FlowVLA: Learning Flow-Aware Physical Completion for Quantitative Robotic Pouring

Liwen Yang; Yutian Zhang; Jiaqi Zhai; Li Yang; Tutian Tang; Qiwei Shan; Yancheng Bi; Qiankuan Shangguan

cs.ROOct 21, 2026

FlowVLA: Learning Flow-Aware Physical Completion for Quantitative Robotic Pouring

Authors: Liwen Yang, Yutian Zhang, Jiaqi Zhai, Li Yang, Tutian Tang, Qiwei Shan, Yancheng Bi, Qiankuan Shangguan,

Organizations: Zhejiang University · DEEP Robotics · Shanghai Artificial Intelligence Laboratory · Northeastern University, China ·

Abstract

During steady pouring, images and robot pose may remain nearly unchanged while transferred mass accumulates, making the return decision ambiguous for a whole-task vision-language-action (VLA) policy. We present FlowVLA, which separates motor generation from physical-completion estimation. A shared $π_{0.5}$ action expert learns approach, pour, and return with boundary-aware supervision. A target-independent estimator fuses visual, joint, wrist-wrench, and recurrent force-belief histories to maintain an estimate of transferred mass. The controller initiates return when this estimate plus predicted residual outflow reaches the requested mass. In coffee-pot/water experiments, FlowVLA achieves 13.1 g goal-balanced mean absolute error (MacroMAE), lower than all tested VLA baselines. Across all attempts, 53.7% both complete the task and finish within +/-10% of the requested mass. The same model interpolates to held-out 150/250-g targets without retraining. Independently trained models further evaluate the formulation in three additional container-fluid settings.

Figures & tables

Fig. 1: Quantitative robotic pouring task. The robot performs grasping, pouring, return, and placement while targeting a requested transferred mass without online scale feedback.

Fig. 2: The architecture of FlowVLA. The action backbone fuses 30-Hz images and robot state with 500-Hz force history and a 20-Hz recurrent belief. The physical-completion module estimates transferred mass and return tail, whose sum determines when to return.

Panel of Figure 3 — Fig. 3: Left: views from head and wrist cameras during approach, grasp, steady pouring, return, and placement. Right: (a) coffee pot, (b) top-handle kettle, (c) soy-sauce dispenser, and (d) oil dispenser.

Fig. 4: Flow-labeled demonstration datasets for the four domains (1,684 episodes total). Left: episode mean flow versus duration; diamonds are task means and error bars span the central 95% episode ranges. Right: duration distributions; thick lines mark interquartile ranges.

Method	Grasp	Post-grasp success	E2E	$N_{m}$	$N_{\mathrm{mass}}$ (100/200/300)	Per-goal MAE (g)	Pooled	Macro	$\leq 10\%$	E2E+ $\pm 10\%$
Method	Grasp	Post-grasp success	E2E	$N_{m}$	$N_{\mathrm{mass}}$ (100/200/300)	100/200/300	Pooled	Macro	$\leq 10\%$	E2E+ $\pm 10\%$
Trajectory-replay controls
TR-LT-ID	100.0%	100.0%	100.0%	37	37 (12/15/10)	66.86/95.48/124.33	94.0	95.6	5.4%	5.4%
TR-LT-Cal	100.0%	100.0%	100.0%	38	38 (13/12/13)	13.40/21.17/25.04	19.8	19.9	57.9%	57.9%
External baselines
$\pi_{0.5}$	65.2%	33.3%	21.7%	45	15 (7/6/2)	69.34/54.97/75.40	64.4	66.6	13.3%	2.9%

TABLE I: Primary coffee-pot/water results at 100/200/300 g. TR-LT replays held-out paths in their original layouts; learned policies use randomized initial source positions (Sec. IV-A ).

Fig. 5: Automatic 300-g trial. (a) Predicted terminal mass using fixed and learned tails, offline electronic-scale reference, and frames at onset, mid-pour, and return. (b) Reconstructed flow and completion-head prediction. (c) Return decision.

Component	Variant	$N_{a}$	$N_{m}$	$N_{\mathrm{mass}}$ 100/200/300	Per-goal MAE (g) 100/200/300	Pooled	Bias	Macro	Grasp	Post-grasp success	E2E
Full	$\widehat{M}_{t}+\widehat{T}_{t}\geq g$	123	84	79 (28/26/25)	6.96/13.81/18.66	12.92	$+2.65$	13.15	68.3%	94.0%	64.2%
Action	No boundary-aware supervision	59	39	33 (13/11/9)	13.39/18.57/28.84	19.33	$+12.16$	20.27	66.1%	84.6%	55.9%
State	$-$ hard-zero gate	53	37	35 (12/12/11)	12.47/13.46/24.82	16.69	$-5.73$	16.92	69.8%	94.6%	66.0%
Trigger	$\widehat{M}_{t}\geq g$	61	40	39 (13/12/14)	10.18/20.11/26.89	19.24	$+6.93$	19.06	65.6%	97.5%	63.9%
	$\widehat{M}_{t}+0.2\widehat{f}_{t}\geq g$	59	40	38 (12/13/13)	7.26/13.86/26.24	16.01	$+2.74$	15.79	67.8%	95.0%	64.4%

TABLE II: System-level mechanism ablations: mass accuracy and manipulation success.

Container / fluid	Goals (g)	$N_{a}$	$N_{m}$	$N_{\mathrm{mass}}$	MAE (g)	Macro Rel.	Grasp	Post-grasp	E2E	E2E+ $\pm 10\%$
						MAE		success
Coffee pot / water	150/250	31	22	10/10	10.94/19.71	7.6%	71.0%	90.9%	64.5%	54.8%
Top-handle kettle / water	200/400	32	25	12/12	34.54/50.73	15.0%	78.1%	96.0%	75.0%	25.0%
Soy-sauce dispenser / saturated brine	100	31	18	11	9.05	9.1%	58.1%	61.1%	35.5%	25.8%
Oil dispenser / cooking oil	50/100	47	30	14/13	4.23/11.86	10.2%	63.8%	90.0%	57.4%	31.9%

TABLE III: FlowVLA on held-out targets and additional container–fluid tasks. Held-out targets use the unchanged primary model; additional tasks use independently trained domain-specific models.

Fig. 6: Median flow (lines) and central 95% episode ranges (shading), with time normalized from onset (0%) to cutoff (100%). Peak P95 is the 95th percentile of episode peak flow.

Robotic Manipulation

Robotic manipulation studies how robots perceive, plan, and control physical interactions to grasp, move, assemble, and use objects.

See all 1,671 papers

Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs
Jun 8, 2026Jonathan C. Kao, Jason Chan, Andy WangRobotic Control Vision-Language-Action Models
Departments of Electrical and Computer Engineering, Computer Science, and Neurobiology, University of California, Los Angeles · Department of Computer Science, University of California, Los Angeles
TemporalFlow-VLA: Learning Physically Grounded Execution History for Long-Horizon Robot Manipulation
Aug 27, 2026Jiarui Yang, Yehao Lu, Yuning Su +9Robot Learning Long-Horizon Robotic Manipulation
The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China. · Zhejiang University, Hangzhou, China. · Simon Fraser University, Burnaby, BC, Canada. +1
Uncertainty Quantification for Flow-Based Vision-Language-Action Models
Jun 16, 2026Ralf Römer, Maximilian Seeliger, Saida Liu +5Flow Matching Uncertainty Estimation for VLA Models
TU Munich · ETH Zurich · TU of Munich +1

Jun 8, 2026J/K move · Enter open · S save

Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs

Jonathan C. Kao, Jason Chan, Andy Wang

Departments of Electrical and Computer Engineering, Computer Science, and Neurobiology, University of California, Los Angeles · Department of Computer Science, University of California, Los Angeles

Robotic Control Vision-Language-Action Models Vision-Based Robot Control VLMs for Robotics

Open paper AskPDF arXiv

We introduce flow control of vision-language-action (VLA) models, a simple and effective way to steer VLA actions in real time through generic inputs, such as a keyboard. This method can be used out-of-the-box and does not require retraining or fine-tuning VLAs. It enables relatively crude user inputs to steer a VLA to align with user intent. Flow control writes the user input into the initial condition of the VLA's flow matching action expert. Because the flow is deterministic, integration retains information about the user input while moving it toward the action distribution learned during training, so that the generated actions reflect the user's intent (high fidelity) and stay close to the VLA's own unsteered actions (high conformity). We demonstrate that flow control has many desirable properties: (1) flow control accurately and responsively steers robot actions with user inputs, (2) it is robust to suboptimal user inputs, (3) it enables users to steer VLAs to achieve significantly higher success rates and faster task completion, and (4) fine-tuning a VLA on flow control trajectories improves the autonomous policy. Together, these results provide a simple and intuitive way for users to help steer VLA actions, increasing task performance. Project page and videos: https://jcykao.github.io/flowcontrol/.

Abstract

Robotic Manipulation

Explore similar work

Flow Control: Steering Vision-Language-Action Models with Simple Real-Time Inputs

TemporalFlow-VLA: Learning Physically Grounded Execution History for Long-Horizon Robot Manipulation

Uncertainty Quantification for Flow-Based Vision-Language-Action Models