Embodied perception

Guidelines for Building Embodied Intelligence Labs in Colleges: From Hardware Selection to Data Closed-Loop

This article thoroughly explains the key points for establishing an embodied intelligence lab in colleges, covering hardware selection, data systems, computing architecture, software frameworks, acceptance standards, and common pitfalls. The article highlights the importance of data closed-loop systems, stating that the core of lab construction lies in establishing a complete process for data collection, annotation, training, simulation, and deployment. Additionally, the article offers specific recommendations such as hardware configuration ratios, sensor selection, site design, data management platforms, simulation platform selection, computing power planning, software architecture unification, and the combination of open-source toolchains, aiming to help college teams efficiently build labs and avoid common mistakes.

Embodied Intelligence Technology Architecture and Learning Path: From Large Models to Robot Deployment Practice

This article revolves around the content of the 2027 Huaqianqian Embodied Intelligence New Product Launch Conference, systematically analyzing the technical architecture, learning path, and application scenarios of embodied intelligence. Starting from the three-layer architecture of perception-decision-execution, the article explores the role of large models in embodied intelligence, and through practical project experience, it analyzes key challenges such as the difficulty of transferring from simulation to real-world deployment, model inference latency optimization, and sensor calibration, providing developers with a complete learning path from beginner to advanced level and a guide to avoid common pitfalls.

CoRL 2026｜Making Robots More Agile: Starting with Learning to Walk

This paper presents LeaP, a learnable source prior for generative robot policies, which replaces fixed standard Gaussian distributions with state-dependent random initialization. LeaP jointly learns the mean and variance of an initial Gaussian distribution, improving action generation in robotic tasks. The method achieves an average success rate of 81.6% in simulation and 80.0% on real robotic arms, outperforming existing baselines like A2A and VITA. The paper is accepted at CoRL 2026, and the code is open-sourced.

Motors Don't Need Upgrades, Robots Can Run Faster! Beihang University Science Subjournal Reveals New Logic for Quadruped Locomotion

Professor Shi Qing's team from Beijing Institute of Technology was inspired by the high-speed running mechanism of the elephant shrew. They designed a micro quadruped robot named FLEXOR equipped with a dual-joint coupled spine. Through dynamic spine-leg coordination, the robot achieved a 31.6% increase in speed and a 32.2% reduction in energy consumption without upgrading its motors. The study reveals the critical role of the timing coordination between the spine and legs in locomotion performance and verifies the universality of this mechanism across different robot morphologies, providing new insights for highly mobile embodied intelligent robots.

GPT-6 Astra Connects to Unitree G1, Cleans the Kitchen!

The Stanford team's HomeBody project demonstrates how GPT-6 Astra controls the Unitree G1 robot to complete kitchen cleaning tasks through a three-step process: spatial exploration, digital twin simulation, and task execution. The system uses pre-trained models and a skill library to perform complex operations in new environments without additional training.

Deployment Year Begins: Zhixuan Deploys 100 Robots in Retail Stores

Zhixuan Robotics has deployed 100 units of the Lingxi X2 humanoid robot in 100 retail stores of Aishida, achieving a 39% increase in store sales. The robots, named 'Aibao,' engage customers by understanding their cooking needs and guiding them toward suitable products, while also seamlessly transferring conversations to human staff when necessary. This marks a milestone in the deployment of embodied AI in real-world retail environments.

The 'War' of Dexterous Hands: 8 Embodied Companies Show Off Their Skills

This article explores the complexity of dexterous hands in real-world tasks, pointing out that evaluation criteria have shifted from single parameters to overall operational capabilities. Eight companies analyze, from standards, hardware, perception, data, models to commercialization, how to achieve the reliability and practicality of dexterous hands. The article emphasizes the integration of vision and tactile sensing, the importance of data loops, and the challenges between model training and real-world deployment.

Robotics Roadmaps from Around the World: Spotlight of the Month - China

China is pursuing a strategic roadmap through its Five-Year Plans to dominate the global robotics industry, focusing on embodied AI and humanoid robotics. The 13th and 14th FYPs laid the foundation for industrial automation, while the 15th FYP emphasizes embodied intelligence, with state support for R&D and mass deployment of humanoids. Despite achievements in market share and production scale, challenges remain in precision hardware and semiconductor self-sufficiency, with risks of overcapacity and market volatility.

Robotic lab sets up and runs optics experiments on demand

MIT researchers have developed a reconfigurable robotic lab that autonomously assembles, tunes, and dismantles optical experiments. The system uses robotic arms, 3D-printed component housings, and a cloud-based interface to enable remote operation. It can build and fine-tune a laser cavity in under 30 minutes, demonstrating the potential for fully automated optical experiments.

Skeleton-guided geometry-aware auto-labeling for robotic grasping: From 4-DoF learning to 6-DoF execution

This research introduces a novel algorithm for generating grasp keypoints using straight skeletons to identify high-potential regions for stable grasping. A fully automated pipeline enables large-scale annotation without human intervention, and a new architecture, SkelGG-CNN, is introduced for 4-DoF grasping. The method is extended to 6-DoF grasping using a generalized quasi-3D skeletonization algorithm, achieving high accuracy on multiple benchmarks and real-world experiments. The framework enables efficient training of lightweight models for real-world deployment.

Robots Are Learning to Feel

This article explores how tactile data is helping robots improve their dexterous manipulation skills. Researchers are creating large tactile datasets and models that can use tactile feedback to enhance robot performance in tasks like folding laundry or turning keys. Challenges include the difficulty of integrating tactile data with vision-based models and the need for more diverse and scalable datasets to achieve significant improvements in robot dexterity.

Unitree@UnitreeRoboticsSignalEditorial score6363

Unitree has fully open-sourced its UnifoLM-WLA-1.0 embodied foundation model, achieving new state-of-the-art results across multiple benchmarks. The model supports cross-task and cross-end-effector generalization, enabling whole-body coordination for both desktop and mobile manipulation.

This Robot Will Draw Your Blood Now

Aletta, the first autonomous blood-draw device approved for use in the U.S., uses imaging and robotics to perform blood draws with high success rates, even in challenging cases. While it addresses staffing shortages in clinical labs, concerns about skin tone bias and sample quality persist, requiring further validation.

Cyborg Roaches Can Stab You With Needles

Researchers at the University of Queensland have developed 'Paraborgs'—cyborg cockroaches equipped with needles and cameras to assist in search-and-rescue missions. These insects, grafted with electronic interfaces, can navigate rubble, deliver drugs, and operate in teams. The study addresses challenges in autonomy, communication, and human interaction with the technology.

Researchers tune into Arctic under-ice sounds and test through-ice communication

Researchers from MIT Lincoln Laboratory deployed sensors in the Arctic to monitor under-ice sounds and test through-ice communication using a magnetic modem. The study addresses challenges in extreme weather and highlights the importance of community collaboration and sensor deployment strategies for Arctic research.

Introducing S1: In-Context Learning for Robotics

Skild AI introduces S1, a robotic foundation model that leverages in-context learning to execute complex, long-horizon tasks without post-training. This marks a significant shift from traditional fine-tuning approaches, enabling rapid deployment and reducing data requirements. The model demonstrates strong performance on unseen tasks, including plant potting, pancake cooking, and kit assembly, and shows robustness to perturbations and common-sense reasoning.

Gemini Robotics 2 brings whole body intelligence to robots

Google DeepMind has released Gemini Robotics 2, a new model that enables robots to perform complex tasks with whole-body intelligence, advanced dexterity, and multi-robot collaboration. The model supports real-time reasoning, on-device adaptation, and safety features for human-robot interaction.

F.03 Arrives at BMW

Figure's latest generation robot, F.03, has arrived at BMW Group Plant Spartanburg, demonstrating advanced dynamic whole-body control and sequencing use cases. Powered by Helix 02, the robot performs complex material manipulation tasks that require both precision and force, marking progress in embodied AI for manufacturing.

Firefly Aerospace Operates NVIDIA Jetson in Lunar Orbit for the First Time

Firefly Aerospace's Blue Ghost Mission 2 will deploy NVIDIA Jetson for on-orbit AI processing, enabling real-time lunar data analysis and reducing latency. This marks the first use of Jetson in lunar orbit, supporting scientific research and future lunar exploration.

Helix-02 Bedroom Tidy

Figure AI demonstrates Helix-02 humanoids performing a bedroom reset in under two minutes using a single learned Vision-Language-Action policy. The robots coordinate without shared planners or message passing, inferring each other's intent from motion alone. Tasks include opening doors, pushing furniture, draping clothing, and making a bed, showcasing integration of locomotion, dexterity, and sensing.