Contact-rich manipulation requires not only vision-dominant task semantics but also closed-loop reactions to force/torque (F/T) transients. Yet, generative visuomotor policies are typically constrained to low-frequency updates due to inference latency and action chunking, underutilizing F/T for control-rate feedback. Furthermore, existing force-aware methods often inject force continuously and indiscriminately, lacking an explicit mechanism to schedule when / how much / where to apply force across different task phases. We propose PhaForce, a phase-scheduled visual--force policy that coordinates low-rate chunk-level planning and high-rate residual correction via a unified contact/phase schedule. PhaForce comprises (i) a contact-aware phase predictor (CAP) that estimates contact probability and phase belief, (ii) a Slow diffusion planner that performs dual-gated visual--force fusion with orthogonal residual injection to preserve vision semantics while conditioning on force, and (iii) a Fast corrector that applies control-rate phase-routed residuals in interpretable corrective subspaces for within-chunk micro-adjustments. Across multiple real-robot contact-rich tasks, PhaForce achieves an average success rate of 86% (+40 pp over baselines), while also substantially improving contact quality by regulating interaction forces and exhibiting robust adaptability to OOD geometric shifts.
Figures & tables
Fig. 1: Comparison of three force-aware policy architectures. Prior works fuse vision and force into a single generative policy, while RDP adopts a slow–fast decomposition without explicit phase scheduling. PhaForce introduces an explicit contact/phase schedule to coordinate force usage for both chunk-level planning (Slow) and within-chunk correction (Fast).
Fig. 2: PhaForce Architecture. The Slow diffusion planner runs at fs=6 Hz to generate action chunks, while CAP and the Fast corrector run at the control rate fc=24 Hz for contact/phase prediction and within-chunk closed-loop correction. In Slow , dual-gated vision–force fusion with orthogonal residual injection preserves vision-dominant task semantics. In Fast , phase-belief soft routing activates corrective subspaces and outputs a residual correction that is composed with the Slow base action to obtain the executed command.
subspace
search
insert
unlock
pull
wiping
x
✓
✓
✓
y
✓
✓
✓
z
✓
✓
roll
✓
pitch
✓
yaw
✓
✓
TABLE I: Corrective subspaces for force-critical phases across tasks
Fig. 3: We design five contact-rich tasks; each task exhibits varying contact states and phase belief , and each phase activates different corrective subspaces. Each row illustrates the phase transitions in a task. PhaForce not only excels on in-distribution tasks but also remains stable under OOD shifts.
Method
Charger
USB
Drawer
Wipe-ID
Wipe-OOD
Avg
DP
20
15
60
95
0
38
DP (force-concat)
20
20
50
85
0
35
RDP
50
55
65
85
75
66
PhaForce (ours)
80
85
85
95
85
86
TABLE II: Success rate (SR, %) across different policies.
Fig. 4: Three common baseline failure modes in plug-in tasks.
Fig. 5: We visualize the contact probability, phase belief, and z -axis force Fz in a USB Plug-in task (curves are smoothed for visualization).
Contact-rich manipulation demands human-like integration of perception and force feedback: vision should guide task progress, while high-frequency interaction control must stabilize contact under uncertainty. Existing learning-based policies often entangle these roles in a monolithic network, trading off global generalization against stable local refinement, while control-centric approaches typically assume a known task structure or learn only controller parameters rather than the structure itself. In this paper, we formalize a physically grounded interaction frame, an instantaneous local basis that decouples force regulation from motion execution, and propose a method to recover it from demonstrations. Based on this, we address both issues by proposing Force Policy, a global-local vision-force policy in which a global policy guides free-space actions using vision, and upon contact, a high-frequency local policy with force feedback estimates the interaction frame and executes hybrid force-position control for stable interaction. Real-world experiments across diverse contact-rich tasks show consistent gains over strong baselines, with more robust contact establishment, more accurate force regulation, and reliable generalization to novel objects with varied geometries and physical properties, ultimately improving both contact stability and execution quality. Project page: https://force-policy.github.io/
Hongjie Fang, Shirun Tang, Mingyu Mei +9
Noematrix · Shanghai Jiao Tong University · Zhejiang University +2
Force-aware Vision-Language-Action (VLA) policies improve contact-rich manipulation, but typically combine task-level motion and contact-dependent adjustment in a single action prediction. Demonstrations provide no explicit labels for decomposing that prediction into a reusable reference action and a correction. We present ForceDelta-VLA, a correction-distillation framework that constructs an explicit force-correction target using paired predictions from a frozen teacher's force-conditioned and learned force-agnostic modes. A separate delay-correction target accounts for reference-action mismatch and the change in reference state. Training uses asynchronous schedule replay with the cached task context available during execution. The resulting lightweight policy adjusts the reference actions using recent force history and robot state, responding to contact changes between reference-action updates without regenerating complete action chunks. Across nine single-arm and bimanual contact-rich tasks, ForceDelta-VLA achieves an 82.2% mean success rate, compared with 54.4% for the original ForceVLA baseline. Direct execution of our Stage-1 Temporal Teacher achieves 70.6%. Relative to ForceVLA, the complete system reduces mean peak contact force over successful trials by approximately 26% on both platforms.
Ju Dong, Yu Fu, Jian Chen +9
TAMS (Technical Aspects of Multimodal Systems), Department of Informatics, University of Hamburg, Hamburg, Germany. · University of Science and Technology of China, Hefei, China. · Technical University of Munich, Germany.
Vision-Language-Action (VLA) models have demonstrated strong performance across diverse robotic manipulation tasks, yet their predominantly vision-centric perception and position-controlled execution remain insufficient for contact-rich manipulation. Visual observations alone often provide limited evidence of contact onset and interaction magnitude, while position-control policies cannot respond compliantly to rapidly changing contact dynamics. To bridge both the perception and control gaps, we propose TAO-Force, a force-conditioned VLA framework that combines force-aware policy learning with contact-regulated execution. For force-aware perception, TAO-Force introduces Force-conditioned Feature-wise Linear Modulation (F-FiLM) to inject encoded force feedback into the representations of a frozen pretrained visual-language backbone while preserving its semantic priors. For responsive control, it employs a contact-gated fast-slow architecture, with a slow position-control branch tracking nominal trajectories during non-contact phases and a fast admittance-control branch regulating physical interaction during contact phases. Detailed analyses on a force-perception task and real-world evaluations across four contact-rich manipulation tasks validate the effectiveness and robustness of TAO-Force.
Bohan Gan, Xuanzhang Wen, Yongsheng Zhao +8
China Mobile (Hangzhou) Information Technology Co., Ltd., Hangzhou 310023, China