RoboSignal Weekly · 2026-W41
ROBOSIGNAL
Could Sports Be the Cheapest Scenario for Robotics Industry to Implement?
本周 20 developments，最受关注的是：Could Sports Be the Cheapest Scenario for Robotics Industry to Implement?；Global First! Hangzhou's Embodied Robot Rivals Figure, Demonstrates Full-Body Autonomous Clothing Folding；Sharpa Releases Three New Haptic Perception Robots, Lowering the Entry Barrier for General Humanoid Robots。
Research
Global First! Hangzhou's Embodied Robot Rivals Figure, Demonstrates Full-Body Autonomous Clothing Folding
The article describes how the WR1 robot, developed by West Lake Robotics, successfully performs complex household tasks such as folding clothes and managing multi-scene operations. It highlights the use of a dual pre-training system, world models, and a general-purpose action execution model to achieve seamless coordination between perception, planning, and execution. The robot's ability to handle flexible objects and maintain task continuity across different environments is emphasized as a significant breakthrough in embodied AI.
Robotics & Automation News10-09Kingston University Chosen to Lead UK’s First Waste and Recycling Robotics Hub
Kingston University has been selected to lead the UK’s first dedicated waste and recycling robotics adoption hub, NORAH, as part of a £40 million government initiative. The hub will test and validate robotic systems on real waste streams, focusing on materials like textiles and mixed recyclables, to improve recovery rates and reduce landfill use. It will also provide training, economic modeling, and deployment support to accelerate automation in the waste sector.
Guidelines for Building an Embodied Intelligence Lab at the University: From Hardware Selection to Data Closed-Loop
This guide addresses the challenges of building a functional embodied intelligence lab in academia, emphasizing the importance of data pipelines over hardware procurement. It covers hardware selection, sensor configuration, data collection, simulation platforms, and software architecture, offering practical advice for avoiding common pitfalls in lab setup and operation.
arXiv Robotics — research abstracts10-09SDPAD: A Fully Spike-Driven Pipeline for End-to-End Autonomous Driving
This paper introduces SDPAD, a fully spike-driven end-to-end planning pipeline for autonomous driving. It converts pre-trained ANN perception stacks into integer-spike form, lifts multi-view images into BEV space using Spike-3D-Lift, and plans through Spike-QFormer, a spiking query transformer. SDPAD achieves high accuracy and low energy consumption, outperforming previous SNN planners and matching mainstream ANN planners in energy efficiency.
arXiv Robotics — research abstracts10-09NavGPT-3: Harnessing Context in a Hierarchical Navigation Runtime
NavGPT-3 is a new system that connects language models with action policies for autonomous navigation. It uses a hierarchical runtime architecture to enable reasoning, acting, and monitoring in parallel, with the action policy trained on 19.28M examples. The system achieves state-of-the-art results on R2R-CE and matches human performance on RxR-CE, demonstrating the potential of integrating language models with physical control.
Embodied Intelligent Robot 'Runs' Forward
Liaoning has seen significant advancements in embodied intelligent robotics, with new products like the 'Songyi' robot from Sinomach and 'Quantum No. 1' from Jinzhibianliang. These robots are designed for industrial tasks such as logistics and automation, supported by policy initiatives and industry collaborations. The region is also building a robust ecosystem for embodied AI, including data infrastructure and innovation alliances.
Hand-Eye-Brain Coordination: A Full Guide to Industrial and Service Robot Integration
This article explains the 'hand-eye-brain' coordination framework for industrial and service robots, detailing the roles of perception, decision-making, and execution. It covers challenges like sensor calibration, force control, and system synchronization, and offers practical advice on simulation, testing, and deployment in real-world scenarios.
How Can Optimus Generate Revenue Without Any Customers?
The article examines Tesla's production and financial strategy for Optimus, noting that while manufacturing capacity has improved, the absence of external customers means each robot is treated as a capital expenditure rather than revenue. It contrasts Tesla's internal deployment model with Chinese companies that generate revenue through sales, highlighting the challenges of achieving profitability in the humanoid robotics market.
Rigidcore Tactile+EMF Professional Data Acquisition Gloves: Breakthrough in Embodied Intelligence Data Collection
Moxian Technology's Rigidcore Tactile+EMF professional data acquisition gloves overcome issues of insufficient accuracy, signal noise, and dynamic capture in data collection through technical breakthroughs such as nearly 1,000 tactile points, 0.1N force sensitivity, and 120Hz sampling rate. These gloves not only enhance the quality of tactile data but also reduce the workload of post-processing data through optimized hardware design, making them an essential infrastructure for embodied intelligence training.
MIT — RoboticsFirst-party10-07Planning system ensures a robot’s flight path will remain collision-free
MIT researchers have developed a new autonomous navigation system called SANDO that guarantees collision-free flight for UAVs in dynamic, unknown environments. The system uses a time-sensitive safety corridor and mathematical proofs to ensure safety, even when obstacles are moving unpredictably. SANDO has been tested in simulations and real-world flights, successfully avoiding collisions in all scenarios.
Daimon Robotics Launches Global First Tactile-Grounded World Model Daimon-TWM
Daimon Robotics has launched Daimon-TWM, the first global tactile-grounded world model, which integrates tactile perception into perception, decision-making, and action generation. The model is based on the largest tactile multimodal physical world dataset, Daimon-Infinity, and demonstrates significant improvements in physical interaction tasks. The company has also built a global tactile data collection network and established industry benchmarks for physical interaction capabilities.
Robotics & Automation News10-05amsight leads ESA project to speed qualification of 3D-printed space components
amsight has been selected to lead the ESA DIQAM project, which seeks to accelerate the qualification of 3D-printed space components through a digital qualification framework. The project aims to make the qualification process faster, more data-driven, and reusable across future builds. It involves developing a Digital Part Qualification File and a software prototype for automated data ingestion and statistical evaluation. The framework will be validated using two industrial demonstrators, including an ArianeGroup Phase Change Material container and an ISPTech 4U propellant tank.
Embodied-AI-Guide: A Comprehensive Tutorial for Embodied Intelligence
The Embodied-AI-Guide is a detailed tutorial and resource hub for understanding and practicing embodied intelligence. It covers foundational concepts, practical implementation with RoboTwin 2.0, and insights into the field's research and development. The guide is structured to help users build a solid understanding of the domain, from data collection to algorithmic design and evaluation, with a focus on real-world deployment and simulation-based learning.
IROS 2026 Field Observations: Long-Term Tasks, Failure Recovery, World Models
The IROS 2026 conference highlights a shift towards long-term tasks, failure recovery, and world modeling in robotics. The event showcases advancements in perception, planning, and control, with a focus on real-world applications and standardized testing. The integration of tactile and force feedback, along with data collection tools, reflects a growing emphasis on embodied intelligence and simulation-to-reality transitions.
From Data Factory to Training Hub: Can Simulation Platforms Bring a Paradigm Shift to Embodied Intelligence?
The article explores the evolution of embodied intelligence from data collection to training infrastructure, emphasizing the need for simulation platforms that enable continuous learning and iteration. It discusses the limitations of raw data and the importance of creating a closed-loop system for model training and real-world deployment, with a focus on physical simulation and the integration of real-world feedback.
Humanoid Robot Dynamic Balance Control: Five Core Challenges and Solutions
This article explores the fundamental challenges in dynamic balance control for humanoid robots, including the physical constraints of motion, the limitations of ZMP theory, joint coupling compensation, delay-sensitive feedback, and real-time multi-body dynamics solving. It provides practical insights and solutions for developers, highlighting the importance of hardware-software integration and real-world testing.
Robots & Hardware
Sharpa Releases Three New Haptic Perception Robots, Lowering the Entry Barrier for General Humanoid Robots
D01 features high-precision haptic perception and human-robot coexistence capabilities, W02 achieves full-hand haptic sensing and lightweight design, and AE01 provides high-fidelity haptic feedback and remote operation data collection. These three products together form a hardware infrastructure for real-world applications, aiming to reduce the deployment threshold for general humanoid robots in complex scenarios.
Deployments
Could Sports Be the Cheapest Scenario for Robotics Industry to Implement?
In 2026, the 'iPhone moment' for the robotics industry appeared in sports events. Multiple cities held events such as humanoid robot half-marathons, fighting leagues, and sports meets, where robots demonstrated their athletic capabilities and gained widespread exposure. The article points out that cultural, sports, and tourism scenarios have become an important path for the robotics industry to implement its technologies, not only meeting the needs of enterprises for demonstration and promotion, but also providing new ways to attract tourists for cities.
List of Representative Domestic Humanoid Robot Enterprises: A 2026 Overview of the Embodied Intelligence Industrialization Landscape
The article outlines the current state of the domestic humanoid robot industry in 2026, detailing the growth and maturity of the sector. It categorizes key players into four groups: listed companies, established manufacturers transitioning into the field, new startups, and cross-industry giants. The text highlights the role of policy, capital, and market demand in driving the industry's expansion and the formation of a competitive ecosystem.
IT Home — Robotics10-04Hyundai Plans to Deploy 25,000 Boston Dynamics Atlas Robots and Build a U.S. Factory with Annual Capacity of 30,000 Units
Boston Dynamics and Hyundai Motor Group are collaborating to establish a robotics application center in Georgia, U.S., for testing and training Atlas robots. Hyundai plans to deploy 25,000 Atlas robots globally in the coming years and build a U.S. factory with an annual production capacity of 30,000 units. The Atlas robot has 56 degrees of freedom, a maximum lifting capacity of 50 kg, and a battery life of approximately 4 hours.