视触融合
Search documents
能“称大象”,也能“称蚂蚁”!打通机器人“进家”最后一公里
Zhong Guo Zheng Quan Bao· 2025-12-02 05:10
Core Insights - The core component of robotic precision operation is the six-dimensional force sensor, which enables robots to perform delicate tasks with human-like flexibility [1][2] - Blue Dot Touch, founded by Liu Wuyue, leverages aerospace technology to develop and commercialize force control technology for intelligent robots, breaking the long-standing foreign monopoly in this field [1][2] Technology Breakthrough - The six-dimensional force sensor allows robots to execute complex tasks by providing real-time feedback on force magnitude and direction, enabling precise interactions in various scenarios [2][3] - The sensor's precision can reach 0.1 Newtons, equivalent to the weight of a bottle cap, ensuring reliable and sensitive operations for tasks like folding clothes or handling fragile items [2][3] Market Dynamics - The demand for six-dimensional force sensors is rapidly increasing as more companies shift from purely visual solutions to a "vision-touch integration" approach, enhancing operational accuracy [4] - The market for six-dimensional force sensors in humanoid robots is projected to grow significantly, with an expected shipment of 12,300 units in China by 2025, representing a year-on-year increase of 510.1% [4] Company Developments - Blue Dot Touch has established four key technology platforms to enhance service efficiency, reducing customer response time to 3-4 weeks [5] - The company is expanding its production capacity with a new 10,000 square meter facility and a fully automated production line, aiming to increase output by 3 to 4 times [5] - Recent funding rounds, including a C-series financing exceeding 100 million RMB, will support product development, capacity expansion, and international market growth [5]
人形机器人做汉堡火了! 伯克利等全新ViTacFormer让机器人操作稳如老手
机器之心· 2025-07-10 06:07
Core Viewpoint - The article discusses the advancements in humanoid robots, particularly focusing on the ViTacFormer framework that integrates visual and tactile information for dexterous manipulation tasks, showcasing its potential to revolutionize kitchen automation and other complex tasks [1][4][24]. Group 1: Technology and Innovation - The ViTacFormer framework is designed to enhance precision, stability, and continuous control in dexterous manipulation by combining visual and tactile data with a predictive mechanism for future tactile feedback [4][11]. - The system utilizes a dual-arm robot setup equipped with advanced tactile sensors and cameras to gather real-time data during operations, allowing for a comprehensive understanding of contact dynamics [13][14]. - ViTacFormer employs a cross-modal attention mechanism and an autoregressive tactile prediction branch, enabling the model to anticipate future contact states, thus improving action generation and overall task performance [9][11][24]. Group 2: Experimental Validation - The performance of ViTacFormer was evaluated through various short-range dexterous manipulation tasks, demonstrating a significant improvement in success rates, with an average increase of over 50% compared to existing methods [22][24]. - In a long-duration task simulating the complete process of making a hamburger, ViTacFormer achieved a continuous operation time of approximately 2.5 minutes with an overall success rate exceeding 80%, highlighting its effectiveness in complex, multi-stage tasks [28].