Flexiv’s Rizon 4 Adaptive Robot Now Supported in NVIDIA Isaac
Flexiv, a global leader in general-purpose robotics, today announced that its flagship Rizon 4 adaptive robot is now supported in NVIDIA Isaac. This support includes a new contact-rich insertion reference workflow from NVIDIA built on NVIDIA Isaac Lab, Isaac ROS, and Rizon 4.
This milestone brings Flexiv’s force-controlled technology into one of the most widely used robotics software platforms, giving developers a powerful new tool to build intelligent, adaptable systems — and makes the Rizon 4 one of the first seven-axis force-controlled robots supported in the Isaac ecosystem.
By integrating the Rizon 4 with NVIDIA’s high-performance software stack, roboticists gain native access to hardware-accelerated packages optimized for NVIDIA GPUs. This support significantly reduces the computational overhead of AI, motion planning, and real-time environment processing, allowing teams to focus on high-level application logic instead of low-level system optimization.
“Support in NVIDIA Isaac demonstrates the utility of our force control technology,” said Shiquan Wang, Flexiv CEO. “As one of the first adaptive robots supported in this ecosystem, the Rizon 4 bridges the gap between high-level AI perception and physical adaptability. We’re enabling solutions that can respond dynamically with controllable contact to real-world conditions."
A New Contact-Rich Insertion Workflow, Built on the Rizon 4
Insertion is one of the hardest problems in electronics assembly. Connector sockets shift by fractions of a millimeter between fixtures and cycles, tolerances are tight, and a replayed trajectory cannot reliably absorb that variation. Traditional position-controlled automation either over-constrains the part or damages it.
NVIDIA’s new contact-rich insertion reference workflow addresses this with a reinforcement learning policy trained in simulation and transferred to real hardware. The first instance of the workflow is DisplayPort cable insertion, running on a Rizon 4 series arm with a Flexiv Grav gripper:
-
Train in simulation. The insertion policy is trained at scale in NVIDIA Isaac Lab using the Newton physics engine, with randomization over socket pose, contact properties, and robot dynamics so the policy learns to succeed without being told exactly where the socket is.
-
Deploy through Isaac ROS. The trained policy runs on the physical robot through GPU-accelerated Isaac ROS packages, alongside FoundationPose for pose estimation and cuMotion for motion planning for the approach phase.
-
Close the loop on contact. The Rizon 4's task-space high-performance force control framework provides the compliant, contact-aware, dynamically precise execution the policy depends on during the final millimeters of insertion.
The workflow and its simulation assets are being released so developers can reproduce the DisplayPort reference workflow and adapt the same recipe to their own connectors, sockets, and fixtures.
Why the Rizon 4 for Contact-Rich Work
Force-sensitive applications such as assembly, insertion, and polishing have long fallen between two worlds: research platforms that are open but not production-ready, and industrial arms that are robust but closed. The Rizon 4 bridges that gap, which is what made it a fit for this workflow:
-
Permissive SDK. Low-level control, including streaming motion commands at 1,000 Hz — a rare capability among industrial robots, and a prerequisite for running a learned policy at high rate on real hardware.
-
Integrated sensing. Built-in joint torque and force-torque sensors eliminate the need for external sensing hardware.
-
A well-tuned high-fidelity force controller. Predictable, well-characterized low-level control makes it substantially easier to transfer a simulation-trained policy onto the physical robot.
Those same properties are already being used in production settings: electronics manufacturers apply the Rizon platform’s force capabilities to tasks such as high-precision, contact-rich assembly, while physical AI developers build on the open SDK and integrated sensing for similar workflows.
Beyond a Single Task
Unlike traditional position-controlled robots that rely on rigid, pre-programmed trajectories, the Rizon 4 can sense and adjust to contact forces in real time. This enables it to compensate for variability in object position, surface properties, and material compliance, making it ideal for tasks that use AI-driven perception to make intelligent decisions about how to act.
Developers working with the Rizon 4 can now use modular Isaac ROS GEMs — ready-to-use GPU-accelerated software modules that provide optimized building blocks for perception, navigation, and manipulation — without writing custom low-level wrapper code. These modules deliver high-performance capabilities out of the box, lowering technical barriers and shortening prototyping cycles. The integration also provides a clear, production-ready path from NVIDIA Isaac Sim virtual testing to physical deployment, allowing teams to validate complex behaviors in simulation before transferring them to the real robot.
Together, these advances create a powerful foundation for physical AI applications, enabling organizations to solve complex real-world challenges with greater speed and reliability.
Availability
The contact-rich insertion workflow will be released by NVIDIA Isaac in October. To learn more about the Rizon 4 and the NVIDIA Isaac ecosystem, full platform documentation and hardware support packages are available on the NVIDIA Isaac ROS Flexiv page: https://nvidia-isaac-ros.github.io/robots/flexiv/index.html
