VAMPS: Visual and Motor Policies from Sampling-Based Planning

Mohamed Yassine Kabouri; Pietro Noah Crestaz; Quang-Nam Nguyen; Qilong Cheng; Ludovic Righetti; Nicolas Mansard

cs.ROOct 4, 2026

VAMPS: Visual and Motor Policies from Sampling-Based Planning

Authors: Mohamed Yassine Kabouri, Pietro Noah Crestaz, Quang-Nam Nguyen, Qilong Cheng, Ludovic Righetti, Nicolas Mansard

Organizations: LAAS-CNRS, Université de Toulouse, CNRS, Toulouse, France. · Machines in Motion Laboratory, New York University, New York, USA. · Industrial Engineering Department, University of Trento, Trento, Italy. · Artificial and Natural Intelligence Toulouse Institute (ANITI), Toulouse.

Abstract

Learning robot policies directly on physical systems remains difficult because data collection is costly and policy exploration can be unsafe. We introduce Visual and Motor Policies from Sampling-Based Planning (VAMPS), a framework that uses Model Predictive Path Integral (MPPI) control to train reusable policies without human demonstrations. VAMPS supports two training modes. For one-step proprioceptive policies, it operates iteratively in simulation: the policy warm-starts MPPI, and the refined trajectories provide new supervision as the policy changes. A learned terminal value improves short-horizon planning, while an Implicit Q-Learning (IQL) critic guides the policy update. Iterative refinement outperforms training once on frozen MPPI data, and we transfer the learned locomotion policy to a Unitree Go2. For visuomotor policies, VAMPS operates directly from real-robot data. MPPI uses task-specific state estimates to plan and execute trajectories while recording RGB and sensor observations on a Flexiv Rizon 10S. Action Chunking with Transformers predicts action chunks, reducing the effective prediction horizon, and is trained offline on this fixed dataset. We demonstrate visuomotor pick-and-place and force-aware whiteboard erasing. In the latter task, the policy additionally observes the measured $6$ -D wrench and desired normal force. These results show that VAMPS can learn policies either in simulation followed by hardware transfer or directly from autonomously collected real-robot data.

Figures & tables

Fig. 1 : Overview of the two VAMPS modes. (a) VAMPS-Iterative: a one-step proprioceptive policy warm-starts MPPI, which refines its behavior and provides new supervision. A terminal value improves short-horizon planning, and an IQL critic weights the policy updates. (b) VAMPS-Batch: MPPI uses task-specific estimates to autonomously collect RGB, sensor and action episodes on the real robot, and ACT trains offline on the resulting fixed dataset.

Panel of Figure 2 — Fig. 2 : The hardware that we consider, four frames each in temporal order. Top: bounding policy of the Unitree Go2 under a forward velocity command, with a proprioceptive policy trained in simulation. Middle: pick-and-place on the Flexiv Rizon 10S. Bottom: whiteboard erasing on the same arm. The two arm tasks are visuomotor and are learned directly from hardware data. Videos are provided in the supplementary video.

Panel of Figure 3 — Fig. 3 : The three VAMPS-Iterative coupling strategies. Each task shows a Gaussian policy and a deterministic policy. Shaded bands: 95 % CI over 4 seeds.

Fig. 4 : Left: median primal residual over four seeds: BC already follows the planner to $0.24$ with no consensus enforced. Right: 95th percentile of $|y_{t,j}^{(i)}|$ over states and action coordinates, on one Go2 seed. Colorbar in action units; $1$ is the bound of $\pi_{\theta}$ .

Fig. 5 : Test return on Panda pick-and-place. Left: planning horizons

T\in\{16,8,4\}

with and without the learned terminal value (TV). Right: VAMPS-Iterative without a critic and with the critic for different AWR temperatures

\beta

; both retain the terminal value. Shaded bands: 95 % CI across seeds.

Fig. 6 : Sensitivity to the hyperparameters. Left: penalty coefficient

\rho

, with the batch size fixed at

1024

. Right: batch size, with

\rho

fixed at

0.005

. Shaded bands: 95 % CI over 4 seeds.

Method	Episode length	Return	Success
PPO	$80$	$279\pm 84$	$0.00$
PPO	$500$	$975\pm 10$	$\textbf{0.98}\pm\textbf{0.03}$
PPO	$1000$	$894\pm 163$	$0.74\pm 0.49$
BC (frozen)	–	$290\pm 85$	$0.02\pm 0.03$
IQL (frozen)	–	$240\pm 40$	$0.01\pm 0.01$
VAMPS-Iterative	$80$	$\textbf{1109}\pm\textbf{76}$	$\textbf{0.98}\pm\textbf{0.02}$

TABLE I : Baselines on Panda: mean

\pm

95 % CI over four seeds at each method’s best checkpoint. PPO is trained at the listed episode length and evaluated over

80

steps, as VAMPS-Iterative.

Fig. 7 : Desired and measured normal force during one successful VAMPS-Batch erasing trial shown in Fig. 2 .

Explore similar work

Aug 4, 2026cs.RO

Unified Visuomotor Targets: Supervising VLAs Beyond Physical Actions

VLA models are trained to predict robot actions from visual and language observations. This is a natural choice, but it creates a mismatch: VLMs encode rich, high-level representations of scenes and goals, while robot actions are low-level signals with limited task structure. We ask whether changing what the policy is trained to predict, rather than how it is architecturally designed, can yield better and more efficiently trained policies. We propose UVT (Unified Visuomotor Target), a unified latent prediction target that jointly encodes motor control and visual scene transition information, requiring no architectural changes and no additional data. Applied to two representative VLA systems across simulation benchmarks and real bimanual manipulation tasks, UVT improves training efficiency, final task performance, and policy robustness, with particularly strong gains under limited training budgets and challenging environmental conditions. Rollout videos and additional qualitative results are available at our project webpage: https://unified-visuomotor-targets.github.io/

Zhenyang Feng, Unnat Jain

Department of Computer Science, University of California, Irvine

Visuomotor Control Latent Prediction Beyond Retrieval

Ask PDF

Sep 17, 2026cs.RO

Accelerating Visual Policy Learning with Sampling-Based Model Predictive Control

Learning visual policies for locomotion and manipulation requires coordinating contact with the environment and can incur substantial computation and GPU memory costs. First-order policy gradients (FoPG) reduce training cost through differentiable simulation, but local optimization can converge to unintended contact patterns. To address this shortfall, we propose Sampling-Guided Policy Search (SGPS), which couples recurring action-target refinement by sampling-based model-predictive control with first-order policy optimization. Behavior cloning initializes the policy from sampled actions; training then alternates sampling-based refinement with short-horizon FoPG updates under perturbed initial states and randomized dynamics. For visual policy training, we use a decoupled FoPG formulation that excludes rendering from the computation graph, enabling direct learning from depth observations without a state-policy teacher. On a single GPU, SGPS learns policies for locomotion, obstacle traversal, crate pushing, and bimanual carrying on simulated Unitree Go2 and G1 robots. Our experiments further show that refinement improves policy learning beyond initialization and tracking alone. For hardware deployment, the distilled policy transfers zero-shot to a real Go2 and uses onboard depth to autonomously trot, crawl, clear hurdles, and switch between these behaviors.

Yilang Liu, Haoxiang You, Qian Wang +2

Department of Mechanical Engineering, Yale University, New Haven, CT 06520, USA · Department of Computer Science, Yale University, New Haven, CT 06520, USA · School of Electrical and Computer Engineering, University of Sydney, Sydney, NSW 2006, Australia

Visuomotor Policy Model Predictive Control Locomotion Visual In-Context Learning Refinement

Ask PDF

Aug 10, 2026cs.RO

JEPA-WAM: Learning Vision-Language-Action Policies with Joint-Embedding World Modeling

Robust robot control benefits from explicitly modeling state transitions, but video-generation world action models (WAMs) introduce substantial deployment cost. Existing latent WAMs avoid explicit future generation, but often compress predictive representations or separate predictive modeling from the representations used for action generation. We introduce JEPA-WAM, a latent WAM built in a pretrained V-JEPA space, which couples latent transition prediction with continuous action generation through a shared predictor. JEPA-WAM predicts a spatially structured joint current-future target that captures task-shared visual temporal structure between current and future observations, while preserving dense patch-level correspondence. Through the shared predictor, transition supervision directly shapes the backbone, from which dedicated representations are extracted for action prediction. The same design can also be instantiated in pretrained VLA policies while preserving their original perception and action pathways. On LIBERO-Plus, JEPA-WAM achieves 79.2%, the best result without large-scale robot-policy pretraining, while its pretrained

π_{0.5}

instantiation reaches 86.3%, achieving the best overall performance. Experiments on RoboTwin 2.0 and real-world bimanual manipulation further demonstrate strong generalization under visual and spatial shifts.

Yihan Lin, Jiawei He, Shifeng Bao +6

School of Information, Renmin University of China, Beijing, China · XYZ Embodied AI, Beijing, China · Key Laboratory of Data Engineering and Knowledge Engineering, Beijing, China +3

Efficient World-Action Model Robot Policies Latent Prediction S-Jepa

Ask PDF