CES 2025: AI Takes the Wheel, Tencent RTC Steers Towards Safer Autonomous Driving

The Consumer Electronics Show (CES) 2025 showcased a future brimming with AI integration, with autonomous driving technology taking center stage. NVIDIA CEO Jensen Huang declared the arrival of the "physical AI" era, where AI can not only perceive but also "proceed, reason, plan and act." This evolution was evident in NVIDIA's announcements, particularly their advancements in autonomous vehicle technology.

Huang emphasized the pivotal role of their DRIVE Hyperion platform, powered by the new NVIDIA AGX Thor system-on-a-chip (SoC). This platform, already embraced by industry giants like Mercedes-Benz and Volvo Cars, facilitates advanced functional safety and autonomous driving capabilities.

However, the road to fully autonomous driving is paved with challenges, and ensuring safety remains paramount. This is where Tencent RTC steps in, offering a robust solution for remote safety operation of autonomous vehicles.

Bridging the Gap: Remote Safety Operation for Autonomous Vehicles

While autonomous driving technology continues to advance, equipping operational autonomous vehicles (Robotaxis) with remote safety operators provides an additional layer of security. When a self-driving system encounters a complex situation, the vehicle can slow down and transfer control to a remote operator. This operator can then guide the vehicle through the challenging scenario at low speeds.

The success of this approach hinges on a stable, low-latency video feed between the vehicle and the remote operator. Any delay in this connection could have dangerous consequences. This is where Tencent RTC Teleoperation Solution shines.

Tencent RTC: Delivering Seamless Remote Control for Safer Autonomous Driving

Built on Tencent Cloud's real-time audio and video technology, the Tencent RTC Teleoperation Solution leverages decades of expertise honed through products like Tencent Meeting and WeChat Channels. This solution prioritizes the real-time performance and stability crucial for Robotaxi commercialization scenarios.

Here's how Tencent RTC addresses the critical needs of remote safety operation:

• Ultra-Low Latency: Guarantees end-to-end video latency of just 200ms, enabling near-instantaneous decision-making for remote safety operators.
• Exceptional Stability: Achieves a video freeze rate of less than 0.1% within 150ms, virtually eliminating disruptive stuttering.
• Consistent Performance: Maintains a 99th percentile video delay of under 200ms, even in challenging conditions with signal blind spots and low bandwidth.
• Safety Focused: Provides a stable and clear view of the vehicle's surroundings, accelerating the safe commercialization of autonomous driving technology.

End-to-End Optimization: The Key to Ultra-Low Latency

Tencent RTC achieves ultra-low latency through meticulous end-to-end optimization across camera capture, encoding, transmission, decoding, and rendering. By leveraging the industry-leading NVIDIA autonomous driving chip platform, the solution optimizes the entire sending pipeline for minimal latency.

Accelerated Capture, Image Transformation, and Encoding

Leveraging the industry-leading NVIDIA autonomous driving chip platform, Tencent Cloud's remote control solution optimizes the entire sending pipeline for minimal latency. Data processing occurs entirely within the chip's memory, bypassing the CPU memory.

1.Camera Capture: We utilize DMA instead of the common MMAP method for camera data acquisition, eliminating one CPU copy and directly transferring data to the chip's physical memory via handles.

2.Image Transformation and Encoding: The encoder's input queue is repurposed as a processing buffer, enabling a cyclical approach for image transformation and encoding while preventing blocking delays.

3.Encoded Output: Encoded data is exported to CPU memory via MMAP, ensuring data within the pre-encoding stage remains off the CPU memory, reducing both latency and CPU usage.

Overcoming Network Challenges for Uninterrupted Control

Complex road environments and network fluctuations can disrupt video quality, hindering remote operation. Tencent RTC tackles this challenge with multi-video stream QoS priority scheduling and dynamic real-time super-resolution. This ensures smooth, high-quality transmission of primary video streams even in low-bandwidth conditions.

Furthermore, the solution employs multi-path network transmission, simultaneously streaming video across different carrier networks. This enables real-time network switching in low-bandwidth scenarios, guaranteeing uninterrupted video transmission.

Tencent RTC: Paving the Way for a Safer Autonomous Future

As the autonomous driving revolution unfolds, safety remains paramount. Tencent RTC Teleoperation Solution provides a reliable and robust solution for remote safety operation, bridging the gap between cutting-edge technology and real-world implementation. By ensuring seamless, low-latency video communication between autonomous vehicles and remote operators, Tencent RTC is helping to steer the future of autonomous driving towards a safer and more reliable reality.