A single destination for timely, editor-curated robotics news from around the world.
A recent study published in the Journal of Field Robotics explores a human pose estimation approach aimed at enhancing multi-modal perception in dynamic occlusion scenarios. This research is particularly relevant for improving human-robot collaboration, as it addresses the challenges posed by occlus...
A recent study published in the Journal of Field Robotics explores a novel approach to obstacle-avoidance path planning for unmanned aerial vehicles (UAVs). This method utilizes MobileViT-based multimodal perception combined with deep reinforcement learning to improve navigation capabilities in comp...
Neura Robotics has introduced Neuron AI, a multimodal foundation model designed for physical AI. This innovative model integrates 3D vision, touch, audio, robot state, and language with memory, allowing robots to process information beyond visual input and retain context when objects are not visible...
Dalian University of Technology has introduced VA-Bench, a testing framework that evaluates 12 multimodal model setups on various robot-arm tasks. Among these models, Qwen3.8-max achieved the highest success rate, completing 53.93% of the tasks. However, none of the models managed to finish a strict...
A research team led by Professor Jianfeng Li from Beijing University of Technology has developed a novel multi-modal dynamic assessment method for patients with idiopathic scoliosis (IS). This method integrates surface electromyography (sEMG) and spatial positioning information (SPI) to monitor and...
ACE Robotics and NTU S-Lab have announced the open-source release of Puffin-World, a multimodal world model that integrates physics, geometry, and appearance. This model utilizes the Puffin-16M dataset and achieves state-of-the-art camera absolute pose errors, reporting sub-degree accuracy across fo...
The article discusses a novel approach to damage-free grasping through the implementation of variable impedance and Quadratic Programming-Collision Barrier Function (QP-CBF) control. This method leverages multimodal oxidation prior to enhance the grasping capabilities of robotic systems. This advan...
Flytrex, an autonomous drone food delivery service, has partnered with Nash, an autonomic logistics platform, to create an autonomous-first, multi-modal delivery platform. This integration is now operational across all of Flytrex's Dallas-Fort Worth locations, combining Flytrex's autonomous fleet wi...
Recently, DailyOmni announced its latest evaluation results, revealing that WITA-Omni Preview, developed by Zhiyuan, topped the rankings with a score of 85.21. This model surpassed leading competitors such as Qianwen, Gemini, Doubao, and NVIDIA, achieving first place in six out of eight sub-indicato...
The latest issue of Science Robotics, Volume 11, Issue 116, published in July 2026, delves into the advancements in bioinspired multimodal robotics. This research highlights how biological systems can inform the design and functionality of robotic systems, leading to more versatile and adaptive tech...
On July 17, 2026, the World Artificial Intelligence Conference (WAIC) commenced in Shanghai, focusing on the theme 'Intelligent Partners, Co-Creating the Future.' Dahuang Technology presented its AI multimodal capabilities, showcasing a comprehensive system that includes understanding, connecting, i...
Noetra, in collaboration with key partners including Sony, SoftBank, NEC, and Honda Motor, has launched extensive R&D for a multimodal foundation model aimed at enhancing AI-enabled robotics in Japan. This initiative is part of a broader effort to develop sovereign AI technologies within the country...
WeRide has introduced WITT, a groundbreaking physical AI foundation model designed to enhance multimodal scene understanding. This model utilizes minimal physical fact units, which are crucial for applications in autonomous driving and robotics. The launch of WITT is significant as it aims to strea...
A new hierarchical planning framework has been developed to improve multi-target substation inspections using UAVs. This framework incorporates perception-aware capabilities, allowing for more efficient navigation and task execution in complex environments. The significance of this development lies...
On October 14, 2026, NEURA Robotics launched Neuron AI, a multimodal foundation model designed for Physical AI. This innovative model is trained using real-world robot data, simulation-enhanced data, and human demonstrations, allowing it to operate across five different NEURA robot embodiments, incl...
CAIR, the Hong Kong AI and robotics center of the Chinese Academy of Sciences, has launched CARES 4.0. This innovative clinical agent assists doctors by drafting reports and providing analyses for their consideration. The introduction of CARES 4.0 is significant as it represents a step forward in i...
Atomica, a microfabrication foundry based in the U.S., has introduced its Physical AI Sensor Platform. This platform is designed to assist customers in creating sensors tailored for various applications, including robotics, autonomy, industrial automation, medical systems, defense, smart infrastruct...
On August 26, 2026, Datatang Inc. announced the launch of a large-scale multimodal dataset focused on Ego-centric perspectives to accelerate research and development for physical AI models. This dataset, under the Nexdata brand, synchronizes video, IMU, SLAM, depth information, hand keypoints, and s...
SenseTime has introduced the SenseNova U1.5-Lite-Preview, which utilizes the NEO-Unify architecture to provide native 4K generation and advanced editing features. This new model is designed to replicate design frameworks effectively across various types of infographics and creative content. The rel...
On July 23, HiDream.ai announced the completion of a Series C funding round, raising 1.5 billion RMB, equivalent to approximately $2.1 billion. This funding was led by the Sichuan Revitalization Science and Technology Innovation Fund, ICBC Capital, and other notable investors. With this round, HiDre...
NueroDance has launched its ND1000 and ND8 series EEG devices, along with the NeuroAI group cross-modal data platform, during an event in Beijing. This initiative aims to establish a neural data infrastructure that extends the capabilities of AI beyond traditional text and image processing. The int...
Bioinspired multimodal robots are advancing rapidly, aiming to match the versatility of animal movement by integrating flying, walking, swimming, and climbing capabilities. Researchers from Beihang University, Dalian University of Technology, and EPFL are addressing engineering challenges such as li...
The Journal of Field Robotics has published an early view article that explores advancements in robotic technology and its applications in various fields. This publication, released in October 2023, highlights the innovative research conducted by a team of engineers and scientists aiming to enhance...
A research team at Wuhan University has developed an innovative method for creating complex three-dimensional structures by utilizing straightforward two-dimensional processing techniques. This breakthrough enables the efficient mass production of programmable and reconfigurable 3D sensors, addressi...
A recent study published in the Journal of Field Robotics highlights the advancements in autonomous robotic systems designed for agricultural applications. Researchers from various institutions collaborated to explore innovative technologies that enhance efficiency and sustainability in farming prac...
In a groundbreaking study published in the May 2026 issue of Science Robotics, researchers have unveiled a new robotic system designed to assist in complex surgical procedures. This innovative technology, developed by a team of engineers and medical professionals, aims to enhance precision and reduc...
SynapX has unveiled SYNData, an innovative multimodal data collection system designed to enhance dexterous manipulation capabilities in robotics. This cutting-edge system integrates ego vision, electromyography (EMG) signals, and data from exoskeleton gloves, facilitating the scalable collection of...
SynapX has introduced SYNData, an innovative multimodal data collection system designed to enhance dexterous manipulation capabilities. Launched recently, this system integrates ego vision, electromyography (EMG) signals, and data from exoskeleton gloves, facilitating the scalable collection of huma...
A groundbreaking development in robotics is underway, as researchers unveil a new type of robot designed for applications beyond traditional factory settings. This innovative robot, which is being developed by a team of engineers and scientists, aims to enhance human interaction and assist in variou...
A recent study published in the Journal of Field Robotics highlights the advancements in robotic technology aimed at enhancing agricultural efficiency. Researchers from various institutions collaborated to develop innovative robotic systems designed to assist farmers in crop monitoring and managemen...
DiDi Autonomous Driving has launched DiDi Voyager Labs, a new research initiative aimed at advancing end-to-end autonomous driving through the development of multimodal large models, world models, and reinforcement learning. This initiative, announced recently, will collaborate with a research team...
A recent study published in the Journal of Field Robotics highlights advancements in robotic technology aimed at improving agricultural efficiency. Researchers from various universities collaborated to develop autonomous systems capable of performing tasks such as planting, monitoring crop health, a...
A team of researchers from Caltech and the Technology Innovation Institute in Abu Dhabi has introduced an innovative multirobot system known as X1. This advanced system integrates a walking humanoid robot with a transforming drone capable of driving. The initiative seeks to enhance the versatility a...
Micro and small autonomous underwater vehicles (AUVs) are increasingly recognized for their ability to integrate various sensors and navigation systems, making them particularly suitable for operations in coastal waters. Their deployment and operation are straightforward, which enhances their appeal...
Peng Zhihui, the founder of AgiBot, unveiled a video today featuring the Lingxi X2, an advanced bipedal humanoid robot. This innovative robot is equipped with a sophisticated computing engine that enables it to perform a variety of tasks, including walking, running, dancing, riding a bicycle, balanc...
RSF defines a common language for robot service capability, lifecycle operations, certification pathways, and service-provider networks.
Daily robotics news, in-depth analysis, conference highlights, and discussions with professionals worldwide.
