REK's October 9 Deathmatch Features Blade-Equipped Robots
The October 9 Deathmatch by REK will feature humanoid robots in combat, including blade-equipped versions. The main event pits Rektile against T-REK.
Search
Mecka Secures Funding to Enhance Human-Demonstration Data Collection
Mecka has raised funds from Sequoia, Nvidia, and Microsoft’s M12 to enhance its robot deployment and data collection. This funding aims to improve their human-demonstration capabilities.
TacHair: Enhancing Robotic Hair Stroking with Tactile Feedback
The TacHair framework enhances robotic hair stroking by utilizing tactile feedback for better contact maintenance. Trials show significant improvements in success rates and contact retention, demonstrating its effectiveness in handling deformable surfaces.
Study on Dynamic-Point Filters in Visual SLAM Systems
This study explores the role of dynamic-point filters in visual SLAM, revealing their mixed effectiveness in varying texture conditions. The findings challenge existing assumptions about filter performance in low-texture environments.
DR02 Humanoid Robot Tests Traffic Reminders in Hangzhou
The DR02 humanoid robot is being tested in Hangzhou, focusing on traffic reminders and pedestrian interactions. The robot boasts all-weather protection capabilities.
Agility Robotics Announces Launch Details for Digit 5
Agility Robotics has announced the launch of its new humanoid robot, Digit 5, with a projected cost of $150,000. The company plans to produce 1,000 units annually, with general availability expected by late 2027 or early 2028.
Adaptive Spraying Framework Enhances Precision in Robotics Agriculture
This study presents a novel adaptive spraying framework for robotics in agriculture, enhancing precision and efficiency. By integrating environmental data, the system significantly improves crop detection and reduces pesticide drift.
SAFE: A Novel Approach for Real-Time Detection of Slip and Fracture in Robotics
The paper presents SAFE, a new sensing method for detecting slip and fracture in fragile objects during robotic manipulation. It demonstrates high success rates in diverse trials, emphasizing its robustness and adaptability.
Dynamic Graph-Based Models in Robotics: Addressing Real-World Challenges
This article reviews the adaptation of graph-based models in robotics to address dynamic environments. It discusses suitable representations, construction pipelines, and practical applications, while identifying key challenges and trends in the field.
Startup Develops Roger for Hazardous Energy and Public Safety
Minerva-Humanoids is creating a humanoid robot called Roger for hazardous energy and public safety tasks. The CEO highlights the role of human operators in its functionality.
The Importance of Memory in In-Home Assistive Robots
In-home assistive robots can help with cleaning and organizing, but they need better memory to avoid causing problems. Without this enhancement, they may lead to more inconveniences for homeowners.
New Large-Scale Motion Capture Dataset for Humanoid Robot Learning
A new dataset has been created to improve the learning capabilities of humanoid robots by providing extensive motion capture data. This initiative aims to bridge the existing data gap in the field.
MITRE's Future-Warfare Study to Focus on Humanoid Logistics
Johnson will contribute to MITRE's study on future warfare, focusing on humanoid robots for logistics. Project Meridian is led by Elon Musk and Palmer Luckey.
Charm Care to Invest ¥300 Million in Donut Robotics for Nursing Home Trials
Charm Care is set to invest ¥300 million in Donut Robotics to enhance nursing home care. The partnership will trial cinnamon and develop nurse-call support systems.
Meta's Humanoid Robotics Program Expands with New Engineering Role
Meta is expanding its humanoid robotics program with a new engineering role focused on hardware support and improvements. This development sheds light on the company's ongoing efforts in the robotics field.
Advancements in Multi-Agent Robotic Systems for 3D Reach-Avoid Games
This study presents a new method for improving assignment quality in multi-agent robotic systems. The proposed approach shows significant enhancements in capture rates and pursuit efficiency in 3D reach-avoid games.
Unified Motion Planning Framework for High-Dimensional Robotics
This paper presents a novel motion planning framework that integrates equality and inequality constraints for robotic systems. The Riemannian Barrier Metric RRT (RMRRT) method shows significant improvements in planning efficiency and success rates across various tasks.
Enhancing Robustness Testing for DNN-Controlled Robotics Systems
This research presents a novel method for robustness testing in DNN-controlled robotics, achieving a 70% success rate. It emphasizes the need for physical validation despite effective simulation results.
New SANDO Method Enhances Navigation for Disaster-Response Robots
The SANDO method is set to revolutionize how disaster-response robots navigate perilous terrains. By improving their ability to traverse unknown environments, this innovation promises to enhance their effectiveness in emergencies.
Galbot Launches ET1 Humanoid Robot Starting at 79,000 Yuan
Galbot has unveiled the ET1 humanoid robot, starting at 79,000 yuan. Enhanced versions offer more advanced features.
RoboParty Unveils RP1 Humanoid Robot with Balance-Recovery Features
RoboParty has launched the RP1 humanoid robot, demonstrating its balance-recovery abilities at IROS. This new model builds on the ROBOTO ORIGIN platform and aims for expanded releases in the near future.
Panasonic Develops Humanoid Robots for Factories and Warehouses
Panasonic is initiating the development of humanoid robots for industrial use, focusing on factories and warehouses. A new R&D division will lead this effort, highlighting battery safety as a significant benefit.
Introducing GOTT: A New Framework for Multi-Fingered Robot Manipulation
GOTT is a new framework that improves the ability of multi-fingered robots to manipulate objects by establishing reliable contact. It adapts to various tasks and robot designs, showing enhanced success in both simulations and real-world applications.
TACET: A Context-Appropriate Acoustic-Social Navigation Method for Quadruped Robots
The TACET method enhances quadruped robot navigation by reducing noise and respecting social contexts. It achieves significant noise reduction while maintaining personal-space compliance in sensitive environments.
Mirror Particle Develops Human Behavior 'World Model'
Mirror Particle is focused on developing a model that captures human behavior. This project aims to improve insights into how humans act and interact.
Clone's Teleoperated Hand Demonstration Highlights Legacy Design
Clone has showcased its teleoperated hand, highlighting its legacy design. The company plans to release a redesigned Torso 4 in November for enterprise tasks.
UBTECH Launches Factory Tour Series Showcasing Production Robots
UBTECH Robotics has unveiled a factory-tour series featuring robots in production. The CEO highlighted a monthly capacity of 1,500 units, emphasizing the efficiency brought by humanoid robots.
Three-Stage Method for Multi-Task Learning in Legged Robots
This research presents a three-stage method for training legged robots to perform multiple tasks using reinforcement learning. The approach successfully combines skills like walking and digging, achieving high performance and robustness in real-world applications.
Awomo-SimDataEngine: Advancing Robot Training Data Generation
The Awomo-PhysicalRSI team has developed Awomo-SimDataEngine, a system that enhances robot training data generation. It combines asset and scene generation with robot demonstration synthesis, leading to improved training success rates.
Atlas Robot's New Hands Enhance Dexterity and Learning Capabilities
Atlas has upgraded its hands to enhance dexterity, now featuring 13 degrees of freedom. This improvement supports better tactile sensing and learning capabilities.
Agility Robotics and FORT-Robotics Enhance Safety Features for Digit 5
Agility Robotics and FORT-Robotics are enhancing safety features for the humanoid robot Digit 5. Their partnership includes new safety systems and communication improvements.
Weekly Robot Video Roundup: Self-Assembling Arm and Drone in Nepal
This week's roundup features a self-assembling modular arm for disaster recovery and drones aiding in flood response in Nepal. Check out these innovative robot applications in action.
Weekly Robot Video Highlights: Modular Arm and Drone Recovery Efforts
This week's robot video highlights include a modular arm for disaster recovery and drones aiding in flood response in Nepal. These innovations demonstrate the potential of robotics in emergency situations.
Advancing Legible Planning in Robotics through Observer Perspective
This paper presents a method for improving legible planning in robotics by focusing on the observer's perspective. It extends previous research without the need for custom planners, offering insights into task space connections.
Path Tracking Controller for Precision Agriculture Using Nonlinear Model Predictive Control
This study introduces a path tracking controller for tractors in precision agriculture, leveraging Nonlinear Model Predictive Control. It evaluates the system's performance through field tests, demonstrating its effectiveness in guiding tractors along predefined paths.
New Design Pattern Enhances Sim-to-Real Robotics Research
A new design pattern in robotics research addresses challenges in sim-to-real transitions for LLM-driven robots. By managing contact fidelity during handoffs, the method enhances governance benchmarking and audit-chain stability.
AstriBot Launches T1 Platform with Lumo AI for $18,000
AstriBot has launched its T1 humanoid robot platform, featuring Lumo AI models. The platform is available to US researchers and developers at a starting price of $18,000.
Boston Dynamics Unveils Redesigned Hands for Atlas Robot
Boston Dynamics has revamped the hands of its Atlas robot, enhancing its ability to use tools with advanced sensors. The redesign also simplifies the hand structure by eliminating the pinky finger.
Former NVIDIA Researcher Joins Microagi to Enhance Robot Deployments
Microagi has appointed a former NVIDIA researcher as chief scientist to advance their Usable Robots team. The focus will be on integrating robot training with industrial applications and data collection.
Fly Ventures and Toyota Ventures Invest in Innovative Robot Hands
Fly Ventures and Toyota Ventures have invested in a Columbia spinout developing robotic hands. These hands utilize touch sensing and learned control for intricate factory tasks.
HTX Launches H2RC Facility for Humanoid Robot Training
HTX has introduced a new facility focused on training humanoid robots for challenging tasks. The H2RC will prepare robots for operations in hazardous environments, including emergency and security scenarios.
Service Robots Enhance Navigation with Furniture Recognition
Service robots are improving their navigation skills by recognizing different types of furniture in office spaces. This recognition is essential for effective route planning and interaction with objects.
Soft Robots Inspired by Octopus Arm Movement
The study of octopus arm movement is paving the way for advancements in soft robotics. By mimicking the flexibility and control of these marine creatures, engineers aim to enhance the functionality of robotic systems.
KAIST Researchers Develop Robot Inspired by Venus Flytrap Mechanism
KAIST researchers have developed a robot that mimics the Venus flytrap's ability to sense and grasp objects. This innovative design combines sensory and gripping functions for improved robotic interaction.
XPENG CEO Discusses Humanoid Robotics Journey in New Documentary
XPENG's CEO He Xiaopeng offers a candid look at the company's struggles and strategies in humanoid robotics. He emphasizes the importance of EV intelligence in developing physical AI.
Husqvarna Secures Exception for Robot Vacuums Amid FCC Ban
Husqvarna has received an exemption from the FCC ban affecting robot vacuums and other devices. The Defense Department has ruled that specific models do not pose a national security risk.
LTX-2.5 Pretrained Checkpoint Enables Video Task Execution
The LTX-2.5 pretrained checkpoint is being used by a robotics team to generate videos of tasks. This model allows for the execution of tasks as demonstrated in the videos.
New Kinematic Construction Links Serial and Parallel Mechanisms
This paper introduces a kinematic framework that connects serial and parallel mechanisms, enhancing robotic motion analysis. Validation through various mechanisms shows high accuracy in results.