ExtremControl: Low-Latency Humanoid Teleoperation with Scaled Velocity Feedforward
ExtremControl: Low-Latency Humanoid Teleoperation with Scaled Velocity Feedforward
This research proposes ExtremControl, a low-latency whole-body control framework for humanoid robots that reduces tracking delay by approximately 70ms through scaled velocity feedforward. The system achieves end-to-end latency as low as 50ms, enabling new reactive behaviors like ping-pong ball balancing and juggling.
This paper introduces ExtremControl, a low-latency whole-body control framework for humanoid robots that reduces tracking delay by approximately 70ms through scaled velocity feedforward. The system achieves end-to-end latency as low as 50ms, enabling new reactive behaviors like ping-pong ball balancing and juggling.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
Reported numbers
end-to-end latency
50
View original evidence
or locomotion setting through experiments in both simulation and the real world. Building on ExtremControl, we implement a teleoperation system supporting both optical motion capture and VR-based tracking, achieving end-to-end latency as low as 50ms --- well beneath the threshold at which system delay adds a full human reaction cycle to the control loop. This enables a qualitatively new class of reactive behaviors, i
Open source S5end-to-end latency
≈200
View original evidence
arXiv:2602.11321v4 Announce Type: replace Abstract: Building a low-latency humanoid teleoperation system is essential for collecting diverse reactive and dynamic demonstrations. However, end-to-end latencies in existing approaches consistently hover around 200ms, roughly equal to human reaction time, that severely limits responsiveness and prevents tasks requiring rapid feedback. We identify position-only PD control
Open source S2tracking delay reduction
≈70
View original evidence
as the root cause of this latency floor and propose ExtremControl, a low-latency whole-body control framework that: (1) incorporates scaled velocity feedforward in low-level control, reducing tracking delay by approximately 70ms with a provably optimal feedforward ratio; (2) operates directly on SE(3) poses of selected rigid links, primarily humanoid extremities, to avoid joint-space retargeting in the control loop.
Open source S3human reaction time
≈200
View original evidence
arXiv:2602.11321v4 Announce Type: replace Abstract: Building a low-latency humanoid teleoperation system is essential for collecting diverse reactive and dynamic demonstrations. However, end-to-end latencies in existing approaches consistently hover around 200ms, roughly equal to human reaction time, that severely limits responsiveness and prevents tasks requiring rapid feedback. We identify position-only PD control
Open source S2teleoperation system latency
50
View original evidence
or locomotion setting through experiments in both simulation and the real world. Building on ExtremControl, we implement a teleoperation system supporting both optical motion capture and VR-based tracking, achieving end-to-end latency as low as 50ms --- well beneath the threshold at which system delay adds a full human reaction cycle to the control loop. This enables a qualitatively new class of reactive behaviors, i
Open source S5
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
or locomotion setting through experiments in both simulation and the real world. Building on ExtremControl, we implement a teleoperation system supporting both optical motion capture and VR-based tracking, achieving end-to-end latency as low as 50ms --- well beneath the threshold at which system delay adds a full human reaction cycle to the control loop. This enables a qualitatively new class of reactive behaviors, i
Open source S5
arXiv:2602.11321v4 Announce Type: replace Abstract: Building a low-latency humanoid teleoperation system is essential for collecting diverse reactive and dynamic demonstrations. However, end-to-end latencies in existing approaches consistently hover around 200ms, roughly equal to human reaction time, that severely limits responsiveness and prevents tasks requiring rapid feedback. We identify position-only PD control
Open source S2
as the root cause of this latency floor and propose ExtremControl, a low-latency whole-body control framework that: (1) incorporates scaled velocity feedforward in low-level control, reducing tracking delay by approximately 70ms with a provably optimal feedforward ratio; (2) operates directly on SE(3) poses of selected rigid links, primarily humanoid extremities, to avoid joint-space retargeting in the control loop.
Open source S3
To minimize retargeting time, we derive a closed-form Cartesian-space mapping that uses a single anthropomorphic calibration step to translate human motion into humanoid link targets, accommodating operators with varying body proportions. Furthermore, we provide a theoretical framework for selecting control hyperparameters, and validate the effectiveness of velocity feedforward control in the reinforcement learning f
Open source S4
ncluding ping-pong ball balancing, juggling, and real-time return, that are beyond the capability of existing teleoperation systems.
Open source S6
Source：arXiv Robotics — research abstracts · arxiv.org