce Type: new Abstract: Humanoid robots must recover from falls and resume commanded motion to sustain locomotion. Learning these behaviors in…
arXiv:2611.18003v1 Announce Type: new Abstract: Reinforcement learning has enabled robust humanoid locomotion, yet training recipes (rewards, architectures…
arXiv:2611.08698v1 Announce Type: new Abstract: Recent advances in robot foundation models have highlighted the potential of in-context learning (ICL) for adapting robot…
arXiv:2611.05979v1 Announce Type: new Abstract: Manipulating diverse objects with multi-fingered dexterous hands is challenging due to the high dimensionality and…
arXiv:2611.18982v1 Announce Type: new Abstract: This paper argues that the robotics and AI community should adopt disclosure standards for demonstration videos. As…
arXiv:2611.19138v1 Announce Type: new Abstract: Autonomous driving is turning to vision-language-action models (VLAs). They answer and plan by decoding, one step at a…
arXiv:2610.36011v1 Announce Type: new Abstract: World-action models (WAMs) offer a promising framework for embodied intelligence, yet mainstream approaches remain…
arXiv:2610.40748v1 Announce Type: new Abstract: Achieving the broad task generalization of embodied models in physical environments remains a central challenge in robot…
arXiv:2611.23930v1 Announce Type: new Abstract: Unmanned Aerial Vehicles (UAVs) are expected to achieve semantic reasoning, intelligent decision-making, and long-horizon…
arXiv:2610.40922v1 Announce Type: new Abstract: End-to-end policies, from task-specific controllers to robot foundation models, learn complex behavior from raw…
arXiv:2611.17730v1 Announce Type: new Abstract: Depth and 3D foundation models can predict geometry from RGB images, allowing zero-shot object navigation without a depth…
arXiv:2610.31779v1 Announce Type: new Abstract: The life-cycle of robotics foundation models crucially depends on data labels. Outcome reward labels are needed for…
arXiv:2610.36507v1 Announce Type: new Abstract: Humanoid behavior foundation models (BFMs) provide reusable whole-body motion priors: given a kinematic reference, they…
arXiv:2611.05567v1 Announce Type: new Abstract: Despite growing interest in foundation models for robotic manipulation, systematic evaluation of their capabilities…
arXiv:2611.19081v1 Announce Type: new Abstract: Integrating MLLM-based agents with robotic foundation models has attracted increasing attention as a means of enhancing…
arXiv:2611.06308v1 Announce Type: new Abstract: Feed-forward geometric foundation models enable dense monocular reconstruction without requiring camera calibration, but…
arXiv:2611.25251v1 Announce Type: new Abstract: Reinforcement learning (RL) can improve vision-language-action (VLA) policies beyond imitation, but humanoid exploration…
This White Paper gives robotics researchers and engineers an overview of a new large-scale motion capture dataset built to close the data gap limiting humanoid robot…
Embodied AI developer (千寻智能) building general-purpose robot models such as Spirit v1.5 and the Moz wheeled humanoids, with offices in Hangzhou, Beijing and Shenzhen.
Embodied AI studies intelligent agents that perceive and act through a body in a physical or simulated environment.
The work applies diffusion models to generate robot action sequences from observations.
Sanctuary AI develops the Phoenix general-purpose robot and associated control software.
Modular bipedal humanoid being developed by Houston-based Persona AI for heavy-industry trades such as shipyard welding, fabrication and inspection. No numeric…
Franka Research 3 is a 7-DoF torque-sensing robot arm aimed at research labs, offering 1 kHz low-level control and integration with ROS 2 and MATLAB.
The paper presents a mobile bimanual teleoperation system and imitation-learning experiments for household-style tasks.
The work studies closed-loop grasping learned from a large collection of robot interaction data.
A study of 96 drone flights found that pretrained AI models were the best at flagging unreliable location data, using only a drone’s motion data rather than its GPS…
The project aggregates robot demonstration data across institutions and studies models trained across different robot embodiments.
Houston humanoid robotics startup founded in 2024 by robotics veterans including Nauticus Robotics founder Nic Radford (CEO, 15 years at NASA) and former Figure AI CTO…
Pony.ai's seventh-generation robotaxi system is a production-oriented Level 4 platform adapted to multiple passenger vehicles from GAC, BAIC and Toyota.