Daimon Robotics Builds Infrastructure Layer for Tactile Intelligence in Robots

Vision is central to modern robotics, but cameras cannot capture everything a robot needs to know about physical contact. Handling flexible objects, inserting components or manipulating delicate items requires data about forces, slippage and contact that visual systems may miss.

Daimon Robotics aims to supply infrastructure that helps robots develop this capability. Rather than focusing only on tactile sensors or a single foundation model, it is building a pipeline connecting tactile sensing, data collection, simulation and AI models.

The goal is to turn physical interactions into training data that helps robots perform manipulation tasks more reliably. Dr. Zhu, Daimon's partner and VP of technology, told The Robot Report that the company is 'actually playing the role as an infrastructure provider' by building tactile intelligence. He said Daimon is not aiming to be a foundation model developer but is providing infrastructure for downstream customers. That distinction shapes its strategy: build tools and data infrastructure others can use to create more capable robotic systems.

Collecting useful tactile data at scale is difficult. Unlike visual data, tactile data depends on physical contact and varies with an object's material, geometry, applied forces and task. Daimon is developing a pipeline to capture and process these interactions, with tactile feedback operating at 30 Hz.

The company is also linking real-world data with simulation so physical interactions can inform training in virtual environments. The sim-to-real gap remains a major challenge, especially in reproducing friction and contact forces. Daimon starts by calibrating simulations against real-world measurements before transferring collected data into simulated environments.

Zhu said current simulation is 'not good enough' and 'kind of terrible' regarding the gap between simulated and real environments. Daimon is developing tactile simulations that account for physical properties measured in real-world testing, aiming to improve fidelity and ease transfer of learned capabilities to physical robots.

Daimon has discussed collecting more than 10,000 hours of data; its longer-term Daimon-Infinity initiative targets more than 1 million hours of tactile embodied data. Zhu also stressed collaboration with companies developing robotic models and applications, saying doing everything internally was not enough and that international collaboration in different downstream scenarios is important. That work helps Daimon understand what other developers need from its sensors, data-collection devices, software and evaluation tools.

Daimon is targeting manipulation tasks such as assembly and packaging, where robots must respond to physical contact rather than follow predetermined trajectories. A robot may need to determine whether a component is properly seated, detect when an object slips or adjust its movements when a part behaves unexpectedly; tactile feedback can help it respond.

At IROS 2026, the company demonstrated delicate manipulation applications, including applying heat-transfer designs to tote bags and threading bracelets. It also showed a robot collecting and packaging broken glass, illustrating how models trained on data from varied scenarios can be prompted to perform specific tasks.

Daimon uses its Umi device to collect data from human interactions. Zhu said the demonstrations were powered by foundation models trained on data collected across multiple scenarios, rather than being built solely around individual robot demonstrations. The company has identified Lenovo Capital and Inovance Technology as key partners.

Zhu said Daimon has moved beyond proof-of-concept projects into industrial assembly lines and warehouses, though he declined to name specific customers because of nondisclosure agreements. The commercial test is whether tactile sensing and the models built around it can consistently improve performance in production environments, where robots must handle variations in objects, materials and operating conditions.