Flexiv Rizon 4 adaptive robot now supported in NVIDIA Isaac

Flexiv announced that its flagship Rizon 4 adaptive robot is now supported in NVIDIA Isaac. Flexiv said that this support includes a new contact-rich insertion reference workflow from NVIDIA built on NVIDIA Isaac Lab, Isaac ROS and Rizon 4.

The company said that the 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.

Rizon 4 added into Isaac

By integrating the Rizon 4 with NVIDIA’s high-performance software stack, Flexiv said that roboticists gain native access to hardware-accelerated packages optimized for NVIDIA GPUs.

”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."

The company said that 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.

Contact-rich insertion workflow built on the Rizon 4

Flexiv said that 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. The company said that traditional position-controlled automation either over-constrains the part or damages it.

Flexiv said that NVIDIA’s new contact-rich insertion reference workflow addresses this with a reinforcement learning policy trained in simulation and transferred to real hardware. The company said that 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.

Flexiv said that 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 Rizon 4 for contact-rich work

Flexiv said that 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 company said that 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.

Flexiv added that 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.

Rizon 4 integration with NVIDIA Isaac goes beyond a single task

Unlike traditional position-controlled robots that rely on rigid, pre-programmed trajectories, Flexiv said that the Rizon 4 can sense and adjust to contact forces in real time. The company said that 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.

Flexiv said that developers working with 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.

The company said that these modules deliver high-performance capabilities out of the box, lowering technical barriers and shortening prototyping cycles. Flexiv added that 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.