Remote driving and safety-critical teleoperation require strict Glass-to-Glass (G2G) latency guarantees. Traditional protocols (like standard WebRTC) are limited by a physical latency floor (acquisition + encoding + network + decoding). Our research introduces Extrapolation-based Latency Control (ELC), a novel framework that combines adaptive video rate control (VP9/WebRTC) at the transmitter with neural video frame extrapolation at the receiver to actively compensate for network delays and achieve sub-physical apparent latency.

To demonstrate the advantages of proactive latency control, the ELC architecture must be rigorously compared against state-of-the-art reactive streaming protocols (standard WebRTC with Google Congestion Control - GCC) over realistic cellular traces (4G/5G/LTE).

Main Objectives:

1. Baseline Calibration & Profiling: Configure, run, and profile the reactive baselines inside our Discrete-Event Simulator (des_engine.py), specifically testing Standard WebRTC (GCC/TWCC) and Heuristic One-Step-Ahead Rate Control under sudden bandwidth drops and real LTE/5G traces.

2. Queue & Delay Analysis: Analyze transport feedback logs, sender queue buildup, frame dropping rates, and Glass-to-Glass delay spikes when strict latency deadlines (e.g., 0 ms, 25 ms, 50 ms) are enforced.

3. Visual Demonstrator: Enhance an offline HTML5/JS side-by-side video demonstrator to visually compare video freezes/stuttering in standard WebRTC against smooth neural extrapolation in ELC.