AMS
$ 0
AMS is a humanoid training system by Kinetix AI that enables robots to learn agile motion and stable balance through combined real-world and simulated data.
Available on backorder
Specifications and details:
| Type | Teleoperation Platforms |
|---|---|
| Availability | In production |
| Manufacturer | KinetixAI |
| Nationality | China |
| Website | https://www.kinetixai.tech/en/ |
| Core Function | Whole-body motion learning and control |
| Training Method | Hybrid (motion capture + synthetic data) |
| Real-Time Control | Yes (supports live teleoperation) |
| Adaptability | High (generalizes to unseen motions) |
| Input Data | Human pose estimation (RGB/video-based) |
| Deployment | Simulation + real-world humanoid robots |
| Primary Use Case | Training humanoids for dynamic and stable tasks |
Description
AMS is a humanoid training system developed by Kinetix AI that focuses on teaching robots how to move with both agility and balance. It combines human motion understanding with advanced learning methods, allowing robots to replicate natural movements such as walking, running, or maintaining stability in complex poses. Instead of relying on rigid programming, AMS enables robots to learn from diverse motion data, which helps them behave more fluidly in real-world environments. As a result, robots trained with AMS can adapt to new situations faster and perform tasks with more human-like coordination.
Moreover, AMS bridges a key gap in robotics by unifying dynamic movement and stable control within a single system. It leverages a mix of motion capture data and simulated training scenarios to teach robots how to transition smoothly between fast actions and precise balance. This approach improves generalization, meaning robots can handle unfamiliar movements without retraining. In addition, AMS supports real-time interaction and teleoperation, allowing human input to guide robot behavior when needed. Overall, it plays a critical role in building versatile humanoids that can operate reliably across industrial, service, and everyday environments.
New! 2026 Humanoid
Robot Market Report
198 pages of exclusive insight from global robotics experts — uncover funding trends, technology challenges, leading manufacturers, supply chain shifts, and surveys and forecasts on future humanoid applications.
now Google DeepMind
Contact Humanoid.guide
Website: https://www.kinetixai.tech/en/research/AMS
