Strike Robot

SR Agentic + SR Platform — Build the new normal for robots faster.

📃
📃

[Strike Robot @StrikeRobot_ai]

Creating a simulated world for robots has never been easier than now.
Introduce SR Platform.

SR Platform provides a seamless generation pipeline:
• Asset Creation
• Spatial Layout Generation
• Real-time Editing
• Simulation & Rollout
Using every model. Data stay yours.

Powered by @AskVenice
Try it: https://t.co/O6QTDxq443

[Strike Robot @StrikeRobot_ai]

A new milestone for SR Platform: vehicles are joining our robotics scenes, complete with detailed interiors, opening doors, and moving wheels.

[Strike Robot @StrikeRobot_ai]

StrikeRobot Private EVM.

Powering the next era of Physical AI.

Coming this December.

[Strike Robot @StrikeRobot_ai]

This is how a dog opens a microwave using a robotic arm strapped to its back

[Strike Robot @StrikeRobot_ai]

A cabinet is more than its shape. SR Platform brings 3D objects to life, down to the details.

[NVIDIA Robotics @NVIDIARobotics]

Serving World Models: Latency vs Throughput with NVIDIA Cosmos 3 Super on Nebius | Cosmos Labs https://t.co/0dfLEfkhCU

[Strike Robot @StrikeRobot_ai]

The entire process carried out on the SR Platform, continuously refined.

[NVIDIA Robotics @NVIDIARobotics]

🦆 Put AI agents to work to help your robot learn to navigate.

Using Microduck as the reference robot, this walkthrough shows how to create a simulated obstacle course with @OpenAI GPT-6 Astra, build 3D assets with @nvidiaomniverse libraries, simulate physics with Newton, train policies in NVIDIA Isaac Lab, and validate them in Isaac Sim on @NVIDIARTXSpark.

[Strike Robot @StrikeRobot_ai]

A soft, elastic object is easy to imagine. Making it simulation-ready is the hard part.
SR Platform starts with a prompt and builds the rest.

[Virtuals Protocol @virtuals_io]

We’re excited to share that our robotics data and deployment lab @eastworlds_io was part of the global stress test behind @dreamlabs_ai’s Dream-1 launch, accelerating physical AI.

[Strike Robot @StrikeRobot_ai]

base:0x10c56f005a379f8eafc88ff5c3f40d30f0031ac9 /burn 🔥 loading . . .

[Strike Robot @StrikeRobot_ai]

Give your robot a world to work in.
Build a scene in SR Platform, add your robot, and inspect it from every angle before simulation.

[Strike Robot @StrikeRobot_ai]

A major milestone for projects in the robotics space. Congratulations to the entire team and Mr. @Rewkang

[RoboStrategy @RoboStrategy]

The first AI robot to ring the bell on Nasdaq

[Strike Robot @StrikeRobot_ai]

This is how SR Platform creates a fully functional asset with multiple DOF.

[Strike Robot @StrikeRobot_ai]

From a simple prompt to simulation-ready assets and scenes.

SR Platform combines AI generation with validation gates that check geometry, articulation, and physics readiness. Clear feedback catches issues and guides refinement throughout the workflow.

Quality checked at every stage. Built for simulation.

[Strike Robot @StrikeRobot_ai]

From a simple prompt to simulation-ready assets and scenes.

SR Platform combines AI generation with validation gates that check geometry, articulation, and physics readiness. Clear feedback catches issues and guides refinement throughout the workflow.

Quality checked at every stage. Built for simulation.

[Strike Robot @StrikeRobot_ai]

API calls are about to fuel the burn.

base:0x10c56f005a379f8eafc88ff5c3f40d30f0031ac9 Burn starts in the next few days. Powered by real API usage.

https://t.co/fMBNHGX1RD

[Strike Robot @StrikeRobot_ai]

SR Platform’s scene pipeline now handles planning, asset reuse or generation, validation, and simulation export in separate stages.

We’re exploring how JEV by @typesafeai could help with the reuse-or-generate decision. JEV integration is in development!

[Strike Robot @StrikeRobot_ai]

From perception to action - fully closed-loop.

SR Agentics enables the robot to understand a high-level instruction, identify objects by material, and autonomously execute semantic pick-and-place tasks inside an SR Platform-generated simulation.

See. Reason. Act. Repeat

[Strike Robot @StrikeRobot_ai]

@mianoedwin_ With cameras or LiDAR, we can build the map and handle obstacle avoidance, something we’ve already demonstrated publicly.

https://t.co/SvBvLniRaT

[Strike Robot @StrikeRobot_ai]

This is how the robot sees the world ��� straight from its camera + LiDAR.

A small use case of StrikeRobot Agentic, showing how agentic systems operate in real scenarios:

• Detects the target person via edge-optimized face detection
• Detects obstacles in real time
• Estimates distance using camera physics (beyond depth sensor limits of Unitree G1)
• Plans the shortest path with A* + smooth trajectories using Bezier
• Continuously replans as the environment changes

✅ Result:
the robot avoids obstacles, optimizes its path, and autonomously moves toward the designated person.

[Strike Robot @StrikeRobot_ai]

When SR Agentics meets SR Platform in simulation.

The entire environment and every object within it are generated by SR Platform.

Within this simulated world, #XLeRobot can now autonomously execute a 12-step sequence of tasks, seamlessly from start to finish: perceiving, reasoning, navigating, and interacting with objects along the way.

12 steps. One continuous autonomous workflow.

[Strike Robot @StrikeRobot_ai]

@gaogaocrypto We handled that in the real world quite some time ago at Eastworlds. https://t.co/KHUshOXQUh

[Strike Robot @StrikeRobot_ai]

/ NOTICE → / REASON → / DECIDE → / ACT

The obstacle wasn't there before.

It appeared mid-mission & the robot had under 200ms to notice, reason, and reroute.

This run, we tested unexpected scenario detection and validated balance stability against our own trained policy.

No hardcoded rules. No human input.