Partnerships
Disney Introduces Autonomous Star Wars Audio-Animatronics With AWS

Key PointsDisney's Anzellans choose among pre-recorded lines rather than generating dialogue live.
View more
- Disney's Anzellans choose among pre-recorded lines rather than generating dialogue live.
- The prototype extends AWS's Disney role from streaming infrastructure to real-time physical character intelligence.
- Unlike Disney's puppeteered BDX droids the Anzellans respond autonomously without any human control.
Disney Experiences announced on November 18, 2026 that Walt Disney Imagineering R&D and AWS have built a three-character Star Wars Audio-Animatronics prototype that selects dialogue and movements in real time. The Anzellans—Vilo Vele, Kado Bre’a and Jibu Bre’a—are designed to operate without a puppeteer or a fixed performance loop.
The characters belong to an alien species from the Star Wars galaxy. Disney says they perceive guest activity in real time, respond to actions such as waving or speaking, and react to one another as well as to visitors. They are scheduled to appear at the Customer Showcase at Caesars Forum during AWS re:Invent in Las Vegas, which runs November 30–December 4, 2026.
Pre-Recorded Dialogue, Real-Time Decisions
AWS technology powers each character’s real-time intelligence. Fast-decision models handle quick reactions, while larger models assess the broader situation. The system intelligently selects pre-recorded audio and plays it with dynamic animations, so the characters choose among recorded lines rather than generating dialogue live. Disney says each component is optimized for latency to support the characters’ real-time responses.
Imagineers wrote and designed the dialogue and personality quirks, and AWS supplies the real-time decisions that bring those choices into an encounter. Samira Panah Bakhtiar, AWS general manager for Telco, Media & Entertainment, Games, Advertising and Sports, described the prototype as physical AI, with the characters perceiving their environment, reasoning about events and responding dynamically.
AWS Collaboration Extends Beyond Disney+
AWS already serves as a public-cloud infrastructure provider for Disney+. The Anzellans extend that relationship beyond streaming infrastructure, using AWS’s cloud and AI capabilities for the real-time intelligence of physical characters that guests can meet.
Earlier Autonomous Characters and the BDX Contrast
Disney has explored autonomous characters before. In Walt Disney Imagineering’s autonomous-characters overview, the company says its Vyloo figures used algorithms and simple sensors to determine behaviors such as eye contact, head movement and sleep, with animation blending, computer vision and AI supporting interactions in the queue for Guardians of the Galaxy – Mission: Breakout! at Disney California Adventure. Its Automatronics project explored free-roaming characters that could detect their surroundings and decide where to go and how to interact; a prototype named Jake was tested in Tomorrowland at Disneyland Park.
Disney’s April 3, 2025 account of its BDX droids provides a closer comparison. Those free-roaming robots learned movement and balance through reinforcement learning in simulation and belonged to a modular Robotic Character Platform built around expressive motion and character-driven design. Kyle Laughlin, senior vice president of Walt Disney Imagineering Research & Development, said in that account that a behind-the-scenes puppeteer brought out nuances in the droids. The Anzellans instead select responses autonomously, with no one puppeteering or controlling them.
The Anzellans shift the technical task from choreographing a repeatable show to selecting an authored response under changing guest conditions. The key question for the re:Invent demonstrations is whether that autonomy can make encounters feel spontaneous while keeping the characters’ words, gestures and personalities within the boundaries Imagineers created.












