PACE: Temporal-Role Tactile Conditioning for Chunk-Based Insertion Policies

Zhiyuan Chen; Shixiong Xu; Shuai Chen; Yangwei You

cs.ROOct 12, 2026

PACE: Temporal-Role Tactile Conditioning for Chunk-Based Insertion Policies

Authors: Zhiyuan Chen, Shixiong Xu, Shuai Chen, Yangwei You

Organizations: Beijing Xiaomi Robot Technology Co., Ltd.

Abstract

Contact-rich insertion requires robots to combine visual alignment with tactile adjustment. However, existing visuotactile chunk-based policies collapse tactile feedback into a single generation-time fusion pathway, leaving persistent contact states, abrupt contact events, and future contact consequences implicitly modeled in a single representation. We present PACE (Phase-Aware Contact-Event Conditioning), a temporal-role tactile conditioning framework for chunk-based insertion policies. PACE organizes a shared tactile stream into three temporal roles: persistent contact states condition action-chunk generation, abrupt contact events correct the generated chunk, and contact-consequence prediction shapes action representations during training. This design preserves chunk-level action continuity while assigning distinct pathways to different temporal roles of contact feedback. Across five real-robot insertion tasks, PACE achieves an average success rate of 90.7%, outperforming vision-only and generation-time tactile-fusion baselines by over 44 percentage points; on the ManipulationNet benchmark, PACE maintains 88.7% success across six geometry-clearance configurations, including an industrial-grade 0.1-mm clearance. Ablations confirm the complementary contributions of the three temporal roles, mechanistic analyses show that PACE separates normal insertion progress from contact events requiring immediate correction, and cross-signal and cross-architecture experiments indicate that this temporal-role principle extends across different physical feedback signals and policy backbones. Videos and materials are available at https://pace-insertion.github.io/.

Figures & tables

Figure 1: PACE. A temporal-role tactile conditioning framework that organizes one tactile stream into three roles: contact state conditions generation via affine modulation, contact events correct the chunk via gated residual, and contact-consequence prediction shapes representations during training.

Figure 2: Overview of PACE. Multimodal observations enter specialized encoders; a shared tactile bus feeds three temporal-role pathways. Phase: smoothed contact state modulates Transformer encoder features via layer-wise affine conditioning (generation-time). Pred.: decoder representations are supervised to predict future contact changes (training only). Event: contact-event cues produce a gated residual that corrects the generated action chunk (post-generation). The backbone is an ACT-style CVAE-Transformer.

Figure 3: Experimental setup. Left: force-feedback teleoperation system (Force Dimension sigma.7 leader, robot follower). Right: five real insertion tasks and the ManipulationNet benchmark.

Method	Key	2-pin	3-pin	USB	Ethernet	Avg.
Vision-only ACT	4/30	4/30	2/30	1/30	4/30	10.0%
Vision-only DP	5/30	6/30	4/30	3/30	5/30	15.3%
$\pi_{0}$	6/30	8/30	4/30	4/30	6/30	18.7%
ACT + Tactile Cross-Attn	10/30	15/30	11/30	9/30	14/30	39.3%
ACT + Tactile Concat	13/30	17/30	12/30	13/30	14/30	46.0%
PACE	27/30	29/30	28/30	27/30	25/30	90.7%

Table 1(a): Quantitative comparison on real insertion tasks.

Peg	3 mm	1 mm	0.1 mm
Cyl.	25/25	22/25	21/25
Hex.	24/25	22/25	19/25

Table 1(b): ManipulationNet peg-in-hole results.

Method	Key	2-pin	3-pin	USB	Eth.	Avg.
PACE w/o Pred.	25/30	27/30	26/30	26/30	24/30	85.3%
PACE w/o Phase	24/30	26/30	21/30	23/30	24/30	78.7%
PACE w/o Event	20/30	22/30	18/30	19/30	21/30	66.7%
Phase-only	17/30	20/30	16/30	18/30	19/30	60.0%
PACE	27/30	29/30	28/30	27/30	25/30	90.7%

Table 2: Ablation study on PACE design choices.

Figure 4: Mechanistic visualization of PACE’s temporal-role separation during insertion. Top: calibrated end-effector contact force (N). Middle: Phase pathway output, visualized as the second principal component of the feature-wise affine modulation parameters ( $\gamma,\beta$ ) (a.u.). Bottom: Event pathway output, shown as the gate-weighted residual correction level relative to its pre-contact resting level (a.u.). Phase exhibits sustained shifts across different contact phases, whereas Event shows sharp excursions around collision events and does not simply increase with the sustained high force of stable insertion.

Signal	Dim.	2-pin	Key	Avg.
Tactile (default)	6	29/30	27/30	93.3%
F/T	6	27/30	27/30	90.0%
Joint current	7	28/30	25/30	88.3%

Table 3: Alternative physical feedback signals.

Backbone	2-pin	Key	Avg.
Vision-only DP	6/30	5/30	18.3%
DP + PACE	28/30	25/30	88.3%

Table 4: Cross-architecture validation.

Appendix figures & tables17 assets

Supplementary material from the paper’s appendix.

Appendix

Parameter	Value
Transformer encoder layers	4
Transformer decoder layers	7
Hidden dimension $d_{\text{model}}$	512
Attention heads	8
Feed-forward dimension	3200
CVAE latent dimension	32

Appendix

Table A1: ACT backbone hyperparameters.

Component	Input	Hidden layers	Output	Final activation
$\phi_{\text{gate}}$	$\mathbf{e}_{t}\in\mathbb{R}^{D_{w}+1}$	64, 64	$D_{a}$	sigmoid
$\phi_{\text{res}}$	$\text{flatten}(\mathbf{W}_{t})\in\mathbb{R}^{T_{w}\times D_{w}}$	128, 128	$h_{\text{corr}}\times D_{a}$	-

Appendix

Table A2: Event correction module parameterization.

Component	Input	Hidden layers	Output
$\phi_{\text{pred}}$	$\mathbf{z}_{s}\in\mathbb{R}^{d_{\text{model}}}$	512 (ReLU)	$D_{w}$

Appendix

Table A3: Contact-consequence prediction head parameterization.

Component	Additional Parameters
$\phi_{\text{phase}}$ (condition encoder + modulator)	0.546 M
$\phi_{\text{gate}}$	0.005 M
$\phi_{\text{res}}$	0.024 M
$\phi_{\text{pred}}$ (training only)	0.266 M
PACE total	0.841 M

Appendix

Table A4: Additional parameter count of PACE modules.

Parameter	Value
Optimizer	AdamW
Learning rate	$1\times 10^{-5}$
Batch size	32
Training epochs	10000
Chunk size $H$	20
KL weight $\lambda_{\text{kl}}$	10

Appendix

Table C1: Training hyperparameters.

Task	Best epoch
Key	7456
2-pin	7102
3-pin	8126
USB	8003
Ethernet	7914
Cyl-3mm	7571

Appendix

Table C2: Selected checkpoints by task.

Item	Value
Demonstrations per task	~160 episodes
Episode length	~300 steps
RGB image resolution	200 $\times$ 266
Tactile sensor resolution (Vitai GF225)	240 $\times$ 240
Action space	7-DoF joint position

Appendix

Table C3: Dataset and observation statistics.

	Temporal Ensemble	Event correction
Operates on	Predictions from multiple overlapping action chunks at the same time step	Generated action chunk
Mechanism	Fixed exponential weighted averaging	Learned gated residual from latest tactile history
Signal driven	No	Yes, tactile differential
Contact-aware	No	Yes

Appendix

Table D1: Comparison between temporal ensemble and Event correction.

Method	Chunk	Key	2-pin	3-pin	USB	Eth.	Avg.
Phase-only	20	17/30	20/30	16/30	18/30	19/30	60.0%
Phase-only (chunk=10)	10	14/30	17/30	13/30	15/30	15/30	49.3%
PACE	20	27/30	29/30	28/30	27/30	25/30	90.7%

Appendix

Table D2: Short-chunk control on real insertion tasks.

Method	2-pin	Key
RDP	19/30	12/30
PACE	29/30	27/30

Appendix

Table D3: Comparison with RDP on two real insertion tasks (successes/30).

Task	PACE	ACT + Tactile Concat
Key	27/30 [0.74, 0.97]	13/30 [0.27, 0.61]
2-pin	29/30 [0.83, 0.99]	17/30 [0.39, 0.73]
3-pin	28/30 [0.79, 0.98]	12/30 [0.25, 0.58]
USB	27/30 [0.74, 0.97]	13/30 [0.27, 0.61]
Ethernet	25/30 [0.66, 0.93]	14/30 [0.30, 0.64]

Appendix

Table D4: Real-robot successes and Wilson 95% confidence intervals.

Method	3 mm	1 mm	0.1 mm
Vision-only ACT	30%	10%	0%
Vision-only DP	10%	0%	0%
PACE	98%	88%	80%

Appendix

Table D5: Baseline success rates on ManipulationNet, averaged over cylindrical and hexagonal pegs. Each geometry-clearance configuration uses 25 rollouts.

Policy	Feedback on	Feedback off
PACE	29/30	21/30
ACT + Tactile Concat	17/30	7/30

Appendix

Table D6: Policy success under force-feedback collection conditions (2-pin; 30 rollouts per method).

Metric	FF on	FF off	Rel. change	$p$ -value / $d$
Force variance (N 2 )	4.8	12.7	$-62\%$	$p<10^{-13}$ , $d{=}0.80$
Inter-trajectory deviation (N)	1.07	1.92	$-44\%$	$p<10^{-4}$ , $d{=}0.55$
Pairwise force-curve correlation	0.67	0.54	$+24\%$	—
Peak contact force (N)	$10.0\pm 2.2$	$16.7\pm 7.1$	$-40\%$	$p<10^{-24}$ , $d{=}1.28$
Episode length CV	0.108	0.132	$-18\%$	—

Appendix

Table D7: Demonstration quality metrics (2-pin, 162 episodes per condition). Relative change is reported as FF-on vs. FF-off; where tested, differences are statistically significant (Mann-Whitney U test).

Panel of Figure 24 — Figure D1: Full demonstration quality comparison (2-pin, 162 episodes). (a–b) Force curve overlays. (c) Per-episode variance distribution. (d) Inter-trajectory standard deviation over normalized time. (e) Peak force distribution. Force-feedback demonstrations exhibit consistently lower variance, tighter trajectory bundles, and more predictable peak forces.

Figure E1: Representative failure case on USB insertion. The policy produces multiple correction attempts that move toward the target, but coupled lift–translation and insufficient retreat shift the contact point, accumulate object tilt, and lead to terminal jamming.

Component	Additional Params	Inference Latency
ACT backbone	83.87 M	6.2 ms
Contact-state conditioning	0.546 M	< 0.1 ms
Event gate	0.005 M	< 0.1 ms
Event residual corrector	0.024 M	< 0.1 ms
Prediction head	0.266 M	0 ms at inference
PACE training-time total	0.841 M	—

Appendix

Table F1: Computational overhead of PACE modules.

Explore similar work

ContactDP: Contact-Guided Diffusion Policy for Tight Insertion Tasks
Sep 20, 2026Chengyi Xing, Shaoxiong Yao, Diego Romeres +1Contact-Rich Robotic Manipulation Diffusion Policy
Mitsubishi Electric Research Labs, Cambridge, MA, US
InsertAnything: Generalizable Contact-Rich Precision Insertion from Simulation to Reality
Sep 21, 2026Zhenghua Ma, Xinpan Meng, Zeyu Liu +4RL for Robotics Contact-Rich Robotic Manipulation
School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing 100049, China, and the State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China · PaXini AI Technology (Beijing) Co., Ltd., Beijing 100080, China
TacZero: Training-Free Peg Insertion Using a General-Purpose Vision-Language Model with Tactile Feedback
Oct 6, 2026Kazutoshi TanakaZero-Shot Robotic Manipulation Contact-Rich Robotic Manipulation
OMRON SINIC X Corporation, Bunkyo-ku, Tokyo 113-0033, Japan

Sep 20, 2026J/K move · Enter open · S save

ContactDP: Contact-Guided Diffusion Policy for Tight Insertion Tasks

Chengyi Xing, Shaoxiong Yao, Diego Romeres, Devesh K. Jha

Mitsubishi Electric Research Labs, Cambridge, MA, US

Contact-Rich Robotic Manipulation Diffusion Policy Robotic Insertion Force-Controlled Robotic Manipulation

Open paper AskPDF arXiv

High-precision connector insertion remains challenging for robotic systems due to tight mechanical tolerances, partial observability during contact, and multimodal uncertainty arising from occlusion and contact ambiguity. Successful insertion requires closed-loop contact guidance that continuously integrates global alignment cues with local contact feedback to produce stable corrective actions under interaction. In this work, we present ContactDP (Contact-Guided Diffusion Policy for Tight Insertion Tasks), a multimodal diffusion-policy framework for contact-rich insertion. ContactDP jointly integrates wrist RGB observations, fingertip tactile sensing, and wrist-mounted force-torque measurements to infer contact state and generate temporally consistent corrective motions during insertion. To ensure stable execution under contact, the learned policy operates together with a hybrid position-force controller that provides compliant low-level interaction. We evaluate our approach on a suite of industrial-grade connector insertion tasks with varying connector geometries, grasp conditions, and initial misalignment. Across all tasks, ContactDP significantly outperforms vision-only diffusion policies for performance, reliability and generalization.

Abstract

Explore similar work

ContactDP: Contact-Guided Diffusion Policy for Tight Insertion Tasks

InsertAnything: Generalizable Contact-Rich Precision Insertion from Simulation to Reality

TacZero: Training-Free Peg Insertion Using a General-Purpose Vision-Language Model with Tactile Feedback