TAMS: Task-Aware Multi-View Adaptive Streaming for Wireless Telerobotic Manipulation
2026-08-10 • Robotics
RoboticsMultimedia
AI summaryⓘ
The authors developed a system called TAMS that helps improve video feedback during remote robot control when internet speed is limited. TAMS smartly adjusts video quality based on what part of the task the robot is doing, focusing more on the most important camera view for the operator. Tests showed that TAMS helps operators finish tasks faster and with fewer errors compared to just splitting video quality evenly. This works even when the network connection is very slow.
telerobotic manipulationmulti-view videobitrate allocation6-DoF teleoperationStructural Similarity Index (SSIM)adaptive streamingtask phase inferencebandwidth constraints
Authors
Zexin Deng, Zhenhui Yuan, Lu Tian, Subhash Lakshminarayana, Longhao Zou
Abstract
Wireless telerobotic manipulation relies on timely multi-view video feedback, but the available uplink bandwidth is often limited and dynamic. This paper presents Task-Aware Multi-View Adaptive Streaming (TAMS), a system that allocates video bitrate according to the current manipulation phase. TAMS infers task phase from lightweight robot-side signals and prioritizes the camera view most relevant to the operator while preserving baseline visibility for secondary views. Experiments on a six-degree-of-freedom (6-DoF) teleoperation testbed under three constrained network conditions show that TAMS improves primary view Structural Similarity Index (SSIM), reduces task completion time, and increases trial success rate compared with equal and static allocation baselines. Under the most constrained bandwidth condition, TAMS reduces mean completion time from 68.9 s to 43.9 s relative to equal allocation and increases trial success rate from 48% to 71%. Code is available at: https://github.com/Dzxx623/TAMS.