Skip to Content Facebook Feature Image

Touch Ignites Physical Intelligence: Xense Robotics Showcases the Real Ability of Tactile Intelligence at ICRA 2026

Business

Touch Ignites Physical Intelligence: Xense Robotics Showcases the Real Ability of Tactile Intelligence at ICRA 2026
Business

Business

Touch Ignites Physical Intelligence: Xense Robotics Showcases the Real Ability of Tactile Intelligence at ICRA 2026

2026-06-03 22:10 Last Updated At:22:25

VIENNA, June 3, 2026 /PRNewswire/ -- From June 2 to June 4, 2026, ICRA, the flagship global conference in the field of robotics, was grandly held in Vienna, Austria. Xense Robotics appeared at Messe Wien Exhibition & Congress Center, Hall B-123. With "Touch Ignites Physical Intelligence" as its core proposition, Xense Robotics comprehensively displayed a full-stack tactile intelligence technology system covering tactile hardware perception, data acquisition, tactile world models, and VTLA models.

At the exhibition, Xense Robotics presented a major showcase of VTLA model-driven dual-arm long-horizon compliant manipulation, intuitively verifying the core value of tactile intelligence in real and complex robotic operations; the TacCap-Gripper tactile data acquisition device made its global debut, filling a key gap in the data closed loop for robotic physical interaction; meanwhile, a complete product matrix of multimodal tactile sensors was fully exhibited. It also offered an immersive tactile interactive experience at the booth, demonstrating the real-time response performance of high-precision tactile sensing in a lightweight and visualized manner, which highlighted to the global industry the solid ability of tactile intelligence in empowering robotic physical interaction and supporting the real-world implementation of embodied intelligence.

Tactile Intelligence Becomes the Key Gateway to Real-World Physical Intelligence

As visual perception, intelligent motion planning, and multimodal large-model technologies continue to advance rapidly, robots have made significant progress in environmental understanding and task planning. Yet in real, unstructured physical environments, the core challenge for robotic deployment often lies not in "seeing the environment clearly," but in "interacting with precision after contact."

Key physical information such as object slippage, material deformation, contact stability, and force magnitude cannot be accurately and precisely accessed by visual perception alone, yet it directly determines the success rate and performance stability of practical robotic tasks such as grasping, precision assembly, flexible folding, accurate alignment, and pressing. In other words, vision allows robots to see the world, while tactile intelligence enables robots to truly touch and autonomously interact with the physical world. It is a core breakthrough point for bringing embodied intelligence into industrial applications.

At ICRA 2026, Xense Robotics took "Tactile Intelligence Empowering the Implementation of Physical Intelligence" as its core exhibition theme and comprehensively presented its full-stack closed-loop physical intelligence ecosystem, including underlying tactile hardware R&D, high-precision tactile data acquisition, iteration of self-developed perception algorithms, tactile world model construction, and scenario-based application of VTLA models.

Real-World Validation of Core Value: Tactile-Driven Long-Horizon Compliant Autonomous Manipulation

The core showcase at the booth was a VTLA model-driven dual-arm long-horizon autonomous carton-forming operation demonstration, which presented a hard-core technical ability of implementation in a life-like scenario. The seemingly simple carton-forming task is in fact a typical complex robotic operation scenario involving flexibility, multiple steps, strong contact, and high disturbance. It requires the robot to continuously complete a series of long-sequence coherent operations, including cardboard grasping, spreading and unfolding, precise alignment, edge folding and shaping, and pressing and finalizing. It placed extremely high requirements on the device's adaptive capability and real-time regulation capability.

Different from traditional robot fixed-trajectory programming and purely vision-led passive operation modes, Xense Robotics' solution relies entirely on real-time "tactile + visual" feedback to drive autonomous decision-making and motion regulation. Faced with thin, lightweight, easily deformable flexible cardboard materials whose contact states change dynamically, the robot can sense contact position, force magnitude, material deformation, and contact stability in real time, autonomously access the operation state, and dynamically correct the coordinated movements of both arms. Without manually preset trajectories, it can adaptively complete the entire standardized forming operation process.

This real-world demonstration clearly proves that with tactile intelligence, robots can break free from the constraints of preset programs and advance from "passively executing commands" to "actively perceiving, autonomously adapting, and dynamically manipulating." It addresses a key industry pain point in flexible-material handling and long-horizon complex operations, providing a new solution for autonomous robotic work in unstructured scenarios.

Full Portfolio Showcase: Building a Full-Stack Technology Closed-Loop for Tactile Intelligence

In addition to the core real-world demonstration, Xense Robotics brought a major product debut and a full-series technology matrix display this time, elaborately presenting full-stack closed-loop physical intelligence capabilities of "hardware perception - data acquisition - algorithm optimization - scenario implementation."

At the site, TacCap-Gripper, a tailor-made device for robotic physical interaction data acquisition, made its global public debut. As a wearable two-finger tactile data acquisition device for physical intelligence, the product integrates high-precision visuo-tactile sensor, IMU inertial measurement unit, and high-resolution encoder, enabling synchronized acquisition and precise matching of multidimensional data from robot motion, vision, and touch.

In robotic operation, the most critical and difficult-to-capture information is the dynamic physical interaction process after contact. TacCap-Gripper can accurately record key micro-level information such as start and end states of contact, pressure distribution, material deformation, slippage trends, and force fluctuations. It turns ambiguous physical interaction behavior into high-quality embodied data that can be collected, synchronized, modeled, and used for training. This provides essential data support for fine robotic grasping, precision assembly, adaptive manipulation optimization, and iterative training of embodied intelligence models, while filling a critical gap in the industry's physical intelligence data loop.

At the same time, Xense Robotics fully exhibited its complete product matrix of multimodal tactile sensors, comprehensively covering all hardware forms including fingertips, grippers, flat surfaces, and curved surfaces, being adaptable to multiple scenario carriers such as dexterous hands, industrial robotic arms, humanoid robots, various embodied intelligent agents, and flexible interaction devices. Among them, the self-developed fingertip tactile sensor can accurately capture micro-deformation, texture changes, and multidimensional force states, precisely supporting high-precision operations such as alignment, poking, rolling, and fine grasping. Paired with a systematic whole-hand tactile solution, it can realize continuous and all-round hand tactile feedback, fully meeting the needs of complex human-robot interaction and fine operation.

From multimodal perception hardware to professional data acquisition devices, and then to the robotic operation demonstration of VTLA models, what Xense Robotics exhibited this time was not a single product, but a complete physical intelligence enablement system: capturing real physical information through tactile hardware, accumulating high-value interaction data through professional data acquisition devices, and ultimately realizing the continuous evolution of robotic operation capabilities based on self-developed VTLA model algorithms, so that every physical contact becomes a core data asset for robots' autonomous learning and scenario generalization.

Lightweight Immersive Experience: Making Advanced Tactile Technology Visible, Experiential, and Applicable

To intuitively convey the technical advantages of high-precision tactile sensing, Xense Robotics' booth specially set up a lightweight tactile interactive game experience area. Abandoning traditional mechanical handles, touch buttons, and other control methods, it relied entirely on Xense Robotics' self-developed planar tactile sensor. Through visitors' light touches, presses, and changes in force, it could respond in real time and control the progress of the game.

This relaxed and engaging interaction experience directly demonstrates the ultra-high sensitivity, millisecond-level real-time response, and fine-grained pressure recognition of Xense Robotics' tactile sensors. It allows all visitors to experience the delicate perception and dynamic interaction advantages of tactile intelligence firsthand, while also validating the broad application potential of tactile technology in human-robot interaction, multimodal intelligent input, and other scenarios.

Continuous Technical Commitment: Advancing Embodied Intelligence from "Seeing" to "Doing"

From tactile hardware perception and tactile data display to real-task validation and on-site interactive experiences, Xense Robotics, a hard-tech company among the first globally to propose the theory of tactile spatial intelligence, has long focused on the core field of robotic tactile intelligence. Xense Robotics has successfully built a full-stack closed-loop physical intelligence ecosystem covering tactile perception hardware, data acquisition hardware, tactile world models, and scenario-based VTLA applications.

The development of the industry has made it clear that next-generation advanced embodied intelligence systems cannot rely on vision alone for environmental understanding. They also need tactile intelligence to understand the logic of physical interaction and accurately identify core information such as force, deformation, and contact state, enabling adaptation to complex and changing real-world work scenarios. Only by combining visual cognition with tactile perception can robots truly understand the physical world and achieve the core upgrade from "simply executing actions" to "deeply understanding interaction, autonomously adapting to scenarios, and completing tasks reliably."

Looking ahead, Xense Robotics will continue to uphold its core proposition of "Touch Ignites Physical Intelligence".  Xense Robotics will keep iterating high-precision tactile sensing hardware, improving the tactile data ecosystem, and optimizing perception and VTLA model algorithms. Xense Robotics will dedicate to making tactile intelligence a universal foundational capability for humanoid robots, industrial robots, and all types of embodied intelligent agents, accelerating the global expansion of China's hard-tech tactile innovation, and driving embodied intelligence worldwide from laboratory validation to large-scale real-world deployment.

Exhibition Information

Event Name: ICRA 2026 IEEE International Conference on Robotics and Automation
Dates: June 2-4, 2026
Venue: Messe Wien Exhibition & Congress Center | Hall B-123

About Xense Robotics

Xense Robotics Technology (Shanghai) Co., Ltd. ("Xense Robotics" or "Xense") was founded in May 2024 by Daolin Ma, Associate Professor at Shanghai Jiao Tong University and the sole global Best Paper Award winner at ICRA 2021. Oriented toward the era of physical intelligence, Xense Robotics is a high-tech company focused on the frontiers of intelligent robots' perception of and autonomous interaction with the real physical world, being committed to becoming a global leader in tactile intelligence technology.

Xense Robotics is deeply engaged in full-stack tactile intelligence technologies, and provides integrated tactile intelligence hardware and software solutions covering tactile sensors, embodied data acquisition rich in high-quality tactile data, tactile world models, and VTLA model algorithms incorporating tactile modalities. Guided by the core philosophy of "Touch Ignites Physical Intelligence," Xense Robotics gives intelligent robots the ability to accurately perceive, deeply understand, and autonomously interact with the real physical world, enabling intelligent machines to better contact, perceive, and interact with the world around them.

** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **

Touch Ignites Physical Intelligence: Xense Robotics Showcases the Real Ability of Tactile Intelligence at ICRA 2026

Touch Ignites Physical Intelligence: Xense Robotics Showcases the Real Ability of Tactile Intelligence at ICRA 2026

B2C Lifecycle and CRM teams can now design marketing agents that run on their own data, inside their own guardrails, and coordinate with external AI systems like Claude and ChatGPT through an open Model Context Protocol (MCP) server.

SAN FRANCISCO, June 3, 2026 /PRNewswire/ -- MoEngage, the agentic customer engagement platform used by more than 1,350 consumer brands, today launched Merlin AI Custom Agents. Lifecycle marketers and CRM teams can now build their own workflow agents on top of MoEngage data and tools, define the rules each agent runs inside, and watch every step the agent takes. MoEngage is also opening to the enterprise AI stack through an MCP server, so customers can use AI tools like Claude or ChatGPT to access MoEngage data / tools or build external agents leveraging the MoEngage connector.

Most agentic AI in marketing today operates as a black box. The marketer enters a prompt, the system returns an output, and what happened in between stays hidden. For a CMO running hundreds of millions of customer touchpoints across email, push, in-app, and SMS, that opacity is a non-starter. Merlin is built differently. Every Merlin AI agent shows its work. Marketers see the data it pulled, the decisions it made, the channels it touched, and the content it sent. They set the audiences, channels, content rules, and budget limits before the agent runs. Some teams want full autopilot. Others want a hand on the wheel and review every action before it ships. The same agent runs either way.

"Marketers have been telling us for two years they don't want AI that just does the work. They want AI they can see inside, set rules for, and stop when they need to. Merlin is built around that. The reason teams can let our agents run 24/7 and run experiments at a pace they couldn't touch manually is that the agents only do what the marketer's guardrails allow. Visibility and control are what make autonomy safe. Teams at SoundCloud, Loblaws, Swiggy, Domino's, and dozens of other consumer brands shaped what we shipped," said Raviteja Dodda, Co-founder and CEO of MoEngage.

Most martech AI today is built for one audience: a human marketer typing into a chat box. MoEngage is building for both the marketer and the AI agents already running inside the company. Through the MCP server and agent-callable APIs, MoEngage agents pass context to and take direction from external systems. For enterprises standardizing on a platform, the existing stack stays in place rather than getting replaced.

What's new

Custom Agents in Merlin AI. Build agents that run continuously on your workflows. Every custom agent runs on MoEngage data, uses MoEngage tools, and operates inside the rules a marketer defines. A full activity log shows every decision it makes. Customer use cases: agents that QA campaigns before they go out, agents that turn a creative brief into a journey ready for review, and agents that produce analytics reports without anyone opening a dashboard.

New Merlin AI agents. Three additions to the agent suite already in Studio:

  • In-App Template Generator. Describe the in-app message you want. Merlin returns the App Template with responsive code and interaction logic done.
  • Flows Assist. Type the objective of a journey. Merlin returns a multi-stage canvas with triggers, paths, and channel steps wired in. The marketer reviews, edits, and ships.
  • Campaign Insights Agent. Ask questions about your campaigns in plain language. The agent surfaces what's working, what isn't, and what to change next.

MoEngage MCP Connector. Connect MoEngage to external AI systems like Claude and ChatGPT through the Model Context Protocol. Your own agents read MoEngage context, coordinate with Merlin agents, and take action across your stack without custom integration work.

Check out the Merlin AI agents here.

See Merlin AI Custom Agents at Salesforce Connections

MoEngage will be at Salesforce Connections on June 3rd and 4th in Chicago. Teams attending the event can see Merlin AI Custom Agents and the MCP Connector in action at booth #302. Stop by to talk through how the platform fits your stack.

About MoEngage

MoEngage is an Agentic Customer Engagement Platform trusted by over 1,350 global consumer brands, including Flipkart, Domino's, Loblaws, Kayak, Soundcloud, and Deutsche Telekom. The platform combines deep customer analytics, agentic marketing workflows through its Merlin AI Agents, and omnichannel orchestration — helping marketing and product teams deliver experiences that feel personal at any scale. MoEngage is headquartered in San Francisco with offices across North America, EMEA, and Asia. Learn more at moengage.com.

 

** This press release is distributed by PR Newswire through automated distribution system, for which the client assumes full responsibility. **

MoEngage Launches Merlin AI Custom Agents With Full Visibility, Marketer-Defined Guardrails, and Open MCP Architecture

MoEngage Launches Merlin AI Custom Agents With Full Visibility, Marketer-Defined Guardrails, and Open MCP Architecture

MoEngage Launches Merlin AI Custom Agents With Full Visibility, Marketer-Defined Guardrails, and Open MCP Architecture

MoEngage Launches Merlin AI Custom Agents With Full Visibility, Marketer-Defined Guardrails, and Open MCP Architecture

Recommended Articles